{ "version": "1.8.0", "slug": "elevator-mcp-completeness-pack-engine", "title": "MCPVault Clear — Elevator MCP Completeness Pack Engine", "vertical": "Regulatory compliance", "seed": { "s": "elevator-mcp-completeness-pack-engine", "t": "MCPVault Clear — Elevator MCP Completeness Pack Engine", "v": "Regulatory compliance", "r": "Medium-high", "m": "M" }, "product": { "slug": "elevator-mcp-completeness-pack-engine", "project_name": "MCPVault Clear", "project_type": "regulator-fluent compliance documentation workflow application", "vertical": "Regulatory compliance", "audience": "regional multifamily/mixed-use property managers and mid-size owners with 3-40 elevator-equipped buildings", "geography": "US, Colorado Front Range beachhead first; Fairfax County VA / Northern Virginia secondary; AHJ rule library expandable", "scale_expectation": "8-20 buildings under Portfolio Desk in year one; per-building pack volume with inspection-cycle seasonality; high artifact fidelity", "core_workflows": [ "MCP intake & evidence normalization", "Gap matrix scoring against ASME A17.1 §8.6 / AHJ checklist", "Analyst release & licensed elevator consultant escalation", "Vendor chase kit & vault index delivery" ], "discovery": { "one_line_purpose": "On MCPVault Clear, facilities coordinators stop guessing whether an elevator's Maintenance Control Program will survive an AHJ inspection and start proving it. Vendor logs and machine-room photos are extracted at intake, the gap matrix runs against the adopted ASME A17.1 §8.6 checklist, and every Completeness Pack releases with a dated vault index a compliance analyst has signed.", "primary_users": [ "facilities coordinators, PM directors, and risk/facilities VPs at regional multifamily and mixed-use ownership groups", "Compliance analyst / licensed elevator consultant (QEI) on escalation", "AHJ inspector, insurer, or lender diligence team (read-only)" ], "jobs_to_be_done": [ "Produce the ASME A17.1 §8.6 owner-side MCP record for every conveyance without hiring a full-time elevator compliance coordinator", "Catch hard gaps - missing MCP, no on-site accessibility instructions, short retention - before an AHJ inspector does", "Hand an inspector, insurer, or acquiring owner a dated vault index on demand when a vendor changes or a portfolio trades" ], "value_prop": "MCPVault Clear turns a scattered, multi-vendor elevator paperwork trail into a released, analyst-signed §8.6 Completeness Pack - reconstructable on demand, gap-matrix cited, with the owner always the responsible party of record.", "competitors": [ "Full-service elevator consultants who price MCP audits as bespoke, project-length engagements", "OEM/service vendors (Otis, KONE, TKE, Schindler) who write the MCP but have no incentive to prove its completeness independently", "SaaS compliance trackers the facilities team is expected to operate themselves" ], "differentiation": "Done-for-you Completeness Packs, not a dashboard: deterministic hard-gap rules (no MCP, no on-site accessibility instructions, under 5-year retention, missing FEO tests), analyst release on every pack, licensed elevator consultant/QEI escalation only for missing-MCP-authorship or contested code interpretation, and an explicit gap matrix instead of invented log lines.", "positioning_statement": "For facilities coordinators and property management leaders at regional multifamily and mixed-use ownership groups with 3-40 elevator buildings, MCPVault Clear is the done-for-you documentation service that turns scattered vendor MCP paperwork into a released, AHJ-checklist-cited Completeness Pack - unlike full-service elevator consultants who price bespoke engagements, or SaaS trackers that leave the completeness work on your staff." }, "assumptions": [ { "id": "elevator-mcp-completeness-pack-engine-a1", "statement": "Regional PM buyers will pay a flat per-building fee for an analyst-released Completeness Pack rather than treat a free vendor-supplied MCP PDF as good enough.", "confidence": "medium", "impact_if_wrong": "severe", "revisit_trigger": "First 5 design-partner sales calls in Colorado Front Range - reject if willingness-to-pay signal is absent." }, { "id": "elevator-mcp-completeness-pack-engine-a2", "statement": "A single-building MCP Completeness Pack can be reconstructed from owner-supplied evidence (MCP, logs, callbacks, inspections, photos) within the 7-business-day standard cycle.", "confidence": "low", "impact_if_wrong": "high", "revisit_trigger": "First real customer onboarding cycle." }, { "id": "elevator-mcp-completeness-pack-engine-a3", "statement": "AHJs and elevator-consultant partners will tolerate an AI-assisted extraction and gap-scoring layer when the release is explicit, analyst-signed, and consultant-escalated on contested cases.", "confidence": "medium", "impact_if_wrong": "high", "revisit_trigger": "First AHJ inspection or consultant-partner interaction referencing a released pack." }, { "id": "elevator-mcp-completeness-pack-engine-a4", "statement": "Logical per-tenant data isolation with row-level auth is acceptable for the first cohort of buildings; single-tenant hosting is not required.", "confidence": "medium", "impact_if_wrong": "high", "revisit_trigger": "Any prospect (insurer or lender diligence team) with a hard single-tenant clause." }, { "id": "elevator-mcp-completeness-pack-engine-a5", "statement": "Manifest-backed blueprint reflects a real Colorado/Fairfax elevator-MCP workflow, not a synthetic scenario.", "confidence": "medium", "impact_if_wrong": "medium", "revisit_trigger": "First customer walkthrough of the intended workflow." } ], "unknowns": [ { "id": "elevator-mcp-completeness-pack-engine-u1", "question": "Which licensed elevator consultant/QEI will sign off on escalated (red) packs?", "blocks": "Any commercial claim; AHJ-facing delivery on missing-MCP-authorship cases.", "resolution_path": "Named consultant + engagement letter on file before commercial engagement." }, { "id": "elevator-mcp-completeness-pack-engine-u2", "question": "Which AHJ editions and jurisdictions are in scope for launch beyond Colorado and Fairfax County?", "blocks": "Rule-library coverage; checklist card accuracy; canonical/hreflang.", "resolution_path": "Owner confirms in-scope AHJ list in the owner-action pack." }, { "id": "elevator-mcp-completeness-pack-engine-u3", "question": "What is the actual willingness-to-pay above the $1,450-$2,850 pack band across portfolio sizes?", "blocks": "Pricing hypothesis; Portfolio Desk tier economics.", "resolution_path": "5 design-partner discovery calls with explicit pricing conversation." }, { "id": "elevator-mcp-completeness-pack-engine-u4", "question": "Which existing systems (vendor portals, PM software, insurer portals) must intake integrate with day one?", "blocks": "Architecture module boundaries; data-in/out contracts.", "resolution_path": "Design-partner tech-inventory questionnaire." }, { "id": "elevator-mcp-completeness-pack-engine-u5", "question": "Is there a data-residency or litigation-discovery constraint on the evidence vault?", "blocks": "Deployment topology; vault retention policy.", "resolution_path": "Vendor-diligence questionnaire from first prospect; MSA legal review of vault subpoena exposure." } ], "expert_panel": [ { "role": "Product Strategy", "key_concern": "Is the ICP narrow enough to earn a first design-partner cohort without diluting into full elevator consulting?", "recommendation": "Constrain launch to Colorado Front Range multifamily/mixed-use PMs with 3-40 elevator buildings; broaden to Fairfax County only after 5 signed design partners.", "dissent": "May under-price the national installed-base opportunity and slow the fundraising narrative." }, { "role": "Software Architecture", "key_concern": "Are we defaulting to microservices without justification for a document-extraction workload?", "recommendation": "Single deployable modular monolith with a documented seam for the OCR/extraction module, the highest-volume path.", "dissent": "May look unsophisticated to enterprise reviewers expecting a service-mesh diagram." }, { "role": "Frontend / UX", "key_concern": "Is the gap matrix visible and trustable in every workflow screen?", "recommendation": "Every artifact view renders checklist clause to evidence pointer to release signature in one glance, styled as a machine-room register.", "dissent": "Adds vertical density that non-domain reviewers may call cluttered." }, { "role": "Backend / Data", "key_concern": "Is the vault index append-only and reconstructable given the litigation-discovery exposure of maintenance records?", "recommendation": "Event-sourced audit log for all pack state transitions; hash-stamped evidence snapshots; versioned rule tables per AHJ edition.", "dissent": "Higher write-path complexity than plain CRUD; discipline required as AHJ editions change." }, { "role": "AI / ML", "key_concern": "Are extraction outputs grounded, cited, and gated against fabricated log lines?", "recommendation": "Retrieval-first OCR/extraction with source-span citations, structured output validation, and human release gate before delivery.", "dissent": "Slower than open-ended chat; may frustrate prospects expecting instant AI certification." }, { "role": "Security", "key_concern": "Is the STRIDE surface documented for a vault holding subpoena-exposed maintenance records?", "recommendation": "Threat model per module, per-tenant row-level auth, secrets in managed KMS, dependency scanning in CI.", "dissent": "Overhead in early prototype; some controls can wait until first paying portfolio customer." }, { "role": "Privacy / Compliance", "key_concern": "Is the compliance target realistic given the vault's litigation-discovery risk?", "recommendation": "SOC 2 Type I in year one with mapped controls for Type II; client-owned vault export option to limit discovery exposure.", "dissent": "May lock out enterprise buyers requiring ISO/HITRUST on day one." }, { "role": "DevOps / Reliability", "key_concern": "Is the ops model boring enough to run without a dedicated SRE during inspection-cycle demand spikes?", "recommendation": "Single production region + managed database + edge delivery; SLO published as availability + p95 latency only.", "dissent": "Single region concentrates risk during a regional outage at peak inspection season." }, { "role": "Data / Analytics", "key_concern": "Are the leading indicators (cycle time, escalation rate, cure rate) wired before launch?", "recommendation": "Instrument intake-to-release cycle time, escalation-to-consultant rate, and hard-gap cure rate; ship dashboards before first design partner.", "dissent": "Analytics scope-creep can steal weeks from core extraction and rules work." }, { "role": "Accessibility", "key_concern": "Does the analyst release workflow meet WCAG 2.2 AA for every screen a reviewer uses?", "recommendation": "Enforce keyboard-only walkthrough for the gap-matrix and release screens; add axe-core to CI on reviewer surfaces.", "dissent": "Density-heavy ledger UI is hard to ship AA-clean quickly." }, { "role": "SEO / Content", "key_concern": "Is the microsite claim honest and gated on evidence, avoiding any implied inspection guarantee?", "recommendation": "Regulator-fluent topical-authority content only (Colorado 7 CCR 1101-8, Fairfax MCP custody); no fake reviews, no LocalBusiness identity schema until owner facts close.", "dissent": "Slower content velocity than a generic SaaS blog." }, { "role": "Executive Sponsor", "key_concern": "Is there a written kill criterion given elevator-consultant channel-conflict risk?", "recommendation": "Kill/pivot decision at 90 days if no design-partner LOI, or if escalation-to-consultant rate exceeds 15% of packs.", "dissent": "Founders often resist naming kill criteria in writing." } ], "strategy": { "business_model": "Per-building outcome pricing with a recurring Portfolio Desk subscription tier", "revenue_streams": [ "MCP Completeness Pack (flat per-building fee)", "Pre-Inspection Rush add-on", "Vendor Cure Chase Desk add-on", "Portfolio Desk monthly subscription (5-40 buildings)" ], "moat": [ "AHJ edition rule library accumulated per jurisdiction", "Vault index history per building/conveyance", "Licensed elevator consultant escalation relationships" ], "gtm": [ "Founder-led design partner cohort (Colorado Front Range, 5-10 buildings)", "Free MCP Gap Scan lead magnet", "AHJ/industry roundtable presence and elevator-vendor referral partnerships" ], "pricing_hypothesis": "Design-partner packs priced at the low end of the $1,450-$2,850 band; commercial tier validated against consultant audit pricing and coordinator-hour opportunity cost before Portfolio Desk scale-up.", "kill_criteria": [ "No signed design-partner LOI in 4 weeks", "Scan-to-paid conversion below 25% after 8 pilots or rework above 25%", "Escalation-to-consultant rate exceeds 15% of packs sustained over a quarter", "Elevator-consultant partner channel issues a written competitive objection" ] }, "security": { "stride": [ { "threat": "Spoofing", "scenario": "Attacker attempts to impersonate a compliance analyst to release a fabricated Completeness Pack.", "mitigation": "SSO with MFA; release signatures bound to a cryptographic session claim, not a form field." }, { "threat": "Tampering", "scenario": "Historical gap-matrix entries edited after the fact to hide an unresolved hard gap.", "mitigation": "Append-only audit log; hash-chained vault-index snapshots; diff view on every analyst release surface." }, { "threat": "Repudiation", "scenario": "Analyst or consultant denies releasing a delivered Completeness Pack.", "mitigation": "Signed attestations with server-side timestamp + releaser identity; export bundle includes signature manifest." }, { "threat": "Information Disclosure", "scenario": "Cross-tenant leak of Regulated-record, PII, or Internal-audit data through shared retrieval indices or logs.", "mitigation": "Tenant-scoped row-level auth; PII scrubbing in logs; AHJ retrieval indices partitioned per tenant." }, { "threat": "Denial of Service", "scenario": "Runaway OCR/extraction job or export exhausts shared workers during an inspection-season demand spike.", "mitigation": "Per-tenant concurrency + budget caps; circuit breaker on model calls; degrade-gracefully queue." }, { "threat": "Elevation of Privilege", "scenario": "Standard user acquires analyst or consultant-release capability via a workflow shortcut.", "mitigation": "Roles stored in a separate table; capability checks server-side; no client-only role checks." } ], "privacy_posture": "Data-minimization by default; per-tenant isolation; DPA templates on file; client-owned vault export option to limit litigation-discovery exposure.", "compliance_targets": [ "ASME A17.1 §8.6.1.4 5-year record retention", "SOC 2 Type II", "ISO 27001 (year two)" ], "data_classifications": [ "Regulated-record", "PII", "Internal-audit" ] }, "devops": { "ci_cd": "PR -> typecheck + unit + snapshot tests -> preview deploy -> main auto-deploys to a single production region; AHJ rule-table migrations gated on review.", "environments": [ "local", "preview (per-PR)", "staging (shared)", "production (single region + multi-AZ)" ], "observability": [ "Structured logs with tenant + request IDs", "RED metrics per workflow", "Error tracking with source maps", "Model-call spans with cost + latency", "Weekly SLO review" ], "testing_pyramid": [ "Unit tests on gap-matrix scoring and hard-gap rule modules", "Component tests on analyst release surfaces", "Contract tests on AHJ rule-library integrations", "End-to-end smoke test on the intake -> release -> delivery path" ], "accessibility_tests": [ "axe-core in CI on analyst release surfaces", "Keyboard-only walkthrough per workflow", "Prefers-reduced-motion honored" ], "performance_budget": "p95 workflow latency published per module; gap-matrix generation cold-path under 30s or shown as background job." }, "accessibility_i18n_ethics": { "wcag_target": "AA", "locales": [ "en-US" ], "rtl_support": false, "ethical_risks": [ "Pack released without analyst review", "AHJ edition mismatch producing a false hard gap or a missed one", "AHJ-facing errors attributed to AI", "Mis-selling the pack as an engineering or QEI service" ], "ethical_guardrails": [ "Human analyst release required before delivery; consultant escalation for missing-MCP-authorship or contested interpretation", "Per-AHJ-edition rule-card isolation with dated citations", "Standing disclaimer on every pack: documentation-readiness support only, owner remains responsible party" ] }, "governance": { "ownership": [ { "area": "Product + roadmap", "owner": "Executive Sponsor" }, { "area": "Architecture + platform", "owner": "Engineering Lead" }, { "area": "Gap matrix + release workflow", "owner": "Named compliance analyst" }, { "area": "Compliance + privacy", "owner": "Compliance Lead" }, { "area": "Design system", "owner": "Design Lead" }, { "area": "SEO + content", "owner": "Content Lead" } ], "docs_required": [ "ADR log (checked in)", "Owner-action ledger", "Gap matrix evidence register", "STRIDE threat model", "Runbook: incident, restore, breach notification", "Analyst/consultant release playbook + signature policy" ], "naming_conventions": [ "kebab-case slugs for blueprints and routes", "camelCase for TypeScript identifiers", "SCREAMING_SNAKE_CASE for environment variables", "Verb-first action names (e.g., generate-completeness-pack)" ], "change_control": "ADR-per-major-decision; AHJ rule-table migrations require review; production deploys gated on green CI + owner-action ledger check." }, "risk_register": [ { "id": "elevator-mcp-completeness-pack-engine-r1", "risk": "AHJ-facing claim in a released pack proves incorrect (wrong edition, misapplied clause)", "likelihood": "medium", "impact": "severe", "mitigation": "Every hard gap cites a dated checklist clause + evidence pointer; analyst release required", "contingency": "Retraction workflow; customer-notification template; audit-log export within 24 hours", "owner": "legal" }, { "id": "elevator-mcp-completeness-pack-engine-r2", "risk": "AI hallucination / fabricated log line in a delivered pack", "likelihood": "medium", "impact": "high", "mitigation": "Retrieval-first extraction + structured output validation + anti-fabrication QA sampling + analyst release gate", "contingency": "Analyst-triggered rollback + regeneration; incident postmortem published to customer", "owner": "engineering" }, { "id": "elevator-mcp-completeness-pack-engine-r3", "risk": "Cross-tenant data leak of vault-indexed maintenance records", "likelihood": "low", "impact": "severe", "mitigation": "Row-level auth + per-tenant retrieval indices + log-scrubbing", "contingency": "Breach-notification runbook; forced credential rotation; scoped tenant kill switch", "owner": "engineering" }, { "id": "elevator-mcp-completeness-pack-engine-r4", "risk": "Design partner churns before contract, or elevator-consultant partner perceives competitive threat", "likelihood": "medium", "impact": "high", "mitigation": "Weekly working-session cadence; documented value moments; consultant revenue-share on escalations", "contingency": "Structured exit interview; write learnings into ICP + pricing hypothesis", "owner": "owner" }, { "id": "elevator-mcp-completeness-pack-engine-r5", "risk": "Analyst shortage during inspection-season demand spike (early demand trap)", "likelihood": "high", "impact": "high", "mitigation": "Hard pilot cap at 8 buildings; build-before-scale gates; SOC 2 Type I year one", "contingency": "Pause new logo intake; contract framework carve-out with legal review", "owner": "ops" }, { "id": "elevator-mcp-completeness-pack-engine-r6", "risk": "Single-region outage takes production down during a rush-pack cycle", "likelihood": "low", "impact": "high", "mitigation": "Multi-AZ managed database; nightly cross-region backup", "contingency": "Documented restore-to-DR runbook; RTO 8h / RPO 1h during pilot", "owner": "engineering" } ], "roadmap": [ { "phase": "Phase 0 - Discovery + design-partner LOI", "weeks": "Weeks 1-4", "outcomes": [ "3-5 Colorado Front Range design-partner LOIs", "Gap Scan evidence pack from each partner", "Written ICP + pricing hypothesis" ], "exit_criteria": [ "≥3 LOIs signed", "Owner-action ledger populated per partner", "Licensed elevator consultant identity confirmed" ], "kill_criteria": [ "<2 LOIs after 4 weeks", "No willingness-to-pay signal above cost baseline" ] }, { "phase": "Phase 1 - Thin vertical slice", "weeks": "Weeks 5-10", "outcomes": [ "Intake -> gap matrix -> analyst release -> delivery working end-to-end for one building", "Vault index audit trail wired", "Instrumentation live" ], "exit_criteria": [ "1 real Completeness Pack delivered + analyst-released", "p95 workflow latency published" ], "kill_criteria": [ "Analyst release cycle >7 business days", "Vault index cannot be reconstructed on demand" ] }, { "phase": "Phase 2 - Design-partner cohort", "weeks": "Weeks 11-20", "outcomes": [ "3-5 buildings in weekly production use", "First paid Completeness Pack conversion", "SOC 2 Type I scoping" ], "exit_criteria": [ "≥1 paid contract", "Scan-to-paid conversion signal captured", "Postmortem cadence in place" ], "kill_criteria": [ "No paid conversion by week 20", "Escalation-to-consultant rate exceeds 15% without contract offset" ] }, { "phase": "Phase 3 - Commercial launch", "weeks": "Weeks 21-36", "outcomes": [ "Public commercial launch of the microsite as 'ready'", "SOC 2 Type I completed", "Owner-action ledger closed for launched blueprint" ], "exit_criteria": [ "Zero blocking owner actions for launched blueprint", "Publicly indexable microsite with WebPage+FAQPage schema only" ], "kill_criteria": [ "Public launch not defensible against a plausible AHJ or consultant-channel inquiry" ] } ], "metrics": { "north_star": "Released Completeness Packs per week, per building, with zero re-issues for defects of our making", "leading": [ "Design-partner LOIs signed", "Intake -> pack cycle time", "Analyst release cycle time", "Escalation-to-consultant rate", "Hard-gap cure rate within 30 days" ], "lagging": [ "Paid packs signed", "Portfolio Desk net revenue retention (post first cohort)", "AHJ or consultant-channel objection count (target: 0)", "Retraction count on delivered packs (target: 0)" ], "guardrails": [ "Model spend per tenant per week", "PII in logs (target: 0)", "Cross-tenant access attempts (target: 0)", "p95 workflow latency ceiling" ] }, "executive_review": { "consensus": "Ship a thin, gap-matrix-linked, analyst-released vertical slice for MCPVault Clear. Prefer a boring, single-region modular monolith. Do not launch commercially until owner-action facts close and at least one analyst-released Completeness Pack is delivered.", "dissent": "Executive Sponsor and Privacy/Compliance disagree on launch tempo - Privacy recommends waiting for SOC 2 Type II mapping before any public commercial claim.", "go_no_go": "conditional-go", "top_3_risks": [ "AHJ-facing claim in a released pack proves incorrect", "AI hallucination / fabricated log line in a delivered pack", "Cross-tenant data leak of vault-indexed maintenance records" ], "first_10_steps": [ "Confirm the named licensed elevator consultant/QEI + engagement letter on file", "Populate owner-action ledger with entity, jurisdiction, contact inbox, privacy inbox", "Open 5 design-partner discovery calls in Colorado Front Range with explicit pricing conversation", "Write ICP + kill/pivot criteria in the plan file", "Stand up the intake -> gap matrix -> analyst release -> delivery loop", "Wire append-only audit log + hash-chained vault-index snapshots", "Add row-level auth + tenant-scoped AHJ retrieval indices", "Instrument intake-to-release cycle time, escalation rate, and cure-rate events", "Publish the microsite with WebPage+FAQPage schema only and noindex until owner-facts close", "Schedule the 90-day kill/pivot review with executive sponsor" ] } }, "project_site": { "slug": "elevator-mcp-completeness-pack-engine", "app_name": "MCPVault Clear Desk", "archetype": "filing-dossier", "archetype_label": "machine room register desk", "reader_role": "Facilities Coordinator", "one_sentence_app": "MCPVault Clear Desk is a machine room register desk for facilities coordinators who need every elevator's Maintenance Control Program tied to a §8.6-complete record before an AHJ inspector, insurer, or vendor change asks for the binder.", "homepage_sequence": [ "scene", "workflow", "instrument", "offer", "proof", "qualification", "objections" ], "hero": { "frame_label": "Facilities / Compliance · machine room register desk", "eyebrow": "Facilities Coordinator / failed inspection citing MCP or a vendor-change trigger", "interface_title": "MCPVault Clear release desk", "primary_panel_title": "Riverbend Commons · Conveyance 2 of 3 · gap matrix: 2 hard gaps open", "primary_panel_body": "Open pack run: extract the MCP and vendor logs, score against the adopted ASME A17.1 §8.6 / Colorado OPS checklist, then stage the Completeness Pack for analyst release.", "side_panel_title": "Before this ships", "side_panel_items": [ "On-site accessibility instructions confirmed", "5-year retention window checked per conveyance", "Vault index row staged" ], "status_metric": "REVIEW", "status_label": "release gate active" }, "language": { "problem_heading": "The Facilities Coordinator moment", "mechanism_heading": "Inside the MCPVault Clear Desk", "proof_heading": "Why this survives an inspection", "offer_heading": "What leaves the room", "objection_heading": "The hard questions", "qualification_heading": "Who should not use this", "cta_close": "Open a pack run from your most recent MCP and vendor logs — released by a real compliance analyst, escalated to a licensed elevator consultant/QEI when a pack goes red." }, "modules": [ { "name": "MCP intake", "job": "Turns an uploaded MCP, vendor log set, and machine-room photos into a named pack run with a conveyance match, extracted fields, and a missing-evidence list.", "artifact": "triage record" }, { "name": "Gap matrix", "job": "Holds the line-by-line comparison of every required §8.6 / AHJ checklist item against the evidence on file, flagging hard gaps with the clause and evidence pointer behind each.", "artifact": "gap matrix worksheet" }, { "name": "Completeness Pack", "job": "Packages the gap matrix, evidence inventory, punch list, vendor chase kit, and dated vault index into the record an AHJ inspector can review without a meeting.", "artifact": "release package" } ], "checkpoints": [ { "label": "§8.6 checklist item", "pass": "extracted with source citation", "fail": "chased or shipped as explicit gap" }, { "label": "hard-gap rule", "pass": "deterministic gate, evidence-pointer cited", "fail": "blocked before release" }, { "label": "Completeness Pack", "pass": "analyst releases (consultant releases on red)", "fail": "stays draft" } ], "signature_scene": "You're a facilities coordinator at Riverbend Commons. A tenant complaint sent an inspector out last week, and the citation reads 'MCP not on file for Conveyance 2.' The vendor that wrote it left with the last contract. Someone needs to know today whether that's a hard gap or a documentation mix-up, and the only paper trail is a folder of PDFs from three different elevator companies. This page is built like the machine room register desk that person needed before the re-inspection date." }, "ddd": { "slug": "elevator-mcp-completeness-pack-engine", "project_name": "MCPVault Clear", "business_understanding": { "summary": "MCPVault Clear — On MCPVault Clear, multifamily and commercial owners stop guessing whether their Elevator Maintenance Control Program (MCP) will survive an AHJ inspection. Vendor MCPs, service logs, callbacks, and inspection reports are extracted at intake, checked against a jurisdiction-specific ASME A17.1 §8.6 checklist in deterministic code, and every Completeness Pack releases with a dated, cited vault index.", "customer_profile": "regional multifamily / mixed-use property managers and mid-size owners with 3-40 elevator-equipped assets in high-enforcement AHJs (beachhead: Colorado Front Range; secondary: Fairfax County VA / Northern Virginia)", "customer_pain": "Most owners have never reviewed their own MCP. A missing, generic, or inaccessible MCP is treated by the AHJ as an inspection-failure condition independent of equipment condition; the MCP can 'walk' with an outgoing vendor; five-year maintenance/callback/FEO-test records are scattered across 2-4 vendors; nobody has a released, checklist-cited proof of completeness before an inspection, insurer request, or vendor change.", "paid_outcome": "A specialist-released Elevator MCP Completeness Pack per building (or per-conveyance add-on): gap matrix mapped to ASME A17.1 §8.6 / AHJ checklist, evidence inventory, punch list, vendor chase kit, accessibility-instruction template, and a dated vault index — plus an optional Managed Vendor Cure Chase Desk and a recurring Portfolio Desk with quarterly re-scans.", "value_creation": "AI compresses OCR, AHJ-checklist matching, gap scoring, and chase-letter drafting; deterministic code owns every hard-fail gate (no MCP, no on-site accessibility instructions, retention under five years, missing FEO tests); a compliance analyst releases the pack for green/yellow packs and a licensed elevator consultant / QEI is engaged only for missing-MCP authorship or contested code interpretation; the platform binds them with an append-only audit trail and a dated vault index.", "why_ai_native": "The extract-score-release-chase loop is only economical with a bounded AI layer feeding deterministic rules. A pure-manual audit service cannot hit $1,450-$2,850 pack pricing at the cycle times owners need before an inspection; a pure-automated SaaS tracker cannot chase vendors, hold the release gate, or absorb the judgment calls (missing MCP, contested code citation) that keep the pack defensible.", "operational_risks": [ "Compliance analyst bottleneck during high-enforcement season (Colorado 2026 rule awareness spike)", "AHJ edition mismatch causing a false hard-fail", "OEM/vendor refusal to share MCP or service logs", "Fabricated or hallucinated log dates in a released pack", "DeviceClear brand confusion undermining positioning" ], "assumptions": [ "The target audience will pay for a released, checklist-cited documentation-completeness pack over a free vendor-supplied PDF.", "A Completeness Pack can be reconstructed from an owner-supplied evidence set within the standard 7-business-day cycle.", "The vertical tolerates AI-assisted extraction and drafting when compliance-analyst review is explicit and audit-traceable.", "Logical per-tenant isolation with row-level auth is acceptable for the first cohort — single-tenant infrastructure is not required.", "Colorado Front Range and Fairfax County enforcement signals generalize to other high-enforcement AHJs as the rule library expands." ], "validation_questions": [ "Which licensed elevator consultant / QEI will sign red (missing-MCP or contested-citation) packs?", "Which AHJ editions are in scope for launch beyond Colorado and Fairfax County?", "What is the actual willingness-to-pay once a Gap Scan shows a generic or incomplete MCP?", "Which vendor invoice / CMMS systems must intake integrate with on day one?", "Is there a data-residency or client-owned-vault constraint given litigation-discovery risk?" ] }, "domain_discovery": { "actors": [ { "actor": "Customer operator", "role": "facilities coordinator / building engineer or property manager who herds Otis/KONE/TKE/Schindler vendors", "goals": [ "Prove MCP + five-year documentation readiness before the next inspection", "Keep the MCP and records with the building when a vendor changes" ], "decisions": [ "Submit conveyance intake", "Accept or request revisions on the draft gap matrix", "Approve outbound delivery of the Completeness Pack" ], "pain_points": [ "Records scattered across 2-4 vendors and formats", "No independent proof the MCP is equipment-specific", "Discovering a hard gap only after a failed inspection" ] }, { "actor": "Compliance analyst", "role": "Releases green/yellow Completeness Packs; the everyday human chokepoint", "goals": [ "Release only packs whose claims are evidence-cited", "Keep cycle time inside the 7-business-day (5 for rush) standard" ], "decisions": [ "Release, request revision, or escalate to consultant", "Confirm vendor cure evidence closes a hard gap" ], "pain_points": [ "Incomplete machine-room photo evidence", "Ambiguous AI extraction on non-standard vendor invoice formats", "Analyst shortage during high-enforcement season" ] }, { "actor": "Licensed elevator consultant / QEI", "role": "Authors or certifies a new technical MCP when one is missing; interprets contested code citations; advises on alterations/modernization; engaged only on escalation (red packs)", "goals": [ "Release only technically defensible red packs", "Avoid being pulled into full VT program consulting scope" ], "decisions": [ "Author/certify a missing MCP or decline", "Interpret a contested AHJ code citation" ], "pain_points": [ "Perceiving MCPVault as a competitive threat rather than a referral funnel", "Scope creep from documentation review into full consulting" ] }, { "actor": "AHJ / Regulator", "role": "Colorado OPS, Fairfax County Elevator Program, and other adopting jurisdictions; inspects on demand and treats a missing/incomplete MCP as an inspection-failure condition", "goals": [ "Confirm the equipment-specific MCP and five-year records exist and are accessible on-site" ], "decisions": [ "Accept, cite, or red-tag a conveyance based on MCP completeness" ], "pain_points": [ "Generic, non-equipment-specific MCPs presented as compliant", "MCPs that walked with an outgoing vendor" ] }, { "actor": "AI extraction/orchestration layer", "role": "OCRs and classifies intake documents, drafts the gap matrix and vendor chase letters, scores confidence, escalates on ambiguity; never invents dates, procedures, or citations", "goals": [ "Produce a fully cited gap-matrix draft", "Escalate rather than guess on ambiguous equipment or AHJ edition matches" ], "decisions": [ "Draft vs escalate", "Which AHJ edition and checklist cards to cite" ], "pain_points": [ "Heterogeneous vendor invoice formats", "Sparse machine-room photo evidence" ] }, { "actor": "Platform admin", "role": "Runs the tenant, manages users/integrations (internal, not customer-facing)", "goals": [ "Keep the system safe, observable, and edition-current" ], "decisions": [ "Provision users", "Rotate secrets and manage feature flags" ], "pain_points": [ "Change management across tenants and AHJ editions" ] } ], "glossary": [ { "term": "MCP", "definition": "The equipment-specific written Maintenance Control Program required under ASME A17.1 §8.6.", "used_by": "Customer operator, Compliance analyst, Licensed elevator consultant/QEI", "context": "Completeness Pack Fulfillment", "example": "\"Does the MCP on file name this conveyance's specific equipment, or is it generic boilerplate?\"", "notes": "Never abbreviate to a different term; always 'MCP.'" }, { "term": "Completeness Pack", "definition": "The released deliverable for one building/conveyance: gap matrix, evidence inventory, punch list, vendor chase kit, accessibility-instruction template, and dated vault index.", "used_by": "Customer operator, Compliance analyst, Licensed elevator consultant/QEI", "context": "Completeness Pack Fulfillment", "example": "\"Ship the Completeness Pack once the analyst releases it.\"", "notes": "Immutable once released; corrections go through PackRetraction." }, { "term": "Gap matrix", "definition": "The line-by-line comparison of required ASME A17.1 §8.6 / AHJ checklist items vs. the evidence that actually exists.", "used_by": "AI extraction/orchestration layer, Compliance analyst, Licensed elevator consultant/QEI", "context": "Completeness Pack Fulfillment", "example": "\"The gap matrix shows callback logs missing for two of the last five years.\"", "notes": "Every line cites evidence or is marked an explicit gap; never invented." }, { "term": "Hard gap", "definition": "A checklist item an AHJ treats as an inspection-failure condition: no MCP; no on-site accessibility instructions; under five-year retention; missing FEO test where required.", "used_by": "Compliance analyst, Licensed elevator consultant/QEI, Customer operator", "context": "Completeness Pack Fulfillment", "example": "\"Flag this as a hard gap — the machine room has no accessible MCP copy.\"", "notes": "Also called hard-fail; distinguish from a soft/administrative gap." }, { "term": "Gap Scan", "definition": "The free, scored, preview-only lead magnet for one building / up to two elevators; not a released pack, not a certificate.", "used_by": "Customer operator, AI extraction/orchestration layer", "context": "Sales & Intake", "example": "\"Run the free Gap Scan before committing to a paid Completeness Pack.\"", "notes": "Never call it a certificate or a release." }, { "term": "Vault index", "definition": "The dated, versioned index of every evidence item behind a Completeness Pack.", "used_by": "Compliance analyst, Customer operator", "context": "Completeness Pack Fulfillment", "example": "\"The vault index lists every invoice, log, and photo cited in this pack.\"", "notes": "Append-only; a retraction adds an entry, it never deletes one." }, { "term": "Chase kit / vendor chase letter", "definition": "The drafted demand-letter templates used to recover missing vendor records.", "used_by": "AI extraction/orchestration layer, Compliance analyst", "context": "Vendor Chase Desk", "example": "\"Send the vendor chase letter for the missing 2023 callback log.\"", "notes": "Distinct from an owner action; a chase letter targets the vendor, not the owner." }, { "term": "Release", "definition": "The compliance analyst's (or, on escalation, the consultant's) signed attestation that a pack is complete and its citations are sourced.", "used_by": "Compliance analyst, Licensed elevator consultant/QEI", "context": "Release & Quality Assurance", "example": "\"Analyst release bound to session + timestamp.\"", "notes": "Never 'approval,' never 'certification,' never an ambiguous 'signoff' — always paired with who: 'analyst release' or 'consultant release.'" }, { "term": "Escalation", "definition": "Routing a pack from AI drafting or analyst review to the licensed consultant; used for 'no MCP exists' and contested-interpretation cases.", "used_by": "AI extraction/orchestration layer, Compliance analyst, Licensed elevator consultant/QEI", "context": "AI Workbench & Extraction", "example": "\"Escalate — no MCP was ever authored for this conveyance.\"", "notes": "Escalation is a hand-off, never a rejection." }, { "term": "AHJ", "definition": "Authority Having Jurisdiction (Colorado OPS, Fairfax County Elevator Program, etc.).", "used_by": "All actors", "context": "AHJ Rule Library & Retrieval", "example": "\"This conveyance's AHJ adopted the 2025 edition with the networked-control cybersecurity module.\"", "notes": "Always cite the adopted edition; edition mismatch is a top risk." }, { "term": "Conveyance", "definition": "One elevator/escalator unit; a building can have several.", "used_by": "All actors", "context": "Completeness Pack Fulfillment", "example": "\"This building has four conveyances; two are past the base pack tier.\"", "notes": "A pack is priced per building (1-4 conveyances included)." }, { "term": "On-site accessibility instructions", "definition": "The requirement that the MCP (paper or electronic) is viewable at the machine room / on site, not just at the vendor's office.", "used_by": "Customer operator, Compliance analyst, AHJ / Regulator", "context": "Completeness Pack Fulfillment", "example": "\"Photo-verify the login instructions posted at the machine room controller.\"", "notes": "A missing accessibility instruction is itself a hard gap." }, { "term": "Portfolio Desk", "definition": "The recurring multi-building subscription (5-40 buildings) with quarterly re-scans.", "used_by": "Customer operator, Compliance analyst", "context": "Portfolio & Recurring Programs", "example": "\"Enroll the 18-building portfolio in the Portfolio Desk for quarterly re-scans.\"", "notes": "Distinct from a one-time Completeness Pack purchase." }, { "term": "Chase Desk", "definition": "The paid add-on that manages vendor cure-evidence follow-up until hard gaps close.", "used_by": "Compliance analyst, Customer operator", "context": "Vendor Chase Desk", "example": "\"Purchase the Chase Desk to keep chasing the vendor until the callback logs surface.\"", "notes": "Priced per open hard-gap cycle." }, { "term": "Owner action", "definition": "A fact only the building owner can supply, e.g. confirming which vendor currently holds MCP custody, or attesting that no MCP exists.", "used_by": "Customer operator, Compliance & Licensing Governance", "context": "Compliance & Licensing Governance", "example": "\"Owner action open: confirm which vendor currently has custody of the MCP.\"", "notes": "Caps the release at yellow while open." } ], "decisions": [ { "decision": "Accept conveyance intake", "who": "Sales & Intake context (rule + operator override)", "inputs": [ "Customer identity", "Building + conveyance count", "Scope statement (ICP fit)" ], "rule": "Reject if the building is out of ICP (no elevators, or a Class-A tower already retaining a full-service consultant) or the scope statement is missing", "output": "Conveyance intake accepted event", "risk": "Accepting an out-of-scope engagement degrades analyst trust and margin" }, { "decision": "Draft vs escalate", "who": "AI extraction/orchestration layer", "inputs": [ "Evidence coverage", "Confidence score", "Equipment / AHJ edition match certainty" ], "rule": "Escalate below confidence threshold, on an ambiguous equipment match, or when no MCP is found", "output": "Draft-ready gap matrix OR escalation event", "risk": "A silent low-confidence draft erodes analyst trust" }, { "decision": "Release the Completeness Pack", "who": "Compliance analyst (green/yellow) or Licensed elevator consultant/QEI (red)", "inputs": [ "Draft gap matrix", "Full evidence citations", "Hard-gate evaluation results" ], "rule": "Release only if every gap-matrix line cites a source or an explicit gap, AND every hard gap is either cleared or logged as an open owner action", "output": "Pack released event", "risk": "Over-broad release erodes the audit trail and inspection defensibility" }, { "decision": "Flip release readiness on the microsite / marketing claims", "who": "Compliance & Licensing Governance", "inputs": [ "Owner-action ledger status", "Evidence closure", "Legal review flag" ], "rule": "Blocked if any owner action is open OR an unresolved release-blocker evidence gap exists", "output": "Release-decision event OR blocked-release event", "risk": "A premature public claim of inspection-readiness is unretractable in perception" }, { "decision": "Retract a delivered Completeness Pack", "who": "Legal + Licensed elevator consultant/QEI", "inputs": [ "Newly discovered fact (e.g. fabricated vendor evidence)", "Impact assessment" ], "rule": "Retract if any released claim is materially wrong OR unsupported by evidence", "output": "Retraction event + customer notification", "risk": "Delayed retraction compounds litigation-discovery exposure on the vault" } ], "events": [ { "event": "conveyanceIntakeAccepted", "meaning": "A building/conveyance batch is now committed to fulfillment", "trigger": "Operator or auto-rule accepts the intake", "downstream": [ "Normalization + AHJ retrieval scheduled", "AI extraction scheduled" ] }, { "event": "evidenceIngested", "meaning": "Enough MCP/log/callback/inspection/photo evidence exists to extract", "trigger": "Normalization passes the coverage rule", "downstream": [ "Extraction authorized" ] }, { "event": "gapMatrixDrafted", "meaning": "AI extraction produced a cited gap-matrix draft for analyst review", "trigger": "Extraction Agent finishes its run", "downstream": [ "Hard-gate evaluation" ] }, { "event": "hardGatesEvaluated", "meaning": "Deterministic rules ran the hard-fail checks against the draft gap matrix", "trigger": "Rule engine completes evaluation", "downstream": [ "Analyst queue or consultant escalation" ] }, { "event": "escalationRaised", "meaning": "AI or the analyst could not complete safely", "trigger": "Confidence below threshold, no MCP found, or contested code interpretation", "downstream": [ "Consultant queue" ] }, { "event": "packReleased", "meaning": "Compliance analyst or licensed consultant took accountability for the pack", "trigger": "Release signature captured", "downstream": [ "Delivery authorized", "Audit-log snapshot" ] }, { "event": "packDelivered", "meaning": "Completeness Pack + chase kit + vault index handed to the customer", "trigger": "Delivery adapter confirms transmit", "downstream": [ "Billing event", "Customer notification" ] }, { "event": "ownerActionResolved", "meaning": "A blocking owner-supplied fact is now on file", "trigger": "Owner/operator updates the ledger", "downstream": [ "Release-decision recomputation" ] }, { "event": "hardGapCured", "meaning": "Vendor-sourced cure evidence closed a previously flagged hard gap", "trigger": "Analyst confirms vendor cure evidence", "downstream": [ "Gap matrix re-scored" ] }, { "event": "packRetracted", "meaning": "A delivered Completeness Pack is formally withdrawn or corrected", "trigger": "Legal + consultant jointly file", "downstream": [ "Customer notification", "Audit-log append" ] } ] }, "subdomains": [ { "name": "Completeness Pack Fulfillment (evidence-linked extraction + release)", "type": "core", "description": "The end-to-end path from conveyance intake to analyst-released or consultant-released Completeness Pack, with every gap-matrix line cited.", "reason": "This is what customers pay for and what an AHJ inspection tests against.", "business_value": "Direct revenue and inspection defensibility.", "recommendation": "build", "ai_involvement": "high", "human_involvement": "high", "risks": [ "Hallucinated or invented log lines", "Analyst bottleneck during high-enforcement season", "Un-reconstructable vault index" ], "validation_questions": [ "Can the analyst release in <=5 business days on a rush pack?", "Can we reconstruct any past pack's vault index on demand?" ] }, { "name": "AI Workbench & Extraction (bounded agents + retrieval)", "type": "core", "description": "The bounded AI layer that OCRs, classifies, drafts the gap matrix, cites evidence, and escalates — never authors a technical MCP or a final release unassisted.", "reason": "The AI-native competitive edge lives here; misuse here creates every high-severity risk.", "business_value": "Cycle-time and margin advantage over full-service consulting.", "recommendation": "build", "ai_involvement": "high", "human_involvement": "medium", "risks": [ "Prompt injection via vendor invoice content", "Grounding drift on non-standard vendor formats", "Silent low-confidence output" ], "validation_questions": [ "What is the acceptance rate of AI-drafted gap matrices by analysts?", "What percent of runs escalate correctly on missing-MCP or contested-citation cases?" ] }, { "name": "Release & Quality Assurance (analyst/consultant release + retraction)", "type": "core", "description": "Compliance analyst and licensed elevator consultant/QEI release workflow, signature capture, retraction workflow, and audit-log snapshots.", "reason": "Release is the trust primitive of the whole business.", "business_value": "Defensibility; premium pricing over free vendor PDFs.", "recommendation": "build", "ai_involvement": "medium", "human_involvement": "high", "risks": [ "Release-signature spoofing", "Repudiation of a release", "Delayed retraction" ], "validation_questions": [ "Is every release cryptographically bound to an authenticated session?", "Can we replay any past release on demand?" ] }, { "name": "AHJ Rule Library & Retrieval", "type": "supporting", "description": "Per-jurisdiction AHJ edition library (Colorado, Fairfax/VA, expandable) and ASME A17.1 §8.6 checklist cards feeding the extraction layer.", "reason": "Poor or stale AHJ retrieval directly causes false hard-fails.", "business_value": "Drives extraction and release quality.", "recommendation": "build", "ai_involvement": "high", "human_involvement": "medium", "risks": [ "Stale AHJ edition after a rule update", "Cross-tenant retrieval leakage" ], "validation_questions": [ "Is every checklist card dated to its adopted edition?" ] }, { "name": "Compliance & Licensing Governance", "type": "supporting", "description": "Owner-action ledger, release-decision policy, licensing-boundary enforcement (AI may extract/classify/gap-score/draft chase letters; consultant may author/certify MCPs and interpret contested code; the company never inspects, certifies, or practices engineering).", "reason": "Cross-cuts every context; owns 'can we publicly claim this is inspection-ready.'", "business_value": "Prevents category-level and licensing-boundary failure.", "recommendation": "build", "ai_involvement": "low", "human_involvement": "high", "risks": [ "Premature public claim of inspection-readiness", "Mis-selling as engineering / QEI services" ], "validation_questions": [ "Are all owner actions closed before a public release claim?" ] }, { "name": "Sales & Intake", "type": "supporting", "description": "Free Gap Scan lead capture through accepted engagement + scope statement.", "reason": "Feeds Fulfillment; not the differentiator, but if broken, nothing else runs.", "business_value": "Feeds pipeline via the Gap Scan lead magnet.", "recommendation": "build", "ai_involvement": "medium", "human_involvement": "high", "risks": [ "Accepting an out-of-ICP engagement" ], "validation_questions": [ "Do we reject buildings with no elevators or Class-A towers already fully staffed?" ] }, { "name": "Client Onboarding & Tenant Profile", "type": "supporting", "description": "Tenant provisioning, compliance-analyst-of-record registration, existing MCP/evidence-pack import, engagement letter.", "reason": "One-time high-touch step per customer.", "business_value": "Reduces time-to-first-pack.", "recommendation": "build", "ai_involvement": "low", "human_involvement": "high", "risks": [ "No analyst of record registered before intake opens" ], "validation_questions": [ "Is a compliance analyst named per tenant before go-live?" ] }, { "name": "Client Delivery & Success", "type": "supporting", "description": "Delivery adapter, customer portal, revision loop, Portfolio Desk renewal signal.", "reason": "Customer-visible surface; drives retention and Portfolio Desk upsell.", "business_value": "Retention.", "recommendation": "build", "ai_involvement": "low", "human_involvement": "medium", "risks": [ "Silent delivery failure on a pack needed before an inspection date" ], "validation_questions": [ "Do we alert the customer within 1h of any delivery failure?" ] }, { "name": "Vendor Chase Desk", "type": "supporting", "description": "Managed vendor cure-evidence follow-up: drafts and tracks chase letters until a flagged hard gap closes.", "reason": "Monetizes the highest-friction part of the workflow (getting records out of OEM/vendor hands) without becoming unpaid consulting.", "business_value": "Add-on revenue ($650-$1,200 per open hard-gap cycle) and hard-gap cure-rate KPI.", "recommendation": "build", "ai_involvement": "medium", "human_involvement": "medium", "risks": [ "OEM/vendor refusal to share MCP/logs", "Chase Desk scope-creeping into unpaid custom consulting" ], "validation_questions": [ "Is the hard-gap cure rate >=70% within 30 days when the Chase Desk is purchased?" ] }, { "name": "Portfolio & Recurring Programs", "type": "supporting", "description": "Portfolio Desk subscription covering 5-40 buildings with quarterly re-scans and a rolling scorecard.", "reason": "Converts one-time packs into recurring revenue for multi-building owners.", "business_value": "Recurring revenue ($899-$2,499/mo).", "recommendation": "build", "ai_involvement": "low", "human_involvement": "medium", "risks": [ "Portfolio Desk scope-creeping into unpaid custom consulting" ], "validation_questions": [ "Is the quarterly re-scan cadence actually met per enrolled building?" ] }, { "name": "Billing & Revenue", "type": "generic", "description": "Per-pack, Rush, Chase Desk, and Portfolio Desk subscription invoicing, dunning, revenue reporting.", "reason": "Solved category; do not build.", "business_value": "Cash collection.", "recommendation": "buy", "ai_involvement": "low", "human_involvement": "low", "risks": [ "Tax jurisdictional errors" ], "validation_questions": [ "Is Stripe Tax sufficient for Colorado + Virginia launch jurisdictions?" ] }, { "name": "Identity & Access", "type": "generic", "description": "SSO, MFA, RBAC, session management.", "reason": "Solved category.", "business_value": "Table stakes.", "recommendation": "integrate", "ai_involvement": "low", "human_involvement": "low", "risks": [ "Role escalation" ], "validation_questions": [ "Are roles stored in a dedicated table?" ] }, { "name": "Analytics & Reporting", "type": "supporting", "description": "Scan-to-paid, cycle time, hard-gap cure rate, escalation rate, gross margin, and portfolio-scorecard reporting.", "reason": "Drives every operational decision against the brief's KPI targets.", "business_value": "Feedback loop.", "recommendation": "build", "ai_involvement": "low", "human_involvement": "low", "risks": [ "Vanity metrics" ], "validation_questions": [ "Is scan-to-paid >=25% wired as the north-star?" ] }, { "name": "External Integrations (Anti-Corruption Layer)", "type": "supporting", "description": "Adapters to vendor invoice inboxes, elevator-vendor work-order / CMMS platforms, customer document portals, and other tools with translation to internal domain terms.", "reason": "External schemas must never leak into the core.", "business_value": "Enables integration without corrupting the model.", "recommendation": "build", "ai_involvement": "low", "human_involvement": "medium", "risks": [ "Silent schema drift" ], "validation_questions": [ "Do all external calls pass through an ACL translator?" ] } ], "core_domain_analysis": { "primary_core": "Completeness Pack Fulfillment (evidence-linked extraction + release)", "secondary_cores": [ "AI Workbench & Extraction (bounded agents + retrieval)", "Release & Quality Assurance (analyst/consultant release + retraction)" ], "supporting_may_become_core": [ "AHJ Rule Library & Retrieval (as multi-AHJ coverage accumulates)", "Vendor Chase Desk (as hard-gap cure-rate becomes a differentiator)" ], "generic_do_not_distract": [ "Billing & Revenue", "Identity & Access" ], "rationale": "The paid outcome (analyst- or consultant-released, evidence-linked Completeness Pack) lives in Fulfillment, but its defensibility depends on AI Workbench & Extraction and Release & Quality Assurance behaving correctly. Treat all three as core; do not dilute engineering time on generic subdomains." }, "bounded_contexts": [ { "name": "Completeness Pack Fulfillment", "purpose": "Turn accepted conveyance intakes into analyst- or consultant-released Completeness Packs.", "subdomain": "Completeness Pack Fulfillment (core)", "type": "core", "owned_language": [ "Conveyance", "Gap matrix", "Hard gap", "Completeness Pack", "Vault index", "Escalation" ], "owns": [ "Conveyance intake lifecycle", "Gap-matrix state", "Evidence links", "Delivery packet composition" ], "does_not_own": [ "Analyst/consultant identity", "Billing", "Public release-claim decision" ], "primary_actors": [ "Customer operator", "AI extraction/orchestration layer", "Compliance analyst" ], "entities": [ "ConveyanceIntake", "GapMatrix", "Completeness Pack", "Delivery" ], "value_objects": [ "Confidence score", "Evidence citation", "Delivery address" ], "aggregates": [ "ConveyanceIntakeAggregate", "GapMatrixAggregate", "CompletenessPackAggregate" ], "domain_services": [ "Gap-matrix composer", "Delivery adapter" ], "application_services": [ "OpenConveyanceIntake", "IngestEvidence", "StartExtractionRun", "EvaluateHardGates", "DeliverCompletenessPack" ], "commands": [ "OpenConveyanceIntake", "IngestEvidence", "StartExtractionRun", "EvaluateHardGates", "DeliverCompletenessPack" ], "domain_events": [ "ConveyanceIntakeAccepted", "EvidenceIngested", "GapMatrixDrafted", "HardGatesEvaluated", "PackDelivered" ], "policies": [ "Auto-request release when hard-gate evaluation is complete", "Auto-block delivery until release is received" ], "specifications": [ "EvidenceCoverageSpec", "DeliverabilitySpec" ], "invariants": [ "A Completeness Pack cannot be delivered without a valid analyst or consultant Release", "Every gap-matrix line cites at least one evidence item or is marked an explicit gap" ], "ai_agents": [ "Extraction Agent" ], "human_roles": [ "Customer operator", "Compliance analyst" ], "data_owned": [ "ConveyanceIntake", "GapMatrix", "Completeness Pack", "Delivery" ], "inputs": [ "Intake payload", "Ingested evidence", "AHJ retrieval hits" ], "outputs": [ "Released Completeness Pack", "Delivery confirmation" ], "external_integrations": [ "Vendor invoice inboxes", "Elevator-vendor work-order / CMMS platforms" ], "risks": [ "An un-cited gap-matrix line slips into delivery", "Delivery adapter fails silently" ], "interfaces": [ "-> Release & Quality Assurance (request release)", "-> Client Delivery & Success (PackDelivered)", "<- AI Workbench & Extraction (GapMatrixDrafted)" ] }, { "name": "AI Workbench & Extraction", "purpose": "Run bounded AI agents that OCR, classify, draft, cite, and escalate.", "subdomain": "AI Workbench & Extraction (core)", "type": "core", "owned_language": [ "Prompt version", "Confidence score", "Escalation", "Retrieval hit" ], "owns": [ "Prompt registry", "Extraction run log", "Confidence thresholds" ], "does_not_own": [ "Evidence sourcing", "Analyst/consultant release", "Business release decisions" ], "primary_actors": [ "AI extraction/orchestration layer", "Ops (prompt owner)" ], "entities": [ "ExtractionRun", "PromptVersion", "RetrievalHit" ], "value_objects": [ "Confidence score", "Token budget", "Model cost" ], "aggregates": [ "ExtractionRunAggregate" ], "domain_services": [ "Retrieval router", "Output validator", "Escalation router" ], "application_services": [ "StartAgentRun", "ValidateOutput", "PublishPromptVersion" ], "commands": [ "StartExtractionRun", "PublishPromptVersion", "SetConfidenceThreshold" ], "domain_events": [ "GapMatrixDrafted", "EscalationRaised", "PromptVersionPublished" ], "policies": [ "Escalate on confidence < threshold, no MCP found, or contested code interpretation", "Never call the model with cross-tenant retrieval context", "Reject output failing the structured-output validator" ], "specifications": [ "GroundedOutputSpec", "TokenBudgetSpec" ], "invariants": [ "No extraction output leaves this context without passing OutputValidator", "Prompt versions are immutable once published" ], "ai_agents": [ "Extraction Agent", "Routing & Classification Agent", "Eval Agent" ], "human_roles": [ "Ops (prompt owner)" ], "data_owned": [ "Prompt registry", "Extraction run logs", "Confidence thresholds" ], "inputs": [ "Intake context", "AHJ retrieval hits", "Prompt version" ], "outputs": [ "Gap-matrix draft payload", "Escalation event", "Run trace" ], "external_integrations": [ "OpenAI / Anthropic API", "AHJ Rule Library retrieval index" ], "risks": [ "Prompt injection via vendor invoice content", "Retrieval leakage across tenants", "Silent hallucination of log lines or dates" ], "interfaces": [ "-> Completeness Pack Fulfillment (GapMatrixDrafted)", "-> Release & Quality Assurance (EscalationRaised)", "<- AHJ Rule Library & Retrieval (RetrievalHit)" ] }, { "name": "Release & Quality Assurance", "purpose": "Compliance analyst / licensed consultant release workflow, signature capture, retraction workflow, audit-log snapshots.", "subdomain": "Release & Quality Assurance (core)", "type": "core", "owned_language": [ "Release", "Retraction", "Analyst session" ], "owns": [ "Release log", "Analyst/consultant queue", "Retraction workflow" ], "does_not_own": [ "Completeness Pack content", "Public release-claim decision" ], "primary_actors": [ "Compliance analyst", "Licensed elevator consultant / QEI", "Legal reviewer" ], "entities": [ "Release", "PackRetraction", "AnalystSession" ], "value_objects": [ "Release manifest", "Retraction reason" ], "aggregates": [ "ReleaseAggregate", "PackRetractionAggregate" ], "domain_services": [ "Release service", "Retraction service" ], "application_services": [ "ReleasePack", "RejectPack", "RetractPack" ], "commands": [ "ReleasePack", "RetractPack" ], "domain_events": [ "PackReleased", "PackReleaseRejected", "PackRetracted" ], "policies": [ "Only the tenant's registered compliance analyst, or the escalated consultant on red packs, may release", "Retraction requires legal + consultant co-signature" ], "specifications": [ "ReleaserAuthoritySpec", "RetractionPreconditionsSpec" ], "invariants": [ "A Release is bound to a live authenticated session, not a form field", "Released Completeness Packs are immutable; corrections go through PackRetraction" ], "ai_agents": [], "human_roles": [ "Compliance analyst", "Licensed elevator consultant / QEI", "Legal reviewer" ], "data_owned": [ "Releases", "Retractions", "Analyst sessions" ], "inputs": [ "Gap matrix drafted", "Escalation payload" ], "outputs": [ "Release event", "Retraction event" ], "external_integrations": [ "IdP (Okta / Google)" ], "risks": [ "Release-signature spoofing", "Repudiation of a release" ], "interfaces": [ "-> Completeness Pack Fulfillment (PackReleased)", "-> Compliance & Licensing Governance (PackRetracted)" ] }, { "name": "AHJ Rule Library & Retrieval", "purpose": "Own per-jurisdiction AHJ edition library, ASME A17.1 §8.6 checklist cards, and retrieval indices feeding extraction.", "subdomain": "AHJ Rule Library & Retrieval (supporting)", "type": "supporting", "owned_language": [ "AHJ", "AHJ edition", "Checklist card" ], "owns": [ "AHJ rule sets", "Checklist cards", "Retrieval indices" ], "does_not_own": [ "Prompt versions", "Model calls" ], "primary_actors": [ "Ops (prompt owner)" ], "entities": [ "AHJRuleSet", "ChecklistCard", "IndexShard" ], "value_objects": [ "Edition citation", "SourceCitation" ], "aggregates": [ "AHJRuleSetAggregate" ], "domain_services": [ "Ingestion pipeline", "Reindex service" ], "application_services": [ "IngestRuleUpdate", "Reindex", "PurgeStaleEdition" ], "commands": [ "IngestRuleUpdate", "Reindex", "PurgeStaleEdition" ], "domain_events": [ "RuleUpdateIngested", "IndexRebuilt" ], "policies": [ "Retrieval indices partitioned per tenant and per AHJ edition", "Purge cascades to indices within SLA" ], "specifications": [ "TenantIsolationSpec", "EditionScopeSpec" ], "invariants": [ "AHJ retrieval is scoped to the checklist edition adopted by the conveyance's jurisdiction" ], "ai_agents": [], "human_roles": [ "Ops (prompt owner)" ], "data_owned": [ "AHJ rule sets", "Indices" ], "inputs": [ "AHJ published rule/edition updates", "Uploaded checklist source docs" ], "outputs": [ "Retrieval hits with citations" ], "external_integrations": [ "Blob storage", "Search API" ], "risks": [ "Cross-tenant retrieval leak", "Stale AHJ edition" ], "interfaces": [ "-> AI Workbench & Extraction" ] }, { "name": "Compliance & Licensing Governance", "purpose": "Own the release-readiness decision, owner-action ledger, and licensing-boundary enforcement.", "subdomain": "Compliance & Licensing Governance (supporting)", "type": "supporting", "owned_language": [ "Owner action", "Release decision", "Licensing boundary" ], "owns": [ "Owner-action ledger", "Release-decision policy", "Licensing-boundary attestations" ], "does_not_own": [ "Completeness Pack content", "Analyst/consultant identity" ], "primary_actors": [ "Business owner / founder", "Legal reviewer", "Compliance analyst" ], "entities": [ "OwnerAction", "ReleaseDecision", "DSARRequest" ], "value_objects": [ "Blocker reason", "Jurisdiction" ], "aggregates": [ "OwnerActionLedgerAggregate" ], "domain_services": [ "Release-decision engine", "DSAR fulfillment service" ], "application_services": [ "ResolveOwnerAction", "RecomputeReleaseDecision", "ProcessDSAR" ], "commands": [ "ResolveOwnerAction", "RaiseOwnerAction", "ProcessDSAR" ], "domain_events": [ "OwnerActionResolved", "ReleaseDecisionChanged", "DSARFulfilled" ], "policies": [ "Block a public release-readiness claim while any owner action is open", "DSAR SLA 30 days", "AI may extract/classify/gap-score/draft chase letters; only a licensed elevator consultant/QEI may author or certify an MCP or interpret contested code; the company never inspects, certifies, or practices engineering" ], "specifications": [ "ReleaseReadinessSpec", "DSARSpec" ], "invariants": [ "Release cannot flip to 'ready' with open blocking owner actions" ], "ai_agents": [], "human_roles": [ "Business owner / founder", "Legal reviewer" ], "data_owned": [ "Owner-action ledger", "Release decisions", "DSAR queue" ], "inputs": [ "Owner/operator input", "Legal review outcome" ], "outputs": [ "Release-decision event", "DSAR confirmation" ], "external_integrations": [ "Email inbox" ], "risks": [ "Public release-readiness claim while a blocker is open", "Mis-selling as engineering / QEI services" ], "interfaces": [ "<- Completeness Pack Fulfillment", "<- Release & Quality Assurance (PackRetracted)" ] }, { "name": "Sales & Intake", "purpose": "Lead (Gap Scan) -> qualified engagement -> accepted conveyance intake.", "subdomain": "Sales & Intake (supporting)", "type": "supporting", "owned_language": [ "Lead", "Engagement", "Gap Scan" ], "owns": [ "Lead pipeline", "Engagement letter", "Gap Scan requests" ], "does_not_own": [ "Fulfillment", "Billing" ], "primary_actors": [ "Business owner / founder", "Customer operator" ], "entities": [ "Lead", "Engagement" ], "value_objects": [ "Scope statement", "Pricing offer" ], "aggregates": [ "EngagementAggregate" ], "domain_services": [ "Scope-fit evaluator" ], "application_services": [ "QualifyLead", "AcceptEngagement" ], "commands": [ "QualifyLead", "AcceptEngagement" ], "domain_events": [ "EngagementAccepted" ], "policies": [ "Reject out-of-ICP engagement (no elevators, or fully staffed Class-A tower)", "Engagement letter required before intake" ], "specifications": [ "ScopeFitSpec" ], "invariants": [ "Cannot open a conveyance intake without an accepted engagement" ], "ai_agents": [], "human_roles": [ "Business owner / founder" ], "data_owned": [ "Leads", "Engagements" ], "inputs": [ "Gap Scan upload", "Discovery notes" ], "outputs": [ "Accepted engagement event" ], "external_integrations": [ "CRM", "Email inbox" ], "risks": [ "Accepting an out-of-scope engagement" ], "interfaces": [ "-> Client Onboarding & Tenant Profile", "-> Completeness Pack Fulfillment (intake enablement)" ] }, { "name": "Client Onboarding & Tenant Profile", "purpose": "Provision the tenant, capture the compliance-analyst-of-record, import any existing MCP/evidence pack.", "subdomain": "Client Onboarding & Tenant Profile (supporting)", "type": "supporting", "owned_language": [ "Tenant", "Analyst of record", "Evidence pack import" ], "owns": [ "Tenant provisioning", "Analyst-of-record record", "Evidence pack import" ], "does_not_own": [ "Release capture", "Delivery" ], "primary_actors": [ "Onboarding lead", "Customer admin" ], "entities": [ "Tenant", "AnalystOfRecord", "EvidencePackImport" ], "value_objects": [ "Contact matrix", "AHJ set" ], "aggregates": [ "TenantAggregate" ], "domain_services": [ "Tenant provisioner" ], "application_services": [ "ProvisionTenant", "RegisterAnalystOfRecord", "ImportEvidencePack" ], "commands": [ "ProvisionTenant", "RegisterAnalystOfRecord", "ImportEvidencePack" ], "domain_events": [ "TenantProvisioned", "AnalystOfRecordRegistered" ], "policies": [ "No intake opens until a compliance analyst of record is registered per tenant" ], "specifications": [ "AnalystCredentialSpec" ], "invariants": [ "Every tenant has at least one named compliance analyst of record on file" ], "ai_agents": [], "human_roles": [ "Onboarding lead" ], "data_owned": [ "Tenants", "Analyst-of-record records", "Evidence pack imports" ], "inputs": [ "Engagement", "Customer-supplied evidence pack" ], "outputs": [ "Provisioned tenant" ], "external_integrations": [ "IdP", "Google Drive / S3" ], "risks": [ "No analyst of record before go-live" ], "interfaces": [ "-> Completeness Pack Fulfillment" ] }, { "name": "Client Delivery & Success", "purpose": "Deliver released packs, own the customer surface, drive Portfolio Desk renewal.", "subdomain": "Client Delivery & Success (supporting)", "type": "supporting", "owned_language": [ "Delivery", "Revision request", "Renewal signal" ], "owns": [ "Customer portal", "Delivery log", "Revision workflow" ], "does_not_own": [ "Released content", "Billing" ], "primary_actors": [ "Customer operator", "Success lead" ], "entities": [ "DeliveryReceipt", "RevisionRequest" ], "value_objects": [ "Delivery method", "NPS signal" ], "aggregates": [ "DeliveryAggregate" ], "domain_services": [ "Delivery adapter" ], "application_services": [ "ConfirmDelivery", "RecordRevisionRequest" ], "commands": [ "ConfirmDelivery", "RecordRevisionRequest" ], "domain_events": [ "DeliveryConfirmed", "RevisionRequested" ], "policies": [ "Alert customer within 1h of any delivery failure" ], "specifications": [ "DeliveryAcknowledgmentSpec" ], "invariants": [ "Every DeliveryConfirmed has a linked Release" ], "ai_agents": [ "Success Copilot (assist only)" ], "human_roles": [ "Success lead" ], "data_owned": [ "Deliveries", "Revision requests" ], "inputs": [ "Released Completeness Pack", "Customer feedback" ], "outputs": [ "Delivery confirmation", "Revision request" ], "external_integrations": [ "Email", "Customer portal" ], "risks": [ "Silent delivery failure ahead of an inspection date" ], "interfaces": [ "<- Completeness Pack Fulfillment", "-> Portfolio & Recurring Programs", "-> Billing & Revenue" ] }, { "name": "Vendor Chase Desk", "purpose": "Manage the paid vendor cure-evidence follow-up until flagged hard gaps close.", "subdomain": "Vendor Chase Desk (supporting)", "type": "supporting", "owned_language": [ "Chase kit", "Vendor chase letter", "Chase Desk" ], "owns": [ "Vendor chase cases", "Chase letter templates", "Cure-evidence log" ], "does_not_own": [ "Gap-matrix release", "Billing" ], "primary_actors": [ "Compliance analyst", "AI extraction/orchestration layer" ], "entities": [ "VendorChaseCase", "ChaseLetter" ], "value_objects": [ "Chase cadence", "Cure-evidence citation" ], "aggregates": [ "VendorChaseCaseAggregate" ], "domain_services": [ "Chase-letter drafter", "Cure-evidence validator" ], "application_services": [ "DispatchChaseLetter", "ConfirmVendorCure" ], "commands": [ "DispatchChaseLetter", "ConfirmVendorCure" ], "domain_events": [ "ChaseLetterDispatched", "HardGapCured" ], "policies": [ "Open a vendor chase case only for a vendor-attributable hard gap on a paid Chase Desk cycle", "A hard gap cannot be marked cured without vendor-sourced cure evidence" ], "specifications": [ "CureEvidenceSpec" ], "invariants": [ "A hard gap cannot be marked cured without vendor-sourced cure evidence citing the original clause" ], "ai_agents": [ "Extraction Agent" ], "human_roles": [ "Compliance analyst" ], "data_owned": [ "Vendor chase cases", "Chase letters" ], "inputs": [ "Flagged hard gap", "Vendor response" ], "outputs": [ "Chase letter", "Cure confirmation" ], "external_integrations": [ "Email", "Elevator-vendor work-order / CMMS platforms" ], "risks": [ "OEM/vendor refusal to share MCP/logs", "Chase Desk scope-creeping into unpaid custom consulting" ], "interfaces": [ "<- Completeness Pack Fulfillment (HardGatesEvaluated)", "-> Completeness Pack Fulfillment (gap matrix re-score)" ] }, { "name": "Portfolio & Recurring Programs", "purpose": "Own the Portfolio Desk subscription: 5-40 buildings, quarterly re-scans, rolling scorecard.", "subdomain": "Portfolio & Recurring Programs (supporting)", "type": "supporting", "owned_language": [ "Portfolio Desk", "Quarterly re-scan" ], "owns": [ "Portfolio enrollment", "Re-scan schedule", "Portfolio scorecard" ], "does_not_own": [ "Individual pack release", "Billing" ], "primary_actors": [ "Success lead", "Customer operator" ], "entities": [ "Portfolio", "ReScanSchedule" ], "value_objects": [ "Cadence", "Scorecard snapshot" ], "aggregates": [ "PortfolioAggregate" ], "domain_services": [ "Re-scan scheduler" ], "application_services": [ "EnrollPortfolio", "ScheduleQuarterlyReScan" ], "commands": [ "EnrollPortfolio", "ScheduleQuarterlyReScan" ], "domain_events": [ "PortfolioEnrolled", "ReScanScheduled" ], "policies": [ "Quarterly re-scan is mandatory for every enrolled building", "Enrollment capped at 40 buildings per Portfolio Desk subscription" ], "specifications": [ "ReScanCadenceSpec" ], "invariants": [ "Every enrolled building has a non-lapsed quarterly re-scan schedule" ], "ai_agents": [], "human_roles": [ "Success lead" ], "data_owned": [ "Portfolios", "Re-scan schedules" ], "inputs": [ "Enrollment request", "Prior Completeness Packs" ], "outputs": [ "Portfolio scorecard", "New conveyance intake batch" ], "external_integrations": [ "Customer portal" ], "risks": [ "Portfolio Desk scope-creeping into unpaid custom consulting" ], "interfaces": [ "-> Completeness Pack Fulfillment (new intake batch)", "<- Client Delivery & Success" ] }, { "name": "Billing & Revenue", "purpose": "Invoicing, subscription management, dunning, revenue reporting across all pricing tiers.", "subdomain": "Billing & Revenue (generic)", "type": "generic", "owned_language": [ "Invoice", "Subscription", "Usage record" ], "owns": [ "Invoices", "Subscriptions", "Usage records" ], "does_not_own": [ "Fulfillment", "Release" ], "primary_actors": [ "Finance", "Customer admin" ], "entities": [ "Subscription", "Invoice", "UsageRecord" ], "value_objects": [ "Line item", "Tax jurisdiction" ], "aggregates": [ "SubscriptionAggregate" ], "domain_services": [ "Billing adapter" ], "application_services": [ "ChargeSubscription", "RecordUsage" ], "commands": [ "ChargeSubscription", "RecordUsage" ], "domain_events": [ "InvoicePaid", "SubscriptionCanceled" ], "policies": [ "Meter delivered Completeness Packs for per-pack pricing" ], "specifications": [ "ChargeabilitySpec" ], "invariants": [ "No charge without a delivered Completeness Pack when priced per pack" ], "ai_agents": [], "human_roles": [ "Finance" ], "data_owned": [ "Subscriptions", "Invoices" ], "inputs": [ "Delivery events" ], "outputs": [ "Invoice records" ], "external_integrations": [ "Stripe" ], "risks": [ "Tax jurisdictional errors" ], "interfaces": [ "<- Client Delivery & Success" ] }, { "name": "Identity & Access", "purpose": "SSO, MFA, RBAC, session management.", "subdomain": "Identity & Access (generic)", "type": "generic", "owned_language": [ "User", "Role", "Session" ], "owns": [ "Users", "Roles table", "Sessions" ], "does_not_own": [ "Business capability decisions" ], "primary_actors": [ "Platform admin", "User" ], "entities": [ "User", "RoleAssignment", "Session" ], "value_objects": [ "Role", "Claim" ], "aggregates": [ "UserAggregate" ], "domain_services": [ "Auth service" ], "application_services": [ "SignIn", "AssignRole" ], "commands": [ "SignIn", "AssignRole" ], "domain_events": [ "UserSignedIn", "RoleAssigned" ], "policies": [ "Roles in a dedicated table, checked server-side" ], "specifications": [ "RoleAuthoritySpec" ], "invariants": [ "No role check runs client-only" ], "ai_agents": [], "human_roles": [ "Platform admin" ], "data_owned": [ "Users", "Roles", "Sessions" ], "inputs": [ "Auth events" ], "outputs": [ "Sessions" ], "external_integrations": [ "IdP (Google / Okta)" ], "risks": [ "Role escalation" ], "interfaces": [ "-> every other context" ] }, { "name": "Analytics & Reporting", "purpose": "Operational + business metrics, outcome reports against the brief's KPI targets.", "subdomain": "Analytics & Reporting (supporting)", "type": "supporting", "owned_language": [ "Metric", "Dashboard", "Outcome report" ], "owns": [ "Metric definitions", "Dashboards" ], "does_not_own": [ "Raw write models" ], "primary_actors": [ "Ops lead", "Business owner / founder" ], "entities": [ "MetricDefinition", "Dashboard" ], "value_objects": [ "Window", "Target" ], "aggregates": [ "MetricDefinitionAggregate" ], "domain_services": [ "Rollup service" ], "application_services": [ "PublishMetric", "PublishDashboard" ], "commands": [ "PublishMetric", "PublishDashboard" ], "domain_events": [ "DashboardPublished" ], "policies": [ "North-star (scan-to-paid) must be wired before Phase 2 launch" ], "specifications": [ "MetricDefinedSpec" ], "invariants": [ "Metrics have a definition, a target, and an owner" ], "ai_agents": [], "human_roles": [ "Ops lead" ], "data_owned": [ "Metric definitions", "Read-model rollups" ], "inputs": [ "Domain events (as read-only consumer)" ], "outputs": [ "Dashboards", "Outcome reports" ], "external_integrations": [ "BI tool" ], "risks": [ "Vanity metrics dominating" ], "interfaces": [ "<- every context (read-only)" ] } ], "context_map": [ { "upstream": "Sales & Intake", "downstream": "Completeness Pack Fulfillment", "pattern": "customer-supplier", "business_reason": "Fulfillment cannot start without an accepted engagement.", "data_exchanged": [ "Engagement", "Scope statement" ], "events_exchanged": [ "EngagementAccepted" ], "contract_type": "Published language (Engagement record)", "failure_risks": [ "Silent scope mismatch" ], "acl_notes": "Fulfillment consumes only fields it needs; no direct DB coupling.", "ownership_boundary": "Sales owns engagement lifecycle." }, { "upstream": "Completeness Pack Fulfillment", "downstream": "Release & Quality Assurance", "pattern": "customer-supplier", "business_reason": "Release is a hard gate on delivery.", "data_exchanged": [ "GapMatrix", "Evidence trail" ], "events_exchanged": [ "GapMatrixDrafted", "PackReleased" ], "contract_type": "Published language", "failure_risks": [ "Analyst bottleneck" ], "acl_notes": "QA never mutates gap-matrix content; only appends a release.", "ownership_boundary": "QA owns the release log." }, { "upstream": "AI Workbench & Extraction", "downstream": "Completeness Pack Fulfillment", "pattern": "customer-supplier", "business_reason": "The gap-matrix draft is produced by AI; Fulfillment consumes it.", "data_exchanged": [ "Gap-matrix draft payload", "Confidence score" ], "events_exchanged": [ "GapMatrixDrafted", "EscalationRaised" ], "contract_type": "Published language (validated schema)", "failure_risks": [ "A draft failing OutputValidator reaches Fulfillment" ], "acl_notes": "OutputValidator sits inside AI Workbench & Extraction.", "ownership_boundary": "AI owns the run log; Fulfillment owns gap-matrix state." }, { "upstream": "AHJ Rule Library & Retrieval", "downstream": "AI Workbench & Extraction", "pattern": "open-host-service", "business_reason": "AHJ retrieval is a stable interface used by all agents.", "data_exchanged": [ "Retrieval hits", "Edition citations" ], "events_exchanged": [ "RuleUpdateIngested", "IndexRebuilt" ], "contract_type": "Open-host published API", "failure_risks": [ "Cross-tenant leak", "Stale AHJ edition" ], "acl_notes": "Every call carries tenant + AHJ-edition claim.", "ownership_boundary": "AHJ Rule Library owns indices." }, { "upstream": "Client Onboarding & Tenant Profile", "downstream": "Completeness Pack Fulfillment", "pattern": "customer-supplier", "business_reason": "No intake without a provisioned tenant + analyst of record.", "data_exchanged": [ "Tenant profile", "Analyst-of-record identity" ], "events_exchanged": [ "TenantProvisioned", "AnalystOfRecordRegistered" ], "contract_type": "Published language", "failure_risks": [ "No analyst of record on file" ], "acl_notes": "Fulfillment reads a projection; does not query Onboarding tables.", "ownership_boundary": "Onboarding owns tenant + analyst-of-record records." }, { "upstream": "Completeness Pack Fulfillment", "downstream": "Client Delivery & Success", "pattern": "customer-supplier", "business_reason": "Delivery is downstream of release.", "data_exchanged": [ "Released Completeness Pack" ], "events_exchanged": [ "PackDelivered", "DeliveryConfirmed" ], "contract_type": "Published language", "failure_risks": [ "Silent delivery failure" ], "acl_notes": "Delivery adapter is inside Fulfillment; Delivery context tracks the receipt.", "ownership_boundary": "Delivery context owns receipts." }, { "upstream": "Release & Quality Assurance", "downstream": "Compliance & Licensing Governance", "pattern": "customer-supplier", "business_reason": "Retractions feed compliance and licensing-boundary workflows.", "data_exchanged": [ "Retraction record" ], "events_exchanged": [ "PackRetracted" ], "contract_type": "Published language", "failure_risks": [ "Retraction not surfaced" ], "acl_notes": "Compliance subscribes to the event stream.", "ownership_boundary": "QA owns the retraction record; Compliance owns the downstream runbook." }, { "upstream": "Compliance & Licensing Governance", "downstream": "Completeness Pack Fulfillment", "pattern": "conformist", "business_reason": "Fulfillment must respect release-readiness decisions.", "data_exchanged": [ "Release decision" ], "events_exchanged": [ "ReleaseDecisionChanged" ], "contract_type": "Read-only projection consumed by Fulfillment", "failure_risks": [ "Fulfillment ignoring a blocked release-readiness claim" ], "acl_notes": "Fulfillment conforms to Compliance's release model.", "ownership_boundary": "Compliance owns the release model." }, { "upstream": "Completeness Pack Fulfillment", "downstream": "Vendor Chase Desk", "pattern": "customer-supplier", "business_reason": "A flagged, vendor-attributable hard gap opens a chase case.", "data_exchanged": [ "Hard-gap flag", "Vendor contact" ], "events_exchanged": [ "HardGatesEvaluated" ], "contract_type": "Published language", "failure_risks": [ "Chase case opened on a non-vendor-attributable gap" ], "acl_notes": "Chase Desk reads a projection of the gap matrix; does not mutate it.", "ownership_boundary": "Vendor Chase Desk owns chase cases." }, { "upstream": "Vendor Chase Desk", "downstream": "Completeness Pack Fulfillment", "pattern": "customer-supplier", "business_reason": "Cure evidence must flow back into a gap-matrix re-score.", "data_exchanged": [ "Cure evidence" ], "events_exchanged": [ "HardGapCured" ], "contract_type": "Published language", "failure_risks": [ "Cure evidence not reflected in the re-score" ], "acl_notes": "Fulfillment re-runs hard-gate evaluation on HardGapCured.", "ownership_boundary": "Chase Desk owns cure evidence; Fulfillment owns the re-score." }, { "upstream": "Client Delivery & Success", "downstream": "Portfolio & Recurring Programs", "pattern": "customer-supplier", "business_reason": "Renewal signal from delivered packs feeds Portfolio Desk enrollment.", "data_exchanged": [ "Renewal signal" ], "events_exchanged": [ "DeliveryConfirmed" ], "contract_type": "Published language", "failure_risks": [ "Missed upsell signal" ], "acl_notes": "Portfolio & Recurring Programs subscribes to delivery events.", "ownership_boundary": "Portfolio owns enrollment + re-scan schedule." }, { "upstream": "Client Delivery & Success", "downstream": "Billing & Revenue", "pattern": "customer-supplier", "business_reason": "Delivery is the meter for per-pack pricing.", "data_exchanged": [ "Delivery receipt" ], "events_exchanged": [ "DeliveryConfirmed" ], "contract_type": "Published language", "failure_risks": [ "Missed usage record" ], "acl_notes": "Billing subscribes to delivery events.", "ownership_boundary": "Billing owns invoicing." }, { "upstream": "Identity & Access", "downstream": "every other context", "pattern": "shared-kernel", "business_reason": "Auth primitives are shared.", "data_exchanged": [ "Session claim", "Role" ], "events_exchanged": [], "contract_type": "Shared kernel (tiny, versioned)", "failure_risks": [ "Kernel bloat" ], "acl_notes": "Kernel kept intentionally small.", "ownership_boundary": "Identity owns the primitives." }, { "upstream": "every context", "downstream": "Analytics & Reporting", "pattern": "conformist", "business_reason": "Analytics conforms to whatever events contexts publish.", "data_exchanged": [ "Domain events (read-only)" ], "events_exchanged": [ "all" ], "contract_type": "Read-only event subscription", "failure_risks": [ "Event schema drift" ], "acl_notes": "Analytics stores its own read model.", "ownership_boundary": "Analytics owns rollups." } ], "external_integrations": [ { "system": "Vendor invoice inboxes", "risk": "Schema drift; silent field rename; rate limits", "internal_model": "evidence citation record or chase notification", "acl_strategy": "Adapter in External Integrations context translates external schema -> internal domain term; upstream schema never leaks past the adapter.", "owner_context": "External Integrations", "data_in": [ "External record" ], "data_out": [ "Ack or receipt" ], "trigger": "api", "failure_strategy": "Exponential backoff with jitter; circuit breaker on repeated failure; dead-letter with owner-visible alert.", "audit_need": "Every call logged with tenant, request id, cost, and payload hash (no PII in logs)." }, { "system": "Elevator-vendor work-order / CMMS platforms", "risk": "Schema drift; silent field rename; rate limits", "internal_model": "evidence citation record or notification", "acl_strategy": "Adapter in External Integrations context translates external schema -> internal domain term; upstream schema never leaks past the adapter.", "owner_context": "External Integrations", "data_in": [ "External record" ], "data_out": [ "Ack or receipt" ], "trigger": "api", "failure_strategy": "Exponential backoff with jitter; circuit breaker on repeated failure; dead-letter with owner-visible alert.", "audit_need": "Every call logged with tenant, request id, cost, and payload hash (no PII in logs)." }, { "system": "Customer document portals", "risk": "Schema drift; silent field rename; rate limits", "internal_model": "evidence citation record or notification", "acl_strategy": "Adapter in External Integrations context translates external schema -> internal domain term; upstream schema never leaks past the adapter.", "owner_context": "External Integrations", "data_in": [ "External record" ], "data_out": [ "Ack or receipt" ], "trigger": "api", "failure_strategy": "Exponential backoff with jitter; circuit breaker on repeated failure; dead-letter with owner-visible alert.", "audit_need": "Every call logged with tenant, request id, cost, and payload hash (no PII in logs)." }, { "system": "OpenAI / Anthropic API", "risk": "Prompt-injection surface; token cost blowout; provider outage", "internal_model": "Gap-matrix draft payload with confidence score + validated schema", "acl_strategy": "OutputValidator + prompt-injection scrubber + per-tenant retrieval scope inside AI Workbench & Extraction.", "owner_context": "AI Workbench & Extraction", "data_in": [ "Prompt + retrieval context" ], "data_out": [ "Draft + confidence" ], "trigger": "api", "failure_strategy": "Exponential backoff with jitter; circuit breaker on repeated failure; dead-letter with owner-visible alert.", "audit_need": "Every call logged with tenant, request id, cost, and payload hash (no PII in logs)." } ], "event_storm": [ { "seq": 1, "command": "QualifyLead", "event": "LeadQualified", "actor": "Business owner / founder", "context": "Sales & Intake", "aggregate": "EngagementAggregate", "policy": "Reject out-of-ICP", "downstream": "Engagement offer", "risk": "Out-of-scope acceptance" }, { "seq": 2, "command": "AcceptEngagement", "event": "EngagementAccepted", "actor": "Customer operator", "context": "Sales & Intake", "aggregate": "EngagementAggregate", "policy": "Engagement letter required", "downstream": "Onboarding starts", "risk": "Missing engagement letter" }, { "seq": 3, "command": "ProvisionTenant", "event": "TenantProvisioned", "actor": "Onboarding lead", "context": "Client Onboarding & Tenant Profile", "aggregate": "TenantAggregate", "policy": "Named analyst of record required", "downstream": "Analyst-of-record registration", "risk": "No analyst of record on file" }, { "seq": 4, "command": "OpenConveyanceIntake", "event": "ConveyanceIntakeAccepted", "actor": "Customer operator", "context": "Completeness Pack Fulfillment", "aggregate": "ConveyanceIntakeAggregate", "policy": "Scope-fit spec", "downstream": "Evidence upload window opens", "risk": "Scope drift beyond ICP" }, { "seq": 5, "command": "IngestEvidence", "event": "EvidenceIngested", "actor": "Customer operator + Normalization service", "context": "Completeness Pack Fulfillment", "aggregate": "ConveyanceIntakeAggregate", "policy": "Evidence coverage spec", "downstream": "Extraction authorized", "risk": "Insufficient machine-room photo evidence" }, { "seq": 6, "command": "StartExtractionRun", "event": "GapMatrixDrafted", "actor": "AI extraction/orchestration layer", "context": "AI Workbench & Extraction", "aggregate": "ExtractionRunAggregate", "policy": "Confidence threshold", "downstream": "Hard-gate evaluation", "risk": "Prompt injection via vendor invoice content" }, { "seq": 7, "command": "EvaluateHardGates", "event": "HardGatesEvaluated", "actor": "Deterministic rule engine", "context": "Completeness Pack Fulfillment", "aggregate": "GapMatrixAggregate", "policy": "Hard-fail checklist spec", "downstream": "Analyst queue or consultant escalation", "risk": "AHJ edition mismatch causing a false hard-fail" }, { "seq": 8, "command": "ReleasePack", "event": "PackReleased", "actor": "Compliance analyst / Licensed elevator consultant (QEI) on escalation", "context": "Release & Quality Assurance", "aggregate": "ReleaseAggregate", "policy": "Releaser authority spec", "downstream": "Delivery authorized", "risk": "Missing-MCP-authorship escalation skipped" }, { "seq": 9, "command": "DeliverCompletenessPack", "event": "PackDelivered", "actor": "Delivery adapter", "context": "Completeness Pack Fulfillment", "aggregate": "CompletenessPackAggregate", "policy": "Deliverability spec", "downstream": "Billing meter, customer notified", "risk": "Silent delivery failure" }, { "seq": 10, "command": "ConfirmDelivery", "event": "DeliveryConfirmed", "actor": "Client Delivery & Success", "context": "Client Delivery & Success", "aggregate": "DeliveryAggregate", "policy": "Ack within SLA", "downstream": "Success cadence", "risk": "Missed ack" }, { "seq": 11, "command": "DispatchChaseLetter", "event": "ChaseLetterDispatched", "actor": "AI extraction/orchestration layer + Compliance analyst", "context": "Vendor Chase Desk", "aggregate": "VendorChaseCaseAggregate", "policy": "Chase-cadence spec", "downstream": "Vendor cure evidence tracked", "risk": "OEM vendor refuses to share MCP/logs" }, { "seq": 12, "command": "ConfirmVendorCure", "event": "HardGapCured", "actor": "Compliance analyst", "context": "Vendor Chase Desk", "aggregate": "VendorChaseCaseAggregate", "policy": "Cure-evidence coverage spec", "downstream": "Gap matrix re-score", "risk": "Fabricated cure evidence accepted" }, { "seq": 13, "command": "ResolveOwnerAction", "event": "OwnerActionResolved", "actor": "Customer operator (attesting for the building owner)", "context": "Compliance & Licensing Governance", "aggregate": "OwnerActionLedgerAggregate", "policy": "Release readiness spec", "downstream": "Release-decision recompute", "risk": "Public claim while blocker open" }, { "seq": 14, "command": "ScheduleQuarterlyReScan", "event": "ReScanScheduled", "actor": "Success lead", "context": "Portfolio & Recurring Programs", "aggregate": "PortfolioAggregate", "policy": "Re-scan cadence spec", "downstream": "New conveyance intake batch opened", "risk": "Portfolio Desk scope-creeping into unpaid custom consulting" }, { "seq": 15, "command": "RetractPack", "event": "PackRetracted", "actor": "Legal reviewer + Licensed elevator consultant/QEI", "context": "Release & Quality Assurance", "aggregate": "PackRetractionAggregate", "policy": "Retraction preconditions", "downstream": "Customer notification, audit log", "risk": "Litigation discovery subpoena of the vault" } ], "critical_path": [ "ConveyanceIntakeAccepted -> EvidenceIngested -> GapMatrixDrafted -> HardGatesEvaluated -> PackReleased -> PackDelivered -> DeliveryConfirmed" ], "exception_flows": [ "GapMatrixDrafted with a missing MCP or contested code interpretation -> EscalationRaised -> Licensed elevator consultant/QEI authors or interprets -> PackReleased (red)", "DeliverCompletenessPack blocked by an open owner action -> DeliveryBlocked -> owner/operator resolves -> retry", "DeliveryFailed at the adapter -> customer alert within 1h -> Success ticket -> retry with backoff", "HardGatesEvaluated flags a vendor-attributable gap with no vendor response -> Vendor Chase Desk opened -> ChaseLetterDispatched -> HardGapCured or re-escalated to owner demand" ], "escalation_flows": [ "AI extraction/orchestration layer escalates to Compliance analyst", "Compliance analyst escalates missing-MCP-authorship or contested code interpretation to Licensed elevator consultant/QEI", "Success lead escalates silent delivery failure to Business owner / founder", "Business owner escalates an AHJ or insurer inquiry to external counsel" ], "retry_flows": [ "External API failure -> exponential backoff with jitter, then dead-letter with owner-visible alert", "Model timeout -> retry once, then EscalationRaised", "Delivery adapter failure -> retry with backoff, then customer alert" ], "manual_override_flows": [ "Compliance analyst may override an AI-classified hard gap and re-route to the consultant", "Business owner may force-block a delivery via the Compliance & Licensing Governance ledger", "Ops may pull a prompt version at any time (feature flag)" ], "commands": [ { "name": "OpenConveyanceIntake", "issued_by": "Customer operator", "preconditions": [ "Engagement accepted", "Tenant provisioned" ], "aggregate": "ConveyanceIntakeAggregate", "success_event": "ConveyanceIntakeAccepted", "failure_event": "IntakeRejected", "authorization": "Tenant member with Operator role", "validation": "Building + conveyance count present; no duplicate open intake for the same building", "audit": "Command + payload hash logged with tenant + user" }, { "name": "IngestEvidence", "issued_by": "Customer operator / Normalization service", "preconditions": [ "Intake open", "File type allowed" ], "aggregate": "ConveyanceIntakeAggregate", "success_event": "EvidenceIngested", "failure_event": "EvidenceRejected", "authorization": "Same tenant", "validation": "Virus scan clean; vendor name canonicalized; unit ID matched", "audit": "Every attachment hashed and logged" }, { "name": "StartExtractionRun", "issued_by": "AI extraction/orchestration layer", "preconditions": [ "Evidence coverage complete", "Prompt version active" ], "aggregate": "ExtractionRunAggregate", "success_event": "GapMatrixDrafted", "failure_event": "EscalationRaised", "authorization": "Service role", "validation": "OutputValidator schema passes; citation-per-line check", "audit": "Prompt version + retrieval hits + cost captured" }, { "name": "EvaluateHardGates", "issued_by": "Deterministic rule engine", "preconditions": [ "GapMatrixDrafted" ], "aggregate": "GapMatrixAggregate", "success_event": "HardGatesEvaluated", "failure_event": "HardGateEvaluationError", "authorization": "Service role", "validation": "Every hard-fail checklist item (MCP present, accessibility instructions, 5-year retention, FEO test) evaluated with a citation", "audit": "Rule version + evaluation result logged" }, { "name": "ReleasePack", "issued_by": "Compliance analyst / Licensed elevator consultant (QEI) on escalation", "preconditions": [ "GapMatrixDrafted", "HardGatesEvaluated", "No unresolved escalation" ], "aggregate": "ReleaseAggregate", "success_event": "PackReleased", "failure_event": "PackReleaseRejected", "authorization": "Analyst role bound to tenant, or Consultant role on red packs", "validation": "Every hard gap either cleared or logged as an open owner action; every gap-matrix line cites evidence", "audit": "Release attestation + timestamp + releaser identity" }, { "name": "DeliverCompletenessPack", "issued_by": "Delivery adapter", "preconditions": [ "PackReleased", "Compliance release-readiness allows delivery" ], "aggregate": "CompletenessPackAggregate", "success_event": "PackDelivered", "failure_event": "DeliveryFailed", "authorization": "Service role", "validation": "Delivery method valid; vault index attached", "audit": "Delivery receipt archived" }, { "name": "ResolveOwnerAction", "issued_by": "Customer operator (attesting for the building owner)", "preconditions": [ "Owner action open" ], "aggregate": "OwnerActionLedgerAggregate", "success_event": "OwnerActionResolved", "failure_event": "OwnerActionRejected", "authorization": "Owner/operator role", "validation": "Supplied fact matches the action schema (e.g. vendor custody attestation, no-MCP-exists attestation)", "audit": "Actor + before/after captured" }, { "name": "DispatchChaseLetter", "issued_by": "Compliance analyst / AI extraction/orchestration layer (draft)", "preconditions": [ "Hard gap open and vendor-attributable", "Vendor contact on file" ], "aggregate": "VendorChaseCaseAggregate", "success_event": "ChaseLetterDispatched", "failure_event": "ChaseLetterFailed", "authorization": "Analyst role", "validation": "Chase letter template populated; no invented procedure text", "audit": "Chase letter + send receipt archived" }, { "name": "ConfirmVendorCure", "issued_by": "Compliance analyst", "preconditions": [ "ChaseLetterDispatched", "Vendor evidence received" ], "aggregate": "VendorChaseCaseAggregate", "success_event": "HardGapCured", "failure_event": "VendorCureRejected", "authorization": "Analyst role", "validation": "Cure evidence cites a source and matches the original hard-gap clause", "audit": "Cure evidence hash + reviewer id logged" }, { "name": "RetractPack", "issued_by": "Legal reviewer + Licensed elevator consultant/QEI", "preconditions": [ "Pack previously delivered", "Material finding documented" ], "aggregate": "PackRetractionAggregate", "success_event": "PackRetracted", "failure_event": "RetractionRejected", "authorization": "Legal AND Consultant co-sign", "validation": "Retraction preconditions spec", "audit": "Full retraction packet archived" } ], "policies": [ { "name": "Auto-request release on hard-gate evaluation complete", "trigger": "HardGatesEvaluated", "condition": "Gap-matrix coverage spec passes", "action": "Enqueue ReleasePack", "context": "Completeness Pack Fulfillment", "ai_involvement": "none", "human_approval": false }, { "name": "Escalate on low confidence or missing MCP", "trigger": "GapMatrixDrafted", "condition": "Confidence < threshold OR no MCP found OR contested code interpretation", "action": "Emit EscalationRaised, route to consultant queue", "context": "AI Workbench & Extraction", "ai_involvement": "author", "human_approval": false }, { "name": "Block delivery on open compliance blocker", "trigger": "DeliverCompletenessPack command", "condition": "Owner-action ledger has an open blocking item", "action": "Reject delivery, emit DeliveryBlocked", "context": "Completeness Pack Fulfillment <-> Compliance & Licensing Governance", "ai_involvement": "none", "human_approval": true }, { "name": "Retract on material finding", "trigger": "MaterialFindingReported", "condition": "Signed claim materially wrong or fabricated evidence discovered", "action": "Open PackRetraction workflow with legal + consultant co-sign", "context": "Release & Quality Assurance", "ai_involvement": "assist", "human_approval": true }, { "name": "Alert on delivery failure", "trigger": "DeliveryFailed", "condition": "Any", "action": "Notify customer within 1h + open Success ticket", "context": "Client Delivery & Success", "ai_involvement": "none", "human_approval": false }, { "name": "Open vendor chase case on vendor-attributable hard gap", "trigger": "HardGatesEvaluated", "condition": "Hard gap = missing 5-year record or missing FEO test attributable to a vendor, and Chase Desk purchased", "action": "Offer / open Vendor Chase Desk case", "context": "Vendor Chase Desk", "ai_involvement": "assist", "human_approval": true } ], "aggregates": [ { "name": "EngagementAggregate", "root": "Engagement", "context": "Sales & Intake", "purpose": "Guard lead qualification and accepted-engagement state.", "entities": [ "Lead", "Engagement" ], "value_objects": [ "ScopeStatement", "PricingOffer" ], "invariants": [ "Cannot open a conveyance intake without an accepted engagement" ], "commands": [ "QualifyLead", "AcceptEngagement" ], "events": [ "EngagementAccepted" ], "repository": "EngagementRepository", "transaction_boundary": "One engagement per transaction" }, { "name": "TenantAggregate", "root": "Tenant", "context": "Client Onboarding & Tenant Profile", "purpose": "Own tenant provisioning and analyst-of-record registration.", "entities": [ "Tenant", "AnalystOfRecord" ], "value_objects": [ "ContactMatrix", "AHJSet" ], "invariants": [ "Every tenant has at least one named analyst of record with a valid credential" ], "commands": [ "ProvisionTenant", "RegisterAnalystOfRecord" ], "events": [ "TenantProvisioned", "AnalystOfRecordRegistered" ], "repository": "TenantRepository", "transaction_boundary": "One tenant per transaction" }, { "name": "ConveyanceIntakeAggregate", "root": "ConveyanceIntake", "context": "Completeness Pack Fulfillment", "purpose": "Guard intake + evidence-ingestion state transitions for one building/conveyance batch.", "entities": [ "ConveyanceIntake", "EvidenceLink" ], "value_objects": [ "ConfidenceScore", "EvidenceCitation" ], "invariants": [ "An intake in state 'delivered' is immutable" ], "commands": [ "OpenConveyanceIntake", "IngestEvidence" ], "events": [ "ConveyanceIntakeAccepted", "EvidenceIngested" ], "repository": "ConveyanceIntakeRepository", "transaction_boundary": "One conveyance intake per transaction" }, { "name": "GapMatrixAggregate", "root": "GapMatrix", "context": "Completeness Pack Fulfillment", "purpose": "Own the line-by-line checklist-vs-evidence comparison and the hard-gate evaluation.", "entities": [ "GapMatrix", "GapMatrixLine", "HardGapFlag" ], "value_objects": [ "ChecklistClauseCitation", "EvidenceCitation" ], "invariants": [ "Every gap-matrix line cites at least one evidence item or is marked an explicit gap" ], "commands": [ "EvaluateHardGates" ], "events": [ "HardGatesEvaluated" ], "repository": "GapMatrixRepository", "transaction_boundary": "One gap matrix per transaction" }, { "name": "CompletenessPackAggregate", "root": "Completeness Pack", "context": "Completeness Pack Fulfillment", "purpose": "Own the Completeness Pack lifecycle from released to delivered.", "entities": [ "Completeness Pack", "Delivery" ], "value_objects": [ "DeliveryAddress", "VaultIndexEntry" ], "invariants": [ "A Completeness Pack cannot be delivered without a valid Release" ], "commands": [ "DeliverCompletenessPack" ], "events": [ "PackDelivered" ], "repository": "CompletenessPackRepository", "transaction_boundary": "One Completeness Pack per transaction" }, { "name": "ExtractionRunAggregate", "root": "ExtractionRun", "context": "AI Workbench & Extraction", "purpose": "Track a single bounded AI extraction run with prompt version, cost, and output validation.", "entities": [ "ExtractionRun", "RetrievalHit" ], "value_objects": [ "ConfidenceScore", "TokenBudget", "ModelCost" ], "invariants": [ "No output emitted without OutputValidator pass", "Retrieval scoped to a single tenant partition" ], "commands": [ "StartExtractionRun" ], "events": [ "GapMatrixDrafted", "EscalationRaised" ], "repository": "ExtractionRunRepository", "transaction_boundary": "One run per transaction" }, { "name": "AHJRuleSetAggregate", "root": "AHJRuleSet", "context": "AHJ Rule Library & Retrieval", "purpose": "Own the per-jurisdiction AHJ edition library and ASME A17.1 §8.6 checklist cards.", "entities": [ "AHJRuleSet", "ChecklistCard" ], "value_objects": [ "EditionCitation" ], "invariants": [ "A checklist card is never served for an edition other than the one adopted by the conveyance's AHJ" ], "commands": [ "IngestRuleUpdate", "Reindex" ], "events": [ "RuleUpdateIngested", "IndexRebuilt" ], "repository": "AHJRuleSetRepository", "transaction_boundary": "One rule-set update per transaction" }, { "name": "ReleaseAggregate", "root": "Release", "context": "Release & Quality Assurance", "purpose": "Bind releaser identity + timestamp + pack hash immutably.", "entities": [ "Release" ], "value_objects": [ "ReleaseManifest" ], "invariants": [ "A Release is bound to a live authenticated session, not a form field", "Released packs are immutable" ], "commands": [ "ReleasePack" ], "events": [ "PackReleased" ], "repository": "ReleaseRepository", "transaction_boundary": "One release per transaction" }, { "name": "PackRetractionAggregate", "root": "PackRetraction", "context": "Release & Quality Assurance", "purpose": "Handle formal correction/withdrawal of a released Completeness Pack.", "entities": [ "PackRetraction" ], "value_objects": [ "RetractionReason", "ImpactStatement" ], "invariants": [ "A retraction requires Legal + Consultant co-signature" ], "commands": [ "RetractPack" ], "events": [ "PackRetracted" ], "repository": "PackRetractionRepository", "transaction_boundary": "One retraction per transaction" }, { "name": "OwnerActionLedgerAggregate", "root": "OwnerActionLedger", "context": "Compliance & Licensing Governance", "purpose": "Own the set of owner-supplied facts blocking a release-readiness claim.", "entities": [ "OwnerAction" ], "value_objects": [ "BlockerReason", "Jurisdiction" ], "invariants": [ "Release cannot flip to 'ready' with open blocking owner actions" ], "commands": [ "RaiseOwnerAction", "ResolveOwnerAction" ], "events": [ "OwnerActionResolved", "ReleaseDecisionChanged" ], "repository": "OwnerActionRepository", "transaction_boundary": "One ledger per tenant" }, { "name": "VendorChaseCaseAggregate", "root": "VendorChaseCase", "context": "Vendor Chase Desk", "purpose": "Own an open hard-gap cure cycle: chase letters, vendor responses, and cure-evidence confirmation.", "entities": [ "VendorChaseCase", "ChaseLetter" ], "value_objects": [ "ChaseCadence", "CureEvidenceCitation" ], "invariants": [ "A hard gap cannot be marked cured without vendor-sourced cure evidence citing the original clause" ], "commands": [ "DispatchChaseLetter", "ConfirmVendorCure" ], "events": [ "ChaseLetterDispatched", "HardGapCured" ], "repository": "VendorChaseCaseRepository", "transaction_boundary": "One chase case per transaction" }, { "name": "PortfolioAggregate", "root": "Portfolio", "context": "Portfolio & Recurring Programs", "purpose": "Own Portfolio Desk enrollment, quarterly re-scan scheduling, and the rolling scorecard.", "entities": [ "Portfolio", "ReScanSchedule" ], "value_objects": [ "Cadence", "ScorecardSnapshot" ], "invariants": [ "Every enrolled building has a non-lapsed quarterly re-scan schedule" ], "commands": [ "EnrollPortfolio", "ScheduleQuarterlyReScan" ], "events": [ "PortfolioEnrolled", "ReScanScheduled" ], "repository": "PortfolioRepository", "transaction_boundary": "One portfolio per transaction" }, { "name": "DeliveryAggregate", "root": "Delivery", "context": "Client Delivery & Success", "purpose": "Own delivery receipts and revision requests.", "entities": [ "Delivery", "RevisionRequest" ], "value_objects": [ "DeliveryMethod" ], "invariants": [ "Every DeliveryConfirmed has a linked Release" ], "commands": [ "ConfirmDelivery", "RecordRevisionRequest" ], "events": [ "DeliveryConfirmed", "RevisionRequested" ], "repository": "DeliveryRepository", "transaction_boundary": "One delivery per transaction" } ], "invariants": [ { "invariant": "A Completeness Pack cannot be delivered without a valid analyst or consultant Release.", "context": "Completeness Pack Fulfillment <-> Release & Quality Assurance", "aggregate": "CompletenessPackAggregate", "why": "Inspection defensibility; brand-risk", "enforcement": "Aggregate command handler rejects delivery without a release reference" }, { "invariant": "Every gap-matrix line cites at least one evidence item or is marked an explicit gap.", "context": "Completeness Pack Fulfillment", "aggregate": "GapMatrixAggregate", "why": "Anti-fabrication; audit reconstructability", "enforcement": "EvidenceCoverageSpec on hard-gate evaluation" }, { "invariant": "A Release is bound to a live authenticated session, not a form field.", "context": "Release & Quality Assurance", "aggregate": "ReleaseAggregate", "why": "Anti-spoofing, anti-repudiation", "enforcement": "Release service validates session claim server-side" }, { "invariant": "Released Completeness Packs are immutable; corrections go through PackRetraction.", "context": "Release & Quality Assurance", "aggregate": "ReleaseAggregate + PackRetractionAggregate", "why": "Preserves the audit chain", "enforcement": "Repository denies mutation after release" }, { "invariant": "No extraction output leaves AI Workbench & Extraction without an OutputValidator pass.", "context": "AI Workbench & Extraction", "aggregate": "ExtractionRunAggregate", "why": "Grounding + hallucination control (no invented log lines or dates)", "enforcement": "ExtractionRun terminates as EscalationRaised on validator failure" }, { "invariant": "AHJ retrieval is scoped to the checklist edition adopted by the conveyance's jurisdiction.", "context": "AHJ Rule Library & Retrieval <-> AI Workbench & Extraction", "aggregate": "AHJRuleSetAggregate", "why": "Prevent AHJ edition mismatch / false hard-fail", "enforcement": "EditionScopeSpec at the retrieval router" }, { "invariant": "Release cannot flip to 'ready' with open blocking owner actions.", "context": "Compliance & Licensing Governance", "aggregate": "OwnerActionLedgerAggregate", "why": "Prevent a premature public claim of inspection-readiness", "enforcement": "ReleaseReadinessSpec on ResolveOwnerAction" }, { "invariant": "Every tenant has at least one named compliance analyst of record on file before intake opens.", "context": "Client Onboarding & Tenant Profile", "aggregate": "TenantAggregate", "why": "No unattributed releases", "enforcement": "AnalystCredentialSpec on tenant provisioning" }, { "invariant": "A hard gap cannot be marked cured without vendor-sourced cure evidence citing the original clause.", "context": "Vendor Chase Desk", "aggregate": "VendorChaseCaseAggregate", "why": "Anti-fabrication on cure claims", "enforcement": "CureEvidenceSpec on ConfirmVendorCure" }, { "invariant": "Roles are stored in a dedicated table and checked server-side.", "context": "Identity & Access", "aggregate": "UserAggregate", "why": "Prevent privilege escalation", "enforcement": "RoleAuthoritySpec + RLS on protected tables" } ], "ai_agents": [ { "name": "Extraction Agent", "context": "AI Workbench & Extraction", "responsibility": "OCR heterogeneous vendor MCPs, service logs, callback records, inspection reports, and machine-room photos; extract equipment-specific fields; build the five-year coverage timeline; draft the cited gap matrix.", "inputs": [ "Ingested evidence (tenant-scoped)", "AHJ rule-set retrieval hits", "Prompt version" ], "outputs": [ "Structured gap-matrix draft", "Confidence score", "Citations" ], "tools": [ "Retrieval API", "Structured-output validator", "Cost meter" ], "forbidden_actions": [ "Call external tools not in its allowlist", "Access another tenant's retrieval index", "Emit output that skips the OutputValidator", "Author a technical MCP or interpret a contested code citation", "Invent log lines, dates, or procedures not present in source evidence" ], "memory_scope": "Per-run only; no cross-run memory; prompt-injection scrubber on all customer and vendor inputs.", "retrieval_sources": [ "Tenant-scoped evidence index", "AHJ edition checklist library (read-only cache)" ], "validations": [ "Structured-output schema", "Citation-coverage rule", "PII-scrub rule on prompt inputs" ], "confidence_scoring": "Model-reported logprobs + citation-coverage combined into a bounded [0..1] score.", "escalation_triggers": [ "Score < threshold", "No MCP found for a conveyance", "Contested code-edition interpretation", "Missing citation on any claim" ], "human_approval": true, "failure_modes": [ "Prompt injection via vendor invoice/log content", "Hallucinated citation", "Retrieval-tenant leak" ], "audit_logs": [ "Prompt version", "Retrieval hits (ids only)", "Cost + latency", "Validator verdict" ], "metrics": [ "Draft acceptance rate", "Escalation rate", "Cost per pack", "p95 latency" ], "versioning": "Prompt versions immutable once published; published via the prompt registry; rollout via feature flag." }, { "name": "Routing & Classification Agent", "context": "AI Workbench & Extraction", "responsibility": "Match each conveyance to the correct AHJ checklist edition and equipment category, and route the intake to the compliance analyst queue or, on ambiguity, the consultant queue.", "inputs": [ "Intake payload", "Building jurisdiction" ], "outputs": [ "Route decision + confidence" ], "tools": [ "AHJ rule-set registry" ], "forbidden_actions": [ "Make final release decisions", "Bypass analyst-queue routing", "Guarantee an inspection outcome" ], "memory_scope": "Per-run only", "retrieval_sources": [ "AHJ edition reference table" ], "validations": [ "Structured-output schema", "Known-route allowlist" ], "confidence_scoring": "Model logprobs.", "escalation_triggers": [ "Score < threshold", "Unrecognized AHJ or edition" ], "human_approval": false, "failure_modes": [ "Wrong route -> wrong reviewer", "Wrong AHJ edition applied" ], "audit_logs": [ "Route decision + rationale" ], "metrics": [ "Routing accuracy vs analyst corrections" ], "versioning": "Same as Extraction Agent" }, { "name": "Eval Agent", "context": "AI Workbench & Extraction", "responsibility": "Run offline evals on prompt versions against a golden dataset of past analyst-released Completeness Packs before rollout.", "inputs": [ "Golden dataset", "Prompt candidate" ], "outputs": [ "Pass/fail per case + drift report" ], "tools": [ "Golden dataset" ], "forbidden_actions": [ "Touch production tenant data" ], "memory_scope": "Per-eval only", "retrieval_sources": [ "Golden dataset only" ], "validations": [ "Regression thresholds" ], "confidence_scoring": "Aggregate over dataset", "escalation_triggers": [ "Regression > threshold" ], "human_approval": true, "failure_modes": [ "Overfit to golden dataset" ], "audit_logs": [ "Full eval report archived" ], "metrics": [ "Pass rate", "Regression rate" ], "versioning": "Every prompt release requires a passing eval" } ], "prompt_chain_map": [ "Intake -> Routing & Classification Agent (AHJ edition + equipment category) -> Extraction Agent (cite + draft gap matrix) -> OutputValidator -> Compliance analyst (release or escalate)", "Retraction analysis -> Eval Agent (assist only) -> Legal reviewer + Consultant co-sign" ], "rag_map": [ "Per-tenant evidence index -> retrieval router -> tenant-scoped hits -> Extraction Agent", "AHJ edition checklist library (Colorado, Fairfax/VA, expandable, read-only cache) -> shared retrieval -> Extraction Agent (cited)" ], "ai_evaluation": [ "Golden dataset of past analyst-released Completeness Packs per AHJ", "Regression thresholds on release-acceptance rate + citation coverage", "Every prompt release requires a passing Eval Agent run" ], "hallucination_controls": [ "Retrieval-first (no free-form generation of log lines, dates, or procedures without citation)", "Structured-output validator enforces citation-per-claim", "Confidence-scored escalation to compliance analyst / consultant", "Analyst or consultant release gate on every outbound Completeness Pack" ], "human_in_the_loop_plan": [ "Compliance analyst release on every green/yellow Completeness Pack", "Licensed elevator consultant/QEI release on every red (missing-MCP or contested-code) Completeness Pack", "Legal + consultant co-sign on retractions", "Business owner approval on public release-readiness claims for the microsite", "Ops sign-off on prompt-version rollout" ], "ai_audit_plan": [ "Every ExtractionRun logged with prompt version, retrieval hit ids, cost, latency, validator verdict", "13-month rolling retention on run logs", "PII scrubbed from log payloads" ], "prompt_versioning": "Prompt versions immutable once published; rolled out via feature flag; every rollout paired with an Eval Agent run.", "human_roles": [ { "role": "Compliance analyst", "responsibilities": [ "Release green/yellow Completeness Packs", "Escalate missing-MCP or contested-interpretation packs to the consultant", "Draft/edit vendor chase letters" ], "contexts": [ "Release & Quality Assurance", "Completeness Pack Fulfillment" ], "decisions_owned": [ "Release (green/yellow)", "Escalation" ], "ai_support": [ "Cited gap-matrix drafts", "Confidence-ranked hard gaps" ], "approval_authority": "Green/yellow pack release", "escalation_authority": "Escalate to Licensed elevator consultant/QEI", "quality_metrics": [ "Cycle time to release", "Release-to-retraction ratio" ], "workload_risks": [ "Analyst shortage / early demand trap" ] }, { "role": "Licensed elevator consultant / QEI", "responsibilities": [ "Author or certify a new technical MCP when none exists", "Interpret contested code citations", "Release red packs", "Advise on alteration/modernization escalations" ], "contexts": [ "Release & Quality Assurance" ], "decisions_owned": [ "Red-pack release", "Technical MCP authorship" ], "ai_support": [ "Escalation summary", "Prior-similar-case surfacing" ], "approval_authority": "Red-pack release", "escalation_authority": "Escalate to Legal reviewer / Business owner", "quality_metrics": [ "Escalation-to-release cycle time" ], "workload_risks": [ "Consultant retainer capacity", "Elevator-consultant partners perceiving MCPVault as a competitor" ] }, { "role": "Business owner / founder", "responsibilities": [ "Resolve escalated owner actions", "Decide public release-readiness for the microsite", "Own commercial claims" ], "contexts": [ "Compliance & Licensing Governance", "Sales & Intake" ], "decisions_owned": [ "Release readiness", "Owner-action ledger policy" ], "ai_support": [ "Blocker summary" ], "approval_authority": "Release readiness (public claims)", "escalation_authority": "Escalate to Legal reviewer", "quality_metrics": [ "Blocker close time" ], "workload_risks": [ "Single-owner queue" ] }, { "role": "Legal reviewer", "responsibilities": [ "Retraction co-sign", "DSAR + AHJ/regulator response", "Litigation-discovery vault requests" ], "contexts": [ "Release & Quality Assurance", "Compliance & Licensing Governance" ], "decisions_owned": [ "Retraction approval", "Regulator/subpoena response" ], "ai_support": [ "Precedent surfacing (assist only)" ], "approval_authority": "Retraction, regulator response", "escalation_authority": "External counsel", "quality_metrics": [ "Retraction latency" ], "workload_risks": [ "Retainer capacity" ] }, { "role": "Success lead", "responsibilities": [ "Delivery health, revision loop, Portfolio Desk renewal signal" ], "contexts": [ "Client Delivery & Success" ], "decisions_owned": [ "Escalate silent failures" ], "ai_support": [ "Delivery health digest" ], "approval_authority": "Customer-visible remediation", "escalation_authority": "Business owner / founder", "quality_metrics": [ "Time-to-alert on delivery failure" ], "workload_risks": [ "Alert fatigue" ] }, { "role": "Onboarding lead", "responsibilities": [ "Provision tenants, register the compliance analyst of record, import existing MCP/evidence pack" ], "contexts": [ "Client Onboarding & Tenant Profile" ], "decisions_owned": [ "Tenant readiness" ], "ai_support": [ "Checklist coverage" ], "approval_authority": "Go-live per tenant", "escalation_authority": "Business owner / founder", "quality_metrics": [ "Time-to-first-pack" ], "workload_risks": [ "Sequential onboarding queue" ] }, { "role": "Ops (prompt owner)", "responsibilities": [ "Prompt version registry + eval sign-off", "AHJ rule-library maintenance" ], "contexts": [ "AI Workbench & Extraction", "AHJ Rule Library & Retrieval" ], "decisions_owned": [ "Prompt rollout", "Rule-library edition updates" ], "ai_support": [ "Eval Agent" ], "approval_authority": "Prompt rollout", "escalation_authority": "Engineering", "quality_metrics": [ "Regression rate at rollout" ], "workload_risks": [ "Version drift", "AHJ edition tracking lag" ] } ], "human_review_checkpoints": [ "AI gap-matrix draft -> compliance analyst approval", "Missing-MCP or contested-code pack -> consultant release", "Public release-readiness claim -> business owner acceptance", "Retraction -> legal + consultant co-sign", "Prompt rollout -> ops + eval agent" ], "escalation_matrix": [ "AI extraction/orchestration layer -> Compliance analyst -> Licensed elevator consultant/QEI -> Business owner -> External counsel", "Success lead -> Business owner -> External counsel (AHJ/insurer inquiries)" ], "manual_override_rules": [ "Any manual override captured as an explicit override event with actor + reason", "No override may bypass the analyst/consultant release invariant" ], "separation_of_duties": [ "Extraction Agent cannot release a pack; Compliance analyst cannot author a technical MCP without consultant escalation; Legal reviewer cannot silently retract a pack" ], "quality_control_workflow": [ "Weekly analyst calibration meeting", "Monthly eval-agent regression report", "Quarterly retraction-rate review with business owner + legal" ], "data_objects": [ { "name": "ConveyanceIntake", "meaning": "Unit of intake work per building/conveyance batch brought in by the customer", "owner_context": "Completeness Pack Fulfillment", "writers": [ "Completeness Pack Fulfillment" ], "readers": [ "Release & Quality Assurance", "Analytics & Reporting" ], "source_of_truth": "Completeness Pack Fulfillment DB", "retention": "5 years + 6 months (mirrors ASME A17.1 §8.6.1.4 retention + buffer)", "privacy": "confidential", "audit": true }, { "name": "GapMatrix", "meaning": "Line-by-line cited comparison of required checklist items vs. evidence found", "owner_context": "Completeness Pack Fulfillment", "writers": [ "Completeness Pack Fulfillment" ], "readers": [ "Release & Quality Assurance", "Vendor Chase Desk", "Analytics & Reporting" ], "source_of_truth": "Completeness Pack Fulfillment DB + AHJ Rule Library pointers", "retention": "5 years + 6 months", "privacy": "confidential", "audit": true }, { "name": "Completeness Pack", "meaning": "Analyst/consultant-released deliverable", "owner_context": "Completeness Pack Fulfillment", "writers": [ "Completeness Pack Fulfillment" ], "readers": [ "Release & Quality Assurance", "Client Delivery & Success", "Analytics & Reporting" ], "source_of_truth": "Completeness Pack Fulfillment DB (immutable after release)", "retention": "5 years + 6 months (mirrors the §8.6.1.4 5-year duty + buffer)", "privacy": "regulated", "audit": true }, { "name": "Release", "meaning": "Analyst or consultant release attestation", "owner_context": "Release & Quality Assurance", "writers": [ "Release & Quality Assurance" ], "readers": [ "Completeness Pack Fulfillment", "Analytics & Reporting" ], "source_of_truth": "Release & Quality Assurance DB (append-only)", "retention": "5 years + 6 months", "privacy": "confidential", "audit": true }, { "name": "OwnerActionLedger", "meaning": "Blocker facts per tenant (e.g. vendor custody attestation, no-MCP-exists attestation)", "owner_context": "Compliance & Licensing Governance", "writers": [ "Compliance & Licensing Governance" ], "readers": [ "Completeness Pack Fulfillment (release decision)", "Analytics & Reporting" ], "source_of_truth": "Compliance & Licensing Governance DB", "retention": "5 years + 6 months", "privacy": "internal", "audit": true }, { "name": "ExtractionRun", "meaning": "Trace of one AI Workbench extraction run", "owner_context": "AI Workbench & Extraction", "writers": [ "AI Workbench & Extraction" ], "readers": [ "Analytics & Reporting", "Release & Quality Assurance (on escalation)" ], "source_of_truth": "AI Workbench & Extraction DB", "retention": "13 months (rolling)", "privacy": "internal", "audit": true }, { "name": "Tenant", "meaning": "Customer organization + registered compliance analyst / consultant of record", "owner_context": "Client Onboarding & Tenant Profile", "writers": [ "Client Onboarding & Tenant Profile" ], "readers": [ "all contexts" ], "source_of_truth": "Onboarding DB", "retention": "Life of contract + 3.5 years", "privacy": "confidential", "audit": true }, { "name": "VendorChaseCase", "meaning": "Open hard-gap cure cycle with vendor chase letters + cure evidence", "owner_context": "Vendor Chase Desk", "writers": [ "Vendor Chase Desk" ], "readers": [ "Completeness Pack Fulfillment", "Analytics & Reporting" ], "source_of_truth": "Vendor Chase Desk DB", "retention": "5 years + 6 months", "privacy": "confidential", "audit": true }, { "name": "Portfolio", "meaning": "Portfolio Desk enrollment, re-scan schedule, and rolling scorecard", "owner_context": "Portfolio & Recurring Programs", "writers": [ "Portfolio & Recurring Programs" ], "readers": [ "Client Delivery & Success", "Analytics & Reporting" ], "source_of_truth": "Portfolio & Recurring Programs DB", "retention": "Life of subscription + 2 years", "privacy": "confidential", "audit": true }, { "name": "Subscription + Invoice", "meaning": "Commercial relationship + charges (per-pack, Rush, Chase Desk, Portfolio Desk)", "owner_context": "Billing & Revenue", "writers": [ "Billing" ], "readers": [ "Analytics & Reporting" ], "source_of_truth": "Billing provider (Stripe)", "retention": "As required by tax law", "privacy": "confidential", "audit": true }, { "name": "User + Role", "meaning": "Identity + authorization", "owner_context": "Identity & Access", "writers": [ "Identity & Access" ], "readers": [ "all contexts" ], "source_of_truth": "Identity DB", "retention": "Life of account + 2 years", "privacy": "confidential", "audit": true } ], "read_models": [ "Operator dashboard read model (per tenant): open intakes, in-extraction, in-release, delivered this quarter", "Analyst queue read model: gap matrices awaiting release with confidence + escalation reason", "Compliance ledger read model: open owner actions + release-decision", "Portfolio scorecard read model: MCP completeness status across 5-40 buildings", "Analytics rollup read model: metric definitions rolled up daily" ], "reporting_models": [ "Outcome report per customer: packs delivered, cycle time, escalation rate, hard-gap cure rate", "Ops report: AI cost per pack, escalation rate, analyst load" ], "data_duplication_notes": [ "Compliance analyst / consultant of record is stored in Onboarding, referenced by Release & Quality Assurance -- QA does not own it", "OwnerActionLedger duplicates minimal facts into read models for Fulfillment consumption" ], "data_retention": [ "Completeness Packs + gap matrices + releases: 5 years + 6 months (mirrors the ASME A17.1 §8.6.1.4 5-year duty + buffer)", "ExtractionRun logs: 13 months rolling", "Users + sessions: life of account + 2 years" ], "data_quality_risks": [ "Silent schema drift from vendor invoice / CMMS systems", "Stale AHJ edition index after a rule-library update", "Missing retraction cross-links after legacy import" ], "use_cases": [ { "name": "Deliver an analyst-released or consultant-released Completeness Pack", "actor": "Customer operator + Compliance analyst", "context": "Completeness Pack Fulfillment + Release & Quality Assurance + AI Workbench & Extraction", "goal": "Produce and deliver a released Elevator MCP Completeness Pack for one building/conveyance", "preconditions": [ "Tenant provisioned", "Compliance analyst of record registered", "Engagement accepted" ], "main_flow": [ "Operator opens a conveyance intake", "Evidence ingested (MCP, logs, callbacks, inspections, machine-room photos)", "Extraction Agent drafts the gap matrix with citations", "Deterministic rules evaluate the hard gates", "Compliance analyst releases the pack (or escalates to consultant)", "Delivery adapter delivers the pack + chase kit + vault index", "Success lead confirms delivery" ], "alternative_flows": [ "Confidence below threshold or no MCP found -> EscalationRaised -> consultant authors/releases", "Blocking owner action open -> DeliveryBlocked -> surfaced to customer operator", "Delivery failure -> alert customer within 1h" ], "business_rules": [ "Every gap-matrix line cites evidence or is an explicit gap", "Only the tenant's registered analyst, or the escalated consultant, may release" ], "ai_role": "Extract + draft the gap matrix + score confidence", "human_role": "Release; escalate; retract", "commands": [ "OpenConveyanceIntake", "IngestEvidence", "StartExtractionRun", "EvaluateHardGates", "ReleasePack", "DeliverCompletenessPack" ], "events": [ "ConveyanceIntakeAccepted", "EvidenceIngested", "GapMatrixDrafted", "HardGatesEvaluated", "PackReleased", "PackDelivered" ], "aggregates": [ "ConveyanceIntakeAggregate", "GapMatrixAggregate", "ExtractionRunAggregate", "ReleaseAggregate", "CompletenessPackAggregate" ], "success": "Completeness Pack delivered + release attached + audit trail complete", "failure_handling": "EscalationRaised -> consultant queue; DeliveryFailed -> customer alert + Success ticket", "audit": "Full command -> event chain with actor + timestamp per step" }, { "name": "Run a vendor cure chase cycle and close a hard gap", "actor": "Compliance analyst", "context": "Vendor Chase Desk + Completeness Pack Fulfillment", "goal": "Recover missing vendor records and clear a flagged hard gap", "preconditions": [ "HardGatesEvaluated flagged a vendor-attributable gap", "Chase Desk purchased" ], "main_flow": [ "Analyst dispatches a chase letter", "Vendor responds with cure evidence", "Analyst confirms cure evidence against the original clause", "Gap matrix re-scored" ], "alternative_flows": [ "Vendor refuses to respond -> repeat chase cadence / escalate to owner demand", "Cure evidence incomplete -> gap stays open" ], "business_rules": [ "Cure evidence must cite the original hard-gap clause", "No cure marked closed without a sourced document" ], "ai_role": "Draft chase letters; flag stale cases", "human_role": "Confirm cure evidence; close or re-escalate", "commands": [ "DispatchChaseLetter", "ConfirmVendorCure" ], "events": [ "ChaseLetterDispatched", "HardGapCured" ], "aggregates": [ "VendorChaseCaseAggregate", "GapMatrixAggregate" ], "success": "Hard gap cured within 30 days and reflected in an updated gap matrix", "failure_handling": "VendorCureRejected -> chase case remains open, escalate to owner", "audit": "Chase letter + cure evidence archived, immutable" }, { "name": "Resolve an owner action and flip release decision", "actor": "Customer operator (attesting for the building owner)", "context": "Compliance & Licensing Governance", "goal": "Close a blocking owner-supplied fact and recompute release readiness", "preconditions": [ "Owner action open" ], "main_flow": [ "Owner/operator supplies fact (e.g. vendor MCP custody attestation)", "Ledger updated", "Release decision recomputed", "Downstream contexts notified" ], "alternative_flows": [ "Fact rejected -> OwnerActionRejected", "Legal review required -> route to legal reviewer" ], "business_rules": [ "Release cannot flip to ready with any blocking action open" ], "ai_role": "Blocker digest", "human_role": "Supply fact + accept release", "commands": [ "ResolveOwnerAction" ], "events": [ "OwnerActionResolved" ], "aggregates": [ "OwnerActionLedgerAggregate" ], "success": "Release decision flips or stays with a clear reason", "failure_handling": "OwnerActionRejected + retry loop", "audit": "Actor + before/after + timestamp" }, { "name": "Retract a delivered Completeness Pack", "actor": "Legal reviewer + Licensed elevator consultant/QEI", "context": "Release & Quality Assurance + Compliance & Licensing Governance", "goal": "Formally withdraw or correct a delivered pack after a material finding", "preconditions": [ "Pack previously delivered", "Material finding documented" ], "main_flow": [ "Finding documented", "Legal reviewer + consultant co-sign the retraction", "Customer notified", "Audit-log append" ], "alternative_flows": [ "Consultant disagrees -> escalate to business owner", "AHJ/insurer inquiry incoming -> run in parallel with legal-response workflow" ], "business_rules": [ "Retraction requires Legal + Consultant co-sign" ], "ai_role": "Surface prior similar cases (assist only)", "human_role": "Co-sign + notify", "commands": [ "RetractPack" ], "events": [ "PackRetracted" ], "aggregates": [ "PackRetractionAggregate", "OwnerActionLedgerAggregate" ], "success": "Retraction filed + customer notified + audit trail updated", "failure_handling": "RetractionRejected path escalates to business owner", "audit": "Full retraction packet archived, immutable" } ], "architecture": { "style": "modular-monolith-event-driven", "why": "Single team + single regulated vertical (elevator MCP documentation completeness) per blueprint + strong consistency requirements around release / delivery / release-decision favor a monolith. Event-driven internals give an audit-friendly append-only log without the operational cost of microservices.", "rejected_alternatives": [ "Microservices -- no independent scaling or team boundary justifies distributed cost yet.", "Serverless-workflow-only -- analyst release and audit invariants are easier to keep correct in a monolith.", "No-code / low-code -- cannot enforce OutputValidator, prompt versioning, or per-tenant retrieval isolation with fidelity." ], "backend_modules": [ "Completeness Pack Fulfillment", "AI Workbench & Extraction", "Release & Quality Assurance", "Compliance & Licensing Governance", "AHJ Rule Library & Retrieval", "Sales & Intake", "Client Onboarding & Tenant Profile", "Client Delivery & Success", "Vendor Chase Desk", "Portfolio & Recurring Programs", "Analytics & Reporting" ], "frontend_modules": [ "Operator dashboard", "Analyst console", "Consultant escalation console", "Client portal", "Business owner console", "Ops (prompt registry) console" ], "api_boundaries": [ "/intake/*", "/packs/*", "/analyst/*", "/compliance/*", "/knowledge/*", "/chase/*", "/portfolio/*", "/admin/*" ], "database_strategy": "One managed Postgres; schema-per-context; cross-context reads via published projections; RLS on protected tables.", "event_bus": "In-process event dispatcher backed by an outbox table (transactional publish); upgrade path to a real broker if throughput demands.", "queue": "Background job queue (managed) for extraction runs, delivery adapters, and reindex jobs.", "workflow_engine": "None initially -- orchestrate via domain events + policies; add a workflow engine if orchestrations exceed 5 sequential steps.", "ai_orchestration": "AI Workbench & Extraction context owns bounded agents; OutputValidator + prompt registry + tenant-scoped retrieval; retries with backoff.", "rag_layer": "Per-tenant partitioned evidence indices plus a shared AHJ edition checklist index in a managed vector DB; ingestion pipeline in the AHJ Rule Library & Retrieval context.", "file_storage": "Managed blob storage with per-tenant prefixes + signed URLs; MCPs, logs, and photos hashed on write.", "authn_authz": "IdP (Google / Okta) for authn; RBAC via a dedicated roles table with server-side checks + RLS.", "admin_dashboard": "Ops-facing admin for tenants, users, feature flags, prompt versions, and the AHJ edition library.", "client_portal": "Customer-facing portal: submit intake, see gap-matrix status, receive packs and chase kits.", "operator_dashboard": "Internal: intake queue, analyst queue, escalation queue, delivery health, chase-case queue.", "observability": "Structured logs with tenant + request ids; RED metrics per workflow; error tracking with source maps; model-call spans with cost + latency; SLO review weekly.", "audit_logging": "Append-only audit log for all state transitions; hash-chained snapshots on released packs.", "deployment": "Single production region + multi-AZ managed DB; per-PR preview deploys; migrations gated on review." }, "module_structure": { "tree": "/src\n /contexts\n /sales-intake\n /domain\n /application\n /infrastructure\n /interfaces\n /client-onboarding\n /domain\n /application\n /infrastructure\n /interfaces\n /completeness-pack-fulfillment\n /domain\n /application\n /infrastructure\n /interfaces\n /ai-workbench-extraction\n /domain\n /application\n /infrastructure\n /interfaces\n /release-quality-assurance\n /domain\n /application\n /infrastructure\n /interfaces\n /ahj-rule-library\n /domain\n /application\n /infrastructure\n /interfaces\n /compliance-licensing-governance\n /domain\n /application\n /infrastructure\n /interfaces\n /vendor-chase-desk\n /domain\n /application\n /infrastructure\n /interfaces\n /portfolio-recurring-programs\n /domain\n /application\n /infrastructure\n /interfaces\n /client-delivery\n /domain\n /application\n /infrastructure\n /interfaces\n /analytics\n /domain\n /application\n /infrastructure\n /interfaces\n /shared\n /kernel # tiny -- Ids, Money, Tenant, Actor\n /events # published-language event contracts\n /auth # session + role primitives\n /observability # logging, metrics, tracing\n /config", "modules": [ { "name": "completeness-pack-fulfillment", "purpose": "ConveyanceIntake -> GapMatrix -> Completeness Pack lifecycle", "owned_domain": [ "ConveyanceIntake", "GapMatrix", "Completeness Pack", "Delivery" ], "application_services": [ "OpenConveyanceIntake", "IngestEvidence", "EvaluateHardGates", "DeliverCompletenessPack" ], "infra_adapters": [ "Delivery adapter", "Outbox publisher" ], "public_interfaces": [ "/intake/*", "/packs/*" ], "forbidden_deps": [ "billing infra", "identity provider internals" ] }, { "name": "ai-workbench-extraction", "purpose": "Bounded AI extraction + classification agents", "owned_domain": [ "ExtractionRun", "PromptVersion" ], "application_services": [ "StartExtractionRun", "PublishPromptVersion" ], "infra_adapters": [ "OpenAI/Anthropic client", "Retrieval router" ], "public_interfaces": [ "internal" ], "forbidden_deps": [ "cross-tenant retrieval", "direct delivery" ] }, { "name": "release-quality-assurance", "purpose": "Release + retraction", "owned_domain": [ "Release", "PackRetraction" ], "application_services": [ "ReleasePack", "RetractPack" ], "infra_adapters": [ "Release service" ], "public_interfaces": [ "/analyst/*" ], "forbidden_deps": [ "gap-matrix content mutation" ] }, { "name": "compliance-licensing-governance", "purpose": "Owner-action ledger + release decision + licensing-boundary enforcement", "owned_domain": [ "OwnerActionLedger", "ReleaseDecision", "DSARRequest" ], "application_services": [ "ResolveOwnerAction", "ProcessDSAR" ], "infra_adapters": [ "Email adapter" ], "public_interfaces": [ "/compliance/*" ], "forbidden_deps": [ "gap-matrix content" ] } ], "dependency_rules": [ "Domain layer must not depend on infrastructure.", "Application layer may depend on domain.", "Infrastructure implements ports defined by application/domain.", "Interfaces call application services.", "Shared kernel must remain small (Ids, Money, Tenant, Actor).", "Contexts communicate through published events or explicit application APIs -- never via direct database access to another context." ] }, "security_governance": { "controls": [ { "risk": "Prompt injection via vendor invoice/log content", "context": "AI Workbench & Extraction", "impact": "high", "control": "Input scrubber + OutputValidator + tenant-scoped retrieval", "audit": "ExtractionRun trace" }, { "risk": "Cross-tenant retrieval leak", "context": "AHJ Rule Library & Retrieval", "impact": "severe", "control": "Per-tenant index partitions + TenantIsolationSpec enforced at router", "audit": "Retrieval call log" }, { "risk": "Release-signature spoofing", "context": "Release & Quality Assurance", "impact": "severe", "control": "Release bound to authenticated session; server-side validation", "audit": "Release manifest" }, { "risk": "Premature public claim of inspection-readiness", "context": "Compliance & Licensing Governance", "impact": "high", "control": "ReleaseReadinessSpec on OwnerActionLedger", "audit": "Release-decision log" }, { "risk": "Privilege escalation", "context": "Identity & Access", "impact": "high", "control": "Roles in dedicated table + server-side checks + RLS", "audit": "Role assignment log" }, { "risk": "Silent delivery failure ahead of an inspection date", "context": "Client Delivery & Success", "impact": "medium", "control": "Adapter receipt required; alert customer within 1h on failure", "audit": "Delivery receipt archive" } ], "ai_governance": [ "Every prompt version has a named owner + eval run + rollout flag", "AI outputs marked as drafts until analyst or consultant release", "Model + prompt inventory maintained in the Ops console" ], "prompt_injection_defense": [ "Strip / neutralize instruction-like patterns in vendor and customer inputs before prompt assembly", "Never concatenate raw vendor/customer input into a system prompt", "OutputValidator rejects outputs that reference forbidden actions" ], "sensitive_data_handling": [ "PII scrubbed from logs", "Regulated data classes never sent to external model providers unless a DPA covers it", "Per-tenant blob storage prefixes + signed URLs" ], "access_control_matrix": [ { "role": "Customer operator", "context": "Completeness Pack Fulfillment", "capabilities": [ "OpenConveyanceIntake", "IngestEvidence", "View own packs" ] }, { "role": "Compliance analyst", "context": "Release & Quality Assurance", "capabilities": [ "ReleasePack (green/yellow)", "Escalate to consultant" ] }, { "role": "Licensed elevator consultant / QEI", "context": "Release & Quality Assurance", "capabilities": [ "ReleasePack (red)", "Author/certify MCP", "Co-sign retraction" ] }, { "role": "Business owner / founder", "context": "Compliance & Licensing Governance", "capabilities": [ "ResolveOwnerAction", "Set release-readiness decision" ] }, { "role": "Legal reviewer", "context": "Release & Quality Assurance + Compliance", "capabilities": [ "Co-sign retraction", "Handle DSAR" ] }, { "role": "Ops", "context": "AI Workbench & Extraction", "capabilities": [ "PublishPromptVersion", "Set confidence threshold" ] }, { "role": "Platform admin", "context": "Identity & Access", "capabilities": [ "Provision users", "Assign roles" ] } ], "audit_log_requirements": [ "Append-only", "Actor + tenant + timestamp + command + before/after hash", "PII scrubbed", "Exportable per tenant on request (DSAR support)" ] }, "observability": { "metrics": [ { "metric": "Released Completeness Packs / week / tenant", "type": "business", "context": "Completeness Pack Fulfillment", "why": "North star: repeatable value delivery", "target": ">= contracted cadence", "alert_threshold": "< 80% of contracted cadence" }, { "metric": "Scan-to-paid conversion", "type": "business", "context": "Sales & Intake", "why": "Validates the Gap Scan lead magnet", "target": ">= 25%", "alert_threshold": "< 15% monthly" }, { "metric": "AI gap-matrix draft acceptance rate", "type": "ai-quality", "context": "AI Workbench & Extraction", "why": "Signals grounding + prompt fit", "target": ">= 70% by Phase 2", "alert_threshold": "< 50% weekly" }, { "metric": "Escalation-to-consultant rate", "type": "ai-quality", "context": "AI Workbench & Extraction", "why": "Guardrails firing correctly, not over- or under-escalating", "target": "<= 15% of packs", "alert_threshold": "> 30% weekly" }, { "metric": "Cycle time to release (p50 + p95)", "type": "operational", "context": "Release & Quality Assurance", "why": "Analyst throughput vs the 7-business-day / 5-day rush standard", "target": "p95 <= 7 business days standard, <= 5 rush", "alert_threshold": "> 7 business days" }, { "metric": "Hard-gap cure rate within 30 days", "type": "business", "context": "Vendor Chase Desk", "why": "Chase Desk value delivered", "target": ">= 70% when Chase Desk purchased", "alert_threshold": "< 50% monthly" }, { "metric": "Delivery failure rate", "type": "reliability", "context": "Client Delivery & Success", "why": "Customer-facing reliability ahead of inspection dates", "target": "< 0.5%", "alert_threshold": "> 1% daily" }, { "metric": "Owner-action open count", "type": "business", "context": "Compliance & Licensing Governance", "why": "Release-readiness for public claims", "target": "0 for launched blueprints", "alert_threshold": "any blocker aging > 30 days" }, { "metric": "Model cost per pack", "type": "financial", "context": "AI Workbench & Extraction", "why": "Margin control against the >=55% gross-margin target", "target": "<= target per pricing tier", "alert_threshold": "> 1.5x target" }, { "metric": "Cross-tenant retrieval violation attempts", "type": "risk", "context": "AHJ Rule Library & Retrieval", "why": "Security invariant", "target": "0", "alert_threshold": "any > 0" } ], "dashboards": [ "Operator dashboard", "Analyst queue", "Delivery health", "AI cost + escalation", "Compliance blockers" ], "audit_reports": [ "Per-tenant audit-log export", "Release manifest export" ], "quality_review_reports": [ "Analyst calibration report", "Escalation-outcome report" ], "ai_evaluation_reports": [ "Eval Agent regression report", "Prompt-rollout diff" ], "client_outcome_reports": [ "Packs delivered", "Cycle time", "Hard-gap cure rate" ] }, "testing_strategy": { "tests": [ { "type": "Domain unit", "validates": "Aggregate invariants", "context": "all core contexts", "example": "CompletenessPackAggregate rejects delivery without a release" }, { "type": "Aggregate invariant", "validates": "Consistency boundaries", "context": "Completeness Pack Fulfillment / Release & QA", "example": "Released pack is immutable" }, { "type": "Policy", "validates": "Reactive rules", "context": "AI Workbench & Extraction", "example": "Escalates below confidence threshold or on no-MCP-found" }, { "type": "Specification", "validates": "Reusable rules", "context": "Compliance & Licensing Governance", "example": "ReleaseReadinessSpec blocks 'ready' with open owner actions" }, { "type": "Application use-case", "validates": "End-to-end command flow", "context": "Fulfillment + QA", "example": "Deliver a released Completeness Pack happy path" }, { "type": "Integration", "validates": "Adapter behavior", "context": "External Integrations", "example": "Vendor invoice inbox adapter translates correctly" }, { "type": "Contract", "validates": "Published-language event schemas", "context": "cross-context", "example": "GapMatrixDrafted payload matches consumer expectations" }, { "type": "AI prompt eval", "validates": "Prompt quality vs golden dataset", "context": "AI Workbench & Extraction", "example": "Extraction Agent accepts >= 40% in shadow mode" }, { "type": "RAG retrieval", "validates": "Tenant isolation + AHJ-edition coverage", "context": "AHJ Rule Library & Retrieval", "example": "Cross-tenant lookup returns zero rows" }, { "type": "Golden dataset", "validates": "AI regression", "context": "AI Workbench & Extraction", "example": "No regression on past released packs" }, { "type": "Human review simulation", "validates": "Escalation UX", "context": "Release & Quality Assurance", "example": "Analyst can complete a release in <= 5 clicks" }, { "type": "End-to-end", "validates": "Critical path", "context": "all", "example": "Intake -> release -> delivery in staging" }, { "type": "Security", "validates": "Auth + RLS + injection defense", "context": "Identity + AI Workbench & Extraction", "example": "Prompt-injection payload is neutralized" }, { "type": "Regression", "validates": "No drift on prior fixes", "context": "all", "example": "Prior retraction bug does not reappear" } ], "critical_domain_rules": [ "No delivery without a release", "No AI extraction output without an OutputValidator pass", "No AHJ retrieval outside the correct edition or tenant partition", "No public release-readiness claim with open blockers" ], "ai_eval_dataset": [ "50 past analyst-released Completeness Packs per AHJ (redacted)", "20 rejected drafts (ground truth for escalation)", "10 injection-payload cases" ], "regression_plan": "Every PR runs domain + policy + spec unit tests. Every prompt release runs the Eval Agent with a regression gate. Weekly critical-path smoke test in staging.", "contract_testing_plan": "Published-language event schemas versioned in /shared/events; consumer tests run in CI against schema-version compatibility.", "manual_qa_checklist": [ "Release flow: signature captured + timestamp + hash", "Retraction flow: co-sign captured + customer notified", "Delivery flow: receipt archived", "DSAR flow: export completes end-to-end" ] }, "mvp_roadmap": [ { "phase": "Phase 0 -- Manual workflow with instrumented capture", "goal": "Deliver one Completeness Pack end-to-end manually, capture every step as a domain event.", "features": [ "Manual intake form", "Evidence upload", "Human-drafted gap matrix", "Analyst release via signed form" ], "contexts": [ "Sales & Intake", "Completeness Pack Fulfillment", "Release & Quality Assurance" ], "ai_needs": [ "[PLACEHOLDER] owner to complete" ], "human_workflows": [ "Analyst release" ], "data_needs": [ "ConveyanceIntake", "GapMatrix", "Completeness Pack" ], "integrations": [ "Email" ], "risks": [ "Un-audited manual step" ], "exit_criteria": [ "1 real Completeness Pack delivered + analyst-released" ] }, { "phase": "Phase 1 -- AI-assisted extraction for internal use only", "goal": "Introduce the Extraction Agent with an analyst gate; no customer-facing AI language.", "features": [ "Extraction Agent (internal)", "OutputValidator", "Escalation route" ], "contexts": [ "AI Workbench & Extraction", "Completeness Pack Fulfillment" ], "ai_needs": [ "Extraction Agent, Routing & Classification Agent" ], "human_workflows": [ "Escalation review" ], "data_needs": [ "ExtractionRun", "PromptVersion" ], "integrations": [ "OpenAI / Anthropic" ], "risks": [ "Prompt injection", "Grounding drift" ], "exit_criteria": [ "AI draft acceptance rate >= 40% in shadow mode" ] }, { "phase": "Phase 2 -- Operator dashboard + owner-action ledger", "goal": "Make the workflow legible and governable for the business owner.", "features": [ "Operator dashboard", "Owner-action ledger", "Release-decision engine" ], "contexts": [ "Compliance & Licensing Governance" ], "ai_needs": [], "human_workflows": [ "Owner action resolution" ], "data_needs": [ "OwnerActionLedger" ], "integrations": [ "IdP" ], "risks": [ "Ungoverned public claims" ], "exit_criteria": [ "Release decisions computed from the ledger" ] }, { "phase": "Phase 3 -- Client delivery portal + Vendor Chase Desk", "goal": "Give customers a portal to see gap-matrix status and receive packs and chase kits.", "features": [ "Client portal", "Delivery adapter", "Vendor Chase Desk case tracking" ], "contexts": [ "Client Delivery & Success", "Vendor Chase Desk" ], "ai_needs": [ "Chase-letter drafting" ], "human_workflows": [ "Success cadence", "Chase-case management" ], "data_needs": [ "Delivery", "VendorChaseCase" ], "integrations": [ "Email" ], "risks": [ "Silent delivery failure" ], "exit_criteria": [ "Delivery-failure alert within 1h" ] }, { "phase": "Phase 4 -- Automated QA, Portfolio Desk, and reporting", "goal": "Wire metrics, the retraction runbook, the eval agent, and Portfolio Desk enrollment.", "features": [ "Eval Agent", "Retraction workflow", "Portfolio Desk enrollment + quarterly re-scan", "Dashboards" ], "contexts": [ "Analytics & Reporting", "Release & Quality Assurance", "Portfolio & Recurring Programs" ], "ai_needs": [ "Eval Agent" ], "human_workflows": [ "Retraction co-sign" ], "data_needs": [ "PackRetraction", "Portfolio" ], "integrations": [], "risks": [ "Vanity metrics" ], "exit_criteria": [ "North-star + guardrail metrics live" ] }, { "phase": "Phase 5 -- Scale + optimization", "goal": "Reduce cost per pack, increase analyst throughput, expand AHJ coverage.", "features": [ "Prompt versioning UI", "Cost budgeting", "Multi-analyst queue", "Third AHJ edition onboarded" ], "contexts": [ "AI Workbench & Extraction", "Release & Quality Assurance", "AHJ Rule Library & Retrieval" ], "ai_needs": [ "Cost meter" ], "human_workflows": [ "Multi-analyst routing" ], "data_needs": [], "integrations": [], "risks": [ "Regression on rollout" ], "exit_criteria": [ "Model cost per pack <= target" ] } ], "scaling_roadmap": [ { "stage": "<= 5 tenants", "trigger": "Design-partner / pilot cohort (8-building cap)", "architecture_change": "Single-region modular monolith + managed DB", "operational_change": "Founder-led ops; weekly working session", "risk": "Single-analyst queue" }, { "stage": "5-25 tenants", "trigger": "First paid conversions past the pilot cap", "architecture_change": "Extract the heaviest module (AI Workbench & Extraction) behind an internal queue; keep the monolith", "operational_change": "Named on-call rotation; SOC 2 Type I scoping", "risk": "Analyst bottleneck" }, { "stage": "25-100 tenants", "trigger": "Multi-analyst demand and a third AHJ edition", "architecture_change": "Split AI Workbench & Extraction into its own service if throughput/isolation demands it; per-tenant retrieval sharding", "operational_change": "Dedicated success + prompt-ops roles", "risk": "Prompt version drift" }, { "stage": "100+ tenants", "trigger": "Enterprise portfolios and additional high-enforcement AHJs", "architecture_change": "Regional deployments; per-region data residency; segregated compliance environments", "operational_change": "Dedicated SRE + compliance team; SOC 2 Type II + framework additions", "risk": "Compliance framework demand exceeds team capacity" } ], "risk_register": [ { "risk": "AHJ edition mismatch causes a false hard-fail", "likelihood": "medium", "impact": "high", "signal": "See ProductBlueprintDNA / risk register for tuned early-warning signals", "mitigation": "Maintain edition-dated checklist cards; cite the edition on every pack; dual-check Colorado and Virginia first", "owner": "engineering", "context": "AHJ Rule Library & Retrieval" }, { "risk": "Client expects a guaranteed inspection pass", "likelihood": "high", "impact": "high", "signal": "See ProductBlueprintDNA / risk register for tuned early-warning signals", "mitigation": "Contract language: documentation-readiness support only; owner remains responsible party; no pass guarantee", "owner": "legal", "context": "Compliance & Licensing Governance" }, { "risk": "Licensed elevator consultant partners perceive MCPVault as a competitor", "likelihood": "medium", "impact": "medium", "signal": "See ProductBlueprintDNA / risk register for tuned early-warning signals", "mitigation": "Refer technical MCP authorship out; revenue-share on escalations; position as a referral funnel", "owner": "owner", "context": "Release & Quality Assurance" }, { "risk": "OEM/vendor refuses to share MCP or service logs", "likelihood": "high", "impact": "medium", "signal": "See ProductBlueprintDNA / risk register for tuned early-warning signals", "mitigation": "Owner-property framing; contract clause templates; photo of the on-site binder; escalate to owner demand", "owner": "ops", "context": "Vendor Chase Desk" }, { "risk": "Fabricated or AI-hallucinated log dates in a released pack", "likelihood": "low", "impact": "high", "signal": "See ProductBlueprintDNA / risk register for tuned early-warning signals", "mitigation": "Evidence citations mandatory; QA red-team; no free-text dates without a source span", "owner": "engineering", "context": "AI Workbench & Extraction" }, { "risk": "DeviceClear brand confusion", "likelihood": "medium", "impact": "medium", "signal": "See ProductBlueprintDNA / risk register for tuned early-warning signals", "mitigation": "Explicit 'not a filing service' positioning; separate slug/brand", "owner": "owner", "context": "Sales & Intake" }, { "risk": "Cybersecurity module scope creep (A17.1-2025 networked-control content)", "likelihood": "medium", "impact": "medium", "signal": "See ProductBlueprintDNA / risk register for tuned early-warning signals", "mitigation": "Optional AHJ-conditional checklist module only; do not block the MVP", "owner": "engineering", "context": "AHJ Rule Library & Retrieval" }, { "risk": "Low willingness-to-pay vs. a 'good enough' free vendor PDF", "likelihood": "medium", "impact": "high", "signal": "See ProductBlueprintDNA / risk register for tuned early-warning signals", "mitigation": "Gap Scan shows the generic/incomplete MCP; price against coordinator hours + inspection risk", "owner": "owner", "context": "Sales & Intake" }, { "risk": "Litigation-discovery subpoena of the vault", "likelihood": "low", "impact": "high", "signal": "See ProductBlueprintDNA / risk register for tuned early-warning signals", "mitigation": "Retention policy; client-owned vault option; legal review of the MSA", "owner": "legal", "context": "Compliance & Licensing Governance" }, { "risk": "Analyst shortage / early demand trap", "likelihood": "medium", "impact": "high", "signal": "See ProductBlueprintDNA / risk register for tuned early-warning signals", "mitigation": "Hard pilot cap of 8 buildings; build-before-scale gates", "owner": "ops", "context": "Release & Quality Assurance" }, { "risk": "Mis-selling as engineering / QEI services", "likelihood": "medium", "impact": "high", "signal": "See ProductBlueprintDNA / risk register for tuned early-warning signals", "mitigation": "Licensing-boundary training; website disclaimers; escalation SOP", "owner": "legal", "context": "Compliance & Licensing Governance" }, { "risk": "Portfolio Desk scope-creeps into unpaid custom consulting", "likelihood": "medium", "impact": "medium", "signal": "See ProductBlueprintDNA / risk register for tuned early-warning signals", "mitigation": "Scope menu; change-order for authorship; weekly cap", "owner": "ops", "context": "Portfolio & Recurring Programs" } ], "adrs": [ { "id": "ADR-001", "decision": "Architecture style", "status": "accepted", "context": "Single team, single regulated vertical (elevator MCP documentation) per blueprint, evidence-linked workflow.", "options": [ "Modular monolith", "Microservices", "Serverless workflow", "No-code first" ], "chosen": "Modular monolith with event-driven internals", "business_reason": "Ship a defensible vertical slice with one team; avoid distributed-systems cost until scale forces it.", "technical_reason": "Deterministic transactions across aggregates; simpler ops; one deployable.", "tradeoffs": [ "May feel unsophisticated to enterprise reviewers", "Refactor cost if we later split" ], "risks": [ "Module boundaries erode without discipline" ], "revisit_trigger": "Any single module needs independent scaling or a team boundary." }, { "id": "ADR-002", "decision": "Bounded context boundaries", "status": "accepted", "context": "Domain analysis above; distinct language groups for Fulfillment, AI Workbench, Release & QA, Compliance & Licensing.", "options": [ "Contexts as above", "One big 'app' context", "Contexts split by UI page" ], "chosen": "Contexts as above (domain-derived)", "business_reason": "Protects the release invariant + owner-action ledger + evidence spine as first-class boundaries.", "technical_reason": "Aggregates align to consistency boundaries; ACLs contain external mess.", "tradeoffs": [ "More code organization discipline" ], "risks": [ "Team tries to bypass the ACL for speed" ], "revisit_trigger": "New subdomain emerges (e.g. a self-serve marketplace)." }, { "id": "ADR-003", "decision": "Database ownership", "status": "accepted", "context": "Modular monolith with a shared Postgres; per-context schemas.", "options": [ "One shared schema", "Schema per context", "DB per context" ], "chosen": "Schema per context in a shared Postgres, cross-context reads only via published projections.", "business_reason": "Keeps operational cost low; enforces boundaries without paying the multi-DB tax.", "technical_reason": "RLS + schema separation gives ownership clarity.", "tradeoffs": [ "Discipline required to avoid cross-schema joins" ], "risks": [ "Bypass joins for speed" ], "revisit_trigger": "A context needs independent scaling or residency." }, { "id": "ADR-004", "decision": "AI orchestration strategy", "status": "accepted", "context": "Retrieval-first with structured-output validation + human release gate.", "options": [ "Open-ended chat", "Retrieval-first + validated", "Autonomous multi-agent" ], "chosen": "Retrieval-first + structured validation + analyst/consultant release gate", "business_reason": "Grounding and inspection defensibility are the paid outcome.", "technical_reason": "OutputValidator gives a hard boundary before drafts leave AI Workbench & Extraction.", "tradeoffs": [ "Slower than agentic chat" ], "risks": [ "Prompt version regression" ], "revisit_trigger": "The Eval Agent shows a step-function accuracy gain from a new pattern." }, { "id": "ADR-005", "decision": "Human review strategy", "status": "accepted", "context": "Regulated vertical; brand + liability-adjacent risk on wrong outputs.", "options": [ "No human review (fully automated)", "Sampling review", "Every-pack review" ], "chosen": "Every-pack review by a named compliance analyst (or licensed consultant on red packs)", "business_reason": "Release is the trust primitive.", "technical_reason": "Release bound to session; append-only log.", "tradeoffs": [ "Analyst throughput becomes the bottleneck" ], "risks": [ "Analyst burnout during high-enforcement season" ], "revisit_trigger": "Sustained low retraction rate + AHJ acceptance." }, { "id": "ADR-006", "decision": "Integration strategy", "status": "accepted", "context": "External systems: vendor invoice inboxes, elevator-vendor work-order/CMMS platforms, customer document portals, ...", "options": [ "Direct API coupling", "Anti-corruption layer per system", "Middleware bus (Zapier/n8n)" ], "chosen": "Anti-corruption layer per system, owned by the External Integrations context", "business_reason": "External schemas must never leak into the core.", "technical_reason": "Adapters translate + validate; upstream breakage is contained.", "tradeoffs": [ "More code than direct coupling" ], "risks": [ "Adapter lag on upstream change" ], "revisit_trigger": "External system stability changes materially." }, { "id": "ADR-007", "decision": "Modular monolith vs microservices", "status": "accepted", "context": "Same as ADR-001.", "options": [ "Monolith", "Microservices" ], "chosen": "Monolith", "business_reason": "Team size and scale do not justify microservices cost.", "technical_reason": "Distributed transactions across release/delivery would be a nightmare early.", "tradeoffs": [ "Refactor cost later" ], "risks": [ "Cultural expectation drift" ], "revisit_trigger": "See ADR-001." }, { "id": "ADR-008", "decision": "Build vs buy for generic subdomains", "status": "accepted", "context": "Billing, Identity, IdP, email.", "options": [ "Build all", "Buy generics" ], "chosen": "Buy generics (Stripe, IdP, transactional email)", "business_reason": "Do not spend core-domain hours on solved categories.", "technical_reason": "Standard SDKs + well-documented failure modes.", "tradeoffs": [ "Vendor risk" ], "risks": [ "Vendor lock-in" ], "revisit_trigger": "Cost or reliability materially degrades." } ], "self_audit": { "scores": [ { "category": "Domain accuracy", "score": 8, "weakness": "None material at this stage.", "improvement": "Maintain the current standard; re-audit after the first pilot buildings land real data." }, { "category": "Ubiquitous language quality", "score": 8, "weakness": "None material at this stage.", "improvement": "Maintain the current standard; re-audit after the first pilot buildings land real data." }, { "category": "Subdomain classification quality", "score": 8, "weakness": "None material at this stage.", "improvement": "Maintain the current standard; re-audit after the first pilot buildings land real data." }, { "category": "Bounded context clarity", "score": 9, "weakness": "None material at this stage.", "improvement": "Maintain the current standard; re-audit after the first pilot buildings land real data." }, { "category": "Core domain focus", "score": 9, "weakness": "None material at this stage.", "improvement": "Maintain the current standard; re-audit after the first pilot buildings land real data." }, { "category": "Context map quality", "score": 8, "weakness": "None material at this stage.", "improvement": "Maintain the current standard; re-audit after the first pilot buildings land real data." }, { "category": "Aggregate design quality", "score": 8, "weakness": "None material at this stage.", "improvement": "Maintain the current standard; re-audit after the first pilot buildings land real data." }, { "category": "Invariant quality", "score": 9, "weakness": "None material at this stage.", "improvement": "Maintain the current standard; re-audit after the first pilot buildings land real data." }, { "category": "AI-agent responsibility design", "score": 9, "weakness": "None material at this stage.", "improvement": "Maintain the current standard; re-audit after the first pilot buildings land real data." }, { "category": "Human review safety", "score": 9, "weakness": "None material at this stage.", "improvement": "Maintain the current standard; re-audit after the first pilot buildings land real data." }, { "category": "Data ownership clarity", "score": 8, "weakness": "None material at this stage.", "improvement": "Maintain the current standard; re-audit after the first pilot buildings land real data." }, { "category": "Integration protection", "score": 8, "weakness": "None material at this stage.", "improvement": "Maintain the current standard; re-audit after the first pilot buildings land real data." }, { "category": "Implementation feasibility", "score": 8, "weakness": "None material at this stage.", "improvement": "Maintain the current standard; re-audit after the first pilot buildings land real data." }, { "category": "Scalability", "score": 7, "weakness": "Single-region; single-analyst bottleneck; monolith split not yet planned.", "improvement": "Add a per-tenant extraction queue + multi-analyst routing at Phase 2." }, { "category": "Security and compliance", "score": 7, "weakness": "High-trust, liability-adjacent vertical needs Type II mapping and per-AHJ controls earlier.", "improvement": "Map controls at Phase 1; commit to Type II by Phase 3." }, { "category": "Testing strategy", "score": 8, "weakness": "None material at this stage.", "improvement": "Maintain the current standard; re-audit after the first pilot buildings land real data." }, { "category": "Operational realism", "score": 7, "weakness": "Founder-led ops assumed through Phase 2; brittle to key-person absence.", "improvement": "Document runbooks; cross-train a success + prompt-ops role by Phase 2." }, { "category": "MVP practicality", "score": 9, "weakness": "None material at this stage.", "improvement": "Maintain the current standard; re-audit after the first pilot buildings land real data." } ], "weakest_parts": [ "Scalability plan assumes a single compliance analyst per tenant through Phase 2", "Operational realism depends on founder-led ops", "Compliance framework depth for Type II" ], "biggest_assumptions": [ "The target audience will pay for a released, checklist-cited documentation-completeness pack over a free vendor-supplied PDF.", "A Completeness Pack can be reconstructed from an owner-supplied evidence set within the standard 7-business-day cycle.", "The vertical tolerates AI-assisted extraction and drafting when compliance-analyst review is explicit and audit-traceable." ], "highest_risk_decisions": [ "Modular monolith (ADR-001)", "Every-pack analyst/consultant release (ADR-005)", "Anti-corruption layer per external system (ADR-006)" ], "needs_domain_expert": [ "Licensed elevator consultant / QEI to validate release-gate ergonomics on red packs", "AHJ-program subject-matter expert on Colorado and Fairfax County edition nuances" ], "needs_legal": [ "Retraction workflow language", "DSAR SLA + AHJ/regulator-response runbook", "Public release-readiness claim policy for the microsite" ], "needs_prototype": [ "Extraction Agent accuracy on a 20-case golden dataset", "Analyst release UX end-to-end in <= 5 minutes per pack", "Per-tenant retrieval isolation test on the AHJ Rule Library" ], "validate_before_prod": [ "Named compliance analyst of record + engagement letter on file", "Owner-action ledger populated per launch tenant", "OutputValidator false-negative rate acceptable", "Delivery failure alert path tested" ] }, "final_recommendations": [ "Ship a modular-monolith, evidence-linked, release-gated vertical slice for MCPVault Clear. Preserve the invariant that no Completeness Pack leaves the system without a signed human release -- compliance analyst on green/yellow, licensed elevator consultant/QEI on red. Do not launch commercially until owner-action facts close and at least one human-released Completeness Pack is delivered.", "Do NOT default to microservices. Extract a module only when a specific pressure demands it.", "Do NOT allow AI extraction outputs to leave AI Workbench & Extraction without an OutputValidator pass and citation coverage.", "Do NOT ship any release-readiness claim on the MCPVault Clear microsite while owner actions are open.", "Do NOT store roles on user/profile tables; use a dedicated roles table with server-side checks + RLS.", "DO wire the north-star (scan-to-paid) + guardrail metrics before Phase 2 launch.", "DO capture every state transition as an append-only domain event; the vault index is the product." ], "extensions": { "service_business_reality_check": { "is_service_business": true, "paid_outcome_clear": true, "workflow_present": true, "ai_native_fit_score": 8, "red_flags": [ "[PLACEHOLDER] owner to complete" ] }, "ai_native_fit": { "score": 8, "why": "Evidence-linked extraction + confidence-scored escalation is only economical with bounded AI orchestration. Pure-manual audit consulting is uneconomic at pack pricing; a pure-automated SaaS tracker is undefensible without a human release gate.", "disqualifiers": [ "Liability-adjacent vertical: cannot ship without a named compliance analyst / licensed consultant release" ] }, "domain_evidence_register": [ { "claim": "MCPVault Clear's paid outcome is an analyst- or consultant-released Completeness Pack", "evidence_type": "primary", "source": "Business Understanding + subdomain 'Completeness Pack Fulfillment'", "strength": "strong", "gaps": "Confirm with 3 design-partner interviews in Colorado Front Range" }, { "claim": "Analyst or consultant release is commercially required for inspection defensibility", "evidence_type": "primary", "source": "ASME A17.1 §8.6 / AHJ enforcement archetype (Colorado, Fairfax)", "strength": "strong", "gaps": "Vertical-specific attestation-standard citation" }, { "claim": "AI extraction materially reduces cycle time vs. pure-manual document review", "evidence_type": "assumed", "source": "Category benchmark (elevator-consultant audit norms)", "strength": "medium", "gaps": "Measure on internal golden dataset" }, { "claim": "Customer will supply structured intake (MCP, logs, callbacks, photos) within SLA", "evidence_type": "assumed", "source": "Prospect conversations (unverified)", "strength": "weak", "gaps": "Run 5 intake dry-runs with pilot buildings" }, { "claim": "Per-tenant AHJ retrieval isolation prevents cross-tenant leakage", "evidence_type": "primary", "source": "Architecture (AHJ Rule Library & Retrieval context)", "strength": "strong", "gaps": "Add automated cross-tenant lookup test" }, { "claim": "Owner-action ledger blocks a premature release-readiness claim", "evidence_type": "primary", "source": "Compliance & Licensing Governance context invariants", "strength": "strong", "gaps": "None" }, { "claim": "Model + prompt versioning enables reproducible gap-matrix outputs", "evidence_type": "primary", "source": "AI Workbench & Extraction context", "strength": "strong", "gaps": "Eval Agent regression thresholds not yet baselined" }, { "claim": "Cycle-time reduction supports the $1,450-$2,850 pack pricing tier", "evidence_type": "assumed", "source": "Pricing hypothesis anchored to consultant audit norms", "strength": "medium", "gaps": "Test with 3 pricing conversations" } ], "assumption_register": [ { "assumption": "The target audience will pay for a released, checklist-cited documentation-completeness pack over a free vendor-supplied PDF.", "impact_if_wrong": "high", "how_to_validate": "Pilot-building interview + measurement", "blocking": true }, { "assumption": "A Completeness Pack can be reconstructed from an owner-supplied evidence set within the standard 7-business-day cycle.", "impact_if_wrong": "high", "how_to_validate": "Pilot-building interview + measurement", "blocking": true }, { "assumption": "The vertical tolerates AI-assisted extraction and drafting when compliance-analyst review is explicit and audit-traceable.", "impact_if_wrong": "high", "how_to_validate": "Pilot-building interview + measurement", "blocking": false }, { "assumption": "Logical per-tenant isolation with row-level auth is acceptable for the first cohort -- single-tenant infrastructure is not required.", "impact_if_wrong": "medium", "how_to_validate": "Instrument metric + review after Phase 1", "blocking": false }, { "assumption": "Colorado Front Range and Fairfax County enforcement signals generalize to other high-enforcement AHJs as the rule library expands.", "impact_if_wrong": "medium", "how_to_validate": "Instrument metric + review after Phase 1", "blocking": false }, { "assumption": "A licensed elevator consultant / QEI can be sourced and retained for this vertical.", "impact_if_wrong": "severe", "how_to_validate": "Recruit + sign engagement letter before commercial launch", "blocking": true }, { "assumption": "External systems (vendor invoice inboxes, CMMS platforms) expose stable APIs with predictable failure modes.", "impact_if_wrong": "medium", "how_to_validate": "Adapter contract tests + failure-injection", "blocking": false } ], "language_conflict_map": [ { "term": "Engagement", "meaning_a": "A signed billing contract", "context_a": "Billing & Revenue", "meaning_b": "An accepted unit of intake work", "context_b": "Sales & Intake", "resolution": "Billing owns 'Subscription'; Sales & Intake owns 'Engagement' as the accepted-intake noun." }, { "term": "Release", "meaning_a": "Analyst or consultant signs a Completeness Pack", "context_a": "Release & Quality Assurance", "meaning_b": "Business owner decides a public claim is release-ready", "context_b": "Compliance & Licensing Governance", "resolution": "QA uses 'analyst release' / 'consultant release'; Compliance uses 'release-readiness decision' -- never conflate the two." }, { "term": "Confidence", "meaning_a": "Model-assigned probability", "context_a": "AI Workbench & Extraction", "meaning_b": "Human analyst confidence in a gap-matrix line", "context_b": "Release & Quality Assurance", "resolution": "Never conflate; always qualify (model_confidence vs analyst_confidence)." } ], "build_buy_integrate": [ { "subdomain": "Completeness Pack Fulfillment (evidence-linked extraction + release)", "decision": "build", "reason": "This is what customers pay for and what an AHJ inspection tests against." }, { "subdomain": "AI Workbench & Extraction (bounded agents + retrieval)", "decision": "build", "reason": "The AI-native competitive edge lives here; misuse here creates every high-severity risk." }, { "subdomain": "Release & Quality Assurance (analyst/consultant release + retraction)", "decision": "build", "reason": "Release is the trust primitive of the whole business." }, { "subdomain": "AHJ Rule Library & Retrieval", "decision": "build", "reason": "Poor or stale AHJ retrieval directly causes false hard-fails." }, { "subdomain": "Compliance & Licensing Governance", "decision": "build", "reason": "Cross-cuts every context; owns the licensing-boundary and release-claim decision." }, { "subdomain": "Sales & Intake", "decision": "build", "reason": "Feeds Fulfillment; not the differentiator, but if broken, nothing else runs." }, { "subdomain": "Client Onboarding & Tenant Profile", "decision": "build", "reason": "One-time high-touch step per customer." }, { "subdomain": "Client Delivery & Success", "decision": "build", "reason": "Customer-visible surface; drives retention." }, { "subdomain": "Vendor Chase Desk", "decision": "build", "reason": "Monetizes the highest-friction part of the workflow without becoming unpaid consulting." }, { "subdomain": "Portfolio & Recurring Programs", "decision": "build", "reason": "Converts one-time packs into recurring revenue for multi-building owners." }, { "subdomain": "Billing & Revenue", "decision": "buy", "reason": "Solved category; do not build." }, { "subdomain": "Identity & Access", "decision": "integrate", "reason": "Solved category." }, { "subdomain": "Analytics & Reporting", "decision": "build", "reason": "Drives every operational decision against the brief's KPI targets." }, { "subdomain": "External Integrations (Anti-Corruption Layer)", "decision": "build", "reason": "External schemas must never leak into the core." } ], "core_protection_strategy": [ "Core contexts (Completeness Pack Fulfillment, AI Workbench & Extraction, Release & Quality Assurance) staffed before any generic subdomain work.", "Any change to a core aggregate requires a paired ADR + invariant test.", "Generic subdomains (Billing, Identity) are bought or integrated; never built in-house without a killer reason.", "Prompt-version rollout to core agents gated on an Eval Agent regression run.", "No feature flag may bypass the analyst/consultant release invariant." ], "boundary_stress_tests": [ { "scenario": "Customer requests changes to a delivered Completeness Pack", "contexts_touched": [ "Client Delivery & Success", "Completeness Pack Fulfillment", "Release & Quality Assurance" ], "breaks_if": "A revision creates a new gap matrix without re-triggering release", "verdict": "holds" }, { "scenario": "Compliance analyst of record changes mid-engagement", "contexts_touched": [ "Client Onboarding & Tenant Profile", "Release & Quality Assurance" ], "breaks_if": "QA cached the analyst identity locally", "verdict": "adjust" }, { "scenario": "Colorado OPS or Fairfax County finalizes a rule change touching §8.6 scope", "contexts_touched": [ "Compliance & Licensing Governance", "AHJ Rule Library & Retrieval" ], "breaks_if": "The retrieval index is not reindexed within SLA", "verdict": "holds" }, { "scenario": "Owner/operator marks an owner action resolved that is actually not", "contexts_touched": [ "Compliance & Licensing Governance" ], "breaks_if": "No re-verification step before the release decision flips", "verdict": "adjust" }, { "scenario": "AI produces a high-confidence gap-matrix line with a wrong citation", "contexts_touched": [ "AI Workbench & Extraction", "Release & Quality Assurance" ], "breaks_if": "OutputValidator does not check citation-to-claim linkage", "verdict": "holds" } ], "unresolved_ownership": [ { "concept": "Compliance analyst engagement letter", "candidates": [ "Client Onboarding & Tenant Profile", "Release & Quality Assurance" ], "recommendation": "Own in Client Onboarding & Tenant Profile; QA references by id." }, { "concept": "Public release-readiness claim / marketing site content", "candidates": [ "Compliance & Licensing Governance", "Client Delivery & Success" ], "recommendation": "Compliance owns the release-decision; Delivery renders it." }, { "concept": "Model + prompt cost attribution", "candidates": [ "AI Workbench & Extraction", "Billing & Revenue" ], "recommendation": "AI Workbench & Extraction owns the raw run cost; Billing consumes rolled-up projections." } ], "published_language_contracts": [ { "producer": "Sales & Intake", "consumer": "Completeness Pack Fulfillment", "contract": "EngagementAccepted", "versioning": "SemVer on event schema; consumer contract tests in CI." }, { "producer": "Completeness Pack Fulfillment", "consumer": "Release & Quality Assurance", "contract": "GapMatrixDrafted, HardGatesEvaluated", "versioning": "SemVer on event schema; consumer contract tests in CI." }, { "producer": "AI Workbench & Extraction", "consumer": "Completeness Pack Fulfillment", "contract": "GapMatrixDrafted, EscalationRaised", "versioning": "SemVer on event schema; consumer contract tests in CI." }, { "producer": "AHJ Rule Library & Retrieval", "consumer": "AI Workbench & Extraction", "contract": "RuleUpdateIngested, IndexRebuilt", "versioning": "SemVer on event schema; consumer contract tests in CI." }, { "producer": "Client Onboarding & Tenant Profile", "consumer": "Completeness Pack Fulfillment", "contract": "TenantProvisioned, AnalystOfRecordRegistered", "versioning": "SemVer on event schema; consumer contract tests in CI." }, { "producer": "Completeness Pack Fulfillment", "consumer": "Client Delivery & Success", "contract": "PackDelivered, DeliveryConfirmed", "versioning": "SemVer on event schema; consumer contract tests in CI." }, { "producer": "Release & Quality Assurance", "consumer": "Compliance & Licensing Governance", "contract": "PackRetracted", "versioning": "SemVer on event schema; consumer contract tests in CI." }, { "producer": "Vendor Chase Desk", "consumer": "Completeness Pack Fulfillment", "contract": "HardGapCured", "versioning": "SemVer on event schema; consumer contract tests in CI." } ], "shared_kernel_warnings": [ "Shared kernel must remain small: Ids, Money, Tenant, Actor. Adding a domain concept here couples every context.", "Never share aggregates across contexts via the shared kernel -- publish an event or expose an application service.", "Any addition to /shared requires 2-context approval to prevent silent coupling." ], "aggregate_stress_tests": [ { "aggregate": "ConveyanceIntakeAggregate", "scenario": "Concurrent command on ConveyanceIntakeAggregate", "invariant_at_risk": "An intake in state 'delivered' is immutable", "verdict": "holds" }, { "aggregate": "GapMatrixAggregate", "scenario": "Concurrent command on GapMatrixAggregate", "invariant_at_risk": "Every gap-matrix line cites evidence or is marked an explicit gap", "verdict": "holds" }, { "aggregate": "CompletenessPackAggregate", "scenario": "Concurrent command on CompletenessPackAggregate", "invariant_at_risk": "A Completeness Pack cannot be delivered without a valid Release", "verdict": "holds" }, { "aggregate": "ReleaseAggregate", "scenario": "Concurrent command on ReleaseAggregate", "invariant_at_risk": "A Release is bound to a live authenticated session, not a form field", "verdict": "holds" }, { "aggregate": "VendorChaseCaseAggregate", "scenario": "Concurrent command on VendorChaseCaseAggregate", "invariant_at_risk": "A hard gap cannot be marked cured without vendor-sourced cure evidence", "verdict": "holds" } ], "agent_stress_tests": [ { "agent": "Extraction Agent", "scenario": "Malformed / adversarial input to the Extraction Agent", "failure_mode": "Prompt injection via vendor invoice content", "guardrail": "Structured-output schema", "verdict": "holds" }, { "agent": "Routing & Classification Agent", "scenario": "Malformed / adversarial input to the Routing & Classification Agent", "failure_mode": "Wrong route -> wrong reviewer or wrong AHJ edition", "guardrail": "Structured-output schema", "verdict": "holds" }, { "agent": "Eval Agent", "scenario": "Malformed / adversarial input to the Eval Agent", "failure_mode": "Overfit to the golden dataset", "guardrail": "Regression thresholds", "verdict": "holds" } ], "regulated_domain_handling": [ { "regime": "ASME A17.1 §8.6 (MCP requirement) and §8.6.1.4 (5-year record retention) as adopted by the AHJ; Colorado 7 CCR 1101-8; Fairfax County / Virginia elevator program policy", "applies_because": "The AHJ treats a missing/incomplete MCP or under-5-year records as an inspection-failure condition; owner remains the legally accountable party even though a vendor typically writes/executes the MCP.", "controls": [ "Edition-dated checklist card cited per hard-gap claim", "Compliance analyst release on green/yellow; licensed elevator consultant/QEI release on red packs" ], "evidence_required": [ "Checklist-clause-to-evidence map", "Release records + vault index rows" ] } ], "unit_economics": { "price_model": "Per-building Completeness Pack tiers (base 1-4 conveyances + per-conveyance overage) + Rush add-on + Chase Desk per-cycle add-on + Portfolio Desk monthly retainer", "unit_of_value": "Released elevator-mcp-completeness-pack-engine Completeness Pack", "gross_margin_pct": 61, "cost_drivers": [ "Analyst minutes per pack", "AI model + retrieval cost", "Consultant reserve (escalations)", "Support + success" ], "breakeven_note": "Breakeven depends on analyst throughput and extraction acceptance rate; target analyst minutes per green pack <=40 by day 90 and >=55% automation share by month 6, per the brief's unit-economics table." }, "margin_leakage_map": [ { "leakage": "Analyst over-editing AI-drafted gap matrices", "cause": "Low AI acceptance rate on non-standard vendor formats", "impact": "high", "mitigation": "Eval Agent regression + prompt-owner accountability" }, { "leakage": "External API retries without backoff", "cause": "Poor adapter design", "impact": "medium", "mitigation": "Exponential backoff + circuit breaker" }, { "leakage": "Cross-tenant retrieval scan cost", "cause": "Missing AHJ-index partitioning", "impact": "high", "mitigation": "Per-tenant index partitions" }, { "leakage": "Vendor Chase Desk cases running past the paid cycle", "cause": "No cadence cap on chase attempts", "impact": "medium", "mitigation": "Chase-cadence spec + weekly cap" } ], "slop_findings": [ { "pattern": "generic 'dashboard'-only value prop", "status": "clean", "note": "Value prop is a released, cited Completeness Pack, not a dashboard." }, { "pattern": "AI-as-magic", "status": "clean", "note": "AI is bounded to extraction + drafting + validation; humans own release." }, { "pattern": "blockchain", "status": "clean", "note": "No blockchain-as-hype in derivation." }, { "pattern": "agent-first (agents replace humans)", "status": "clean", "note": "Every agent has forbidden actions + human escalation." }, { "pattern": "microservices by default", "status": "clean", "note": "ADR-001 chose a modular monolith." }, { "pattern": "everything-is-core", "status": "clean", "note": "Generic subdomains explicitly marked buy/integrate." } ], "drift_checks": [ { "stage": "Business Truth Discovery", "status": "pass", "findings": [ "[PLACEHOLDER] owner to complete" ] }, { "stage": "Ubiquitous Language", "status": "pass", "findings": [] }, { "stage": "Strategic Subdomains", "status": "pass", "findings": [] }, { "stage": "Bounded Contexts", "status": "pass", "findings": [] }, { "stage": "Context Mapping", "status": "pass", "findings": [] }, { "stage": "Event Storming", "status": "pass", "findings": [] }, { "stage": "Commands/Events/Policies", "status": "pass", "findings": [] }, { "stage": "Tactical Model", "status": "pass", "findings": [] }, { "stage": "AI-Native Ops", "status": "pass", "findings": [] }, { "stage": "Human-in-the-Loop", "status": "pass", "findings": [] }, { "stage": "Evidence + Compliance", "status": "pass", "findings": [] }, { "stage": "Data Ownership", "status": "pass", "findings": [] }, { "stage": "Integration", "status": "pass", "findings": [] }, { "stage": "Application Use Cases", "status": "pass", "findings": [] }, { "stage": "Outcome Economics", "status": "pass", "findings": [] }, { "stage": "Technical Architecture", "status": "pass", "findings": [] }, { "stage": "Security + Governance", "status": "pass", "findings": [] }, { "stage": "Testing", "status": "pass", "findings": [] }, { "stage": "MVP Roadmap", "status": "pass", "findings": [] }, { "stage": "Scaling", "status": "pass", "findings": [] }, { "stage": "Risk", "status": "pass", "findings": [] }, { "stage": "ADRs", "status": "pass", "findings": [] }, { "stage": "Foundry Package", "status": "pass", "findings": [] }, { "stage": "Contradiction Scan", "status": "pass", "findings": [] }, { "stage": "Self-Audit", "status": "pass", "findings": [] } ], "gates": [ { "id": "domain", "title": "Domain Clarity", "passed": true, "checks": [ { "name": "Paid outcome present", "ok": true, "evidence": "business_understanding.paid_outcome" }, { "name": ">=3 actors identified", "ok": true, "evidence": "6 actors" } ] }, { "id": "core", "title": "Core Domain", "passed": true, "checks": [ { "name": "At least one core subdomain", "ok": true, "evidence": "Completeness Pack Fulfillment, AI Workbench & Extraction, Release & Quality Assurance" } ] }, { "id": "boundary", "title": "Boundary", "passed": true, "checks": [ { "name": ">=4 bounded contexts", "ok": true, "evidence": "13 contexts" }, { "name": "Every context has owned language", "ok": true, "evidence": "all populated" } ] }, { "id": "invariant", "title": "Invariant", "passed": true, "checks": [ { "name": ">=4 business invariants", "ok": true, "evidence": "9 invariants" } ] }, { "id": "ai-safety", "title": "AI Safety", "passed": true, "checks": [ { "name": "Every agent has forbidden actions", "ok": true, "evidence": "yes" }, { "name": "Every agent has escalation triggers", "ok": true, "evidence": "yes" } ] }, { "id": "buildability", "title": "Buildability", "passed": true, "checks": [ { "name": "MVP roadmap >=2 phases", "ok": true, "evidence": "6 phases" } ] }, { "id": "anti-slop", "title": "Anti-Slop", "passed": true, "checks": [ { "name": "No slop patterns", "ok": true, "evidence": "slop_findings all clean" }, { "name": "No failing contradictions", "ok": true, "evidence": "10 findings, none severity=error" } ] } ], "contradiction_scan": [ { "id": "INV-AGG-ReleaseAggregate+PackRetractionAggregate", "severity": "warn", "message": "Invariant references aggregate 'ReleaseAggregate + PackRetractionAggregate' not defined as a single aggregate", "refs": [ "ReleaseAggregate + PackRetractionAggregate" ] }, { "id": "CMD-EVT-OpenConveyanceIntake-IntakeRejected", "severity": "info", "message": "Command OpenConveyanceIntake references event 'IntakeRejected' not present in domain_events", "refs": [ "OpenConveyanceIntake", "IntakeRejected" ] }, { "id": "CMD-EVT-IngestEvidence-EvidenceRejected", "severity": "info", "message": "Command IngestEvidence references event 'EvidenceRejected' not present in domain_events", "refs": [ "IngestEvidence", "EvidenceRejected" ] }, { "id": "CMD-EVT-EvaluateHardGates-HardGateEvaluationError", "severity": "info", "message": "Command EvaluateHardGates references event 'HardGateEvaluationError' not present in domain_events", "refs": [ "EvaluateHardGates", "HardGateEvaluationError" ] }, { "id": "CMD-EVT-ReleasePack-PackReleaseRejected", "severity": "info", "message": "Command ReleasePack references event 'PackReleaseRejected' not present in domain_events", "refs": [ "ReleasePack", "PackReleaseRejected" ] }, { "id": "CMD-EVT-DeliverCompletenessPack-DeliveryFailed", "severity": "info", "message": "Command DeliverCompletenessPack references event 'DeliveryFailed' not present in domain_events", "refs": [ "DeliverCompletenessPack", "DeliveryFailed" ] }, { "id": "CMD-EVT-ResolveOwnerAction-OwnerActionRejected", "severity": "info", "message": "Command ResolveOwnerAction references event 'OwnerActionRejected' not present in domain_events", "refs": [ "ResolveOwnerAction", "OwnerActionRejected" ] }, { "id": "CMD-EVT-DispatchChaseLetter-ChaseLetterFailed", "severity": "info", "message": "Command DispatchChaseLetter references event 'ChaseLetterFailed' not present in domain_events", "refs": [ "DispatchChaseLetter", "ChaseLetterFailed" ] }, { "id": "CMD-EVT-ConfirmVendorCure-VendorCureRejected", "severity": "info", "message": "Command ConfirmVendorCure references event 'VendorCureRejected' not present in domain_events", "refs": [ "ConfirmVendorCure", "VendorCureRejected" ] }, { "id": "CMD-EVT-RetractPack-RetractionRejected", "severity": "info", "message": "Command RetractPack references event 'RetractionRejected' not present in domain_events", "refs": [ "RetractPack", "RetractionRejected" ] } ], "rubric": { "categories": [ { "category": "Domain accuracy", "score": 8, "min": 7, "passed": true }, { "category": "Ubiquitous language quality", "score": 8, "min": 7, "passed": true }, { "category": "Subdomain classification quality", "score": 8, "min": 7, "passed": true }, { "category": "Bounded context clarity", "score": 9, "min": 7, "passed": true }, { "category": "Core domain focus", "score": 9, "min": 7, "passed": true }, { "category": "Context map quality", "score": 8, "min": 7, "passed": true }, { "category": "Aggregate design quality", "score": 8, "min": 7, "passed": true }, { "category": "Invariant quality", "score": 9, "min": 7, "passed": true }, { "category": "AI-agent responsibility design", "score": 9, "min": 7, "passed": true }, { "category": "Human review safety", "score": 9, "min": 7, "passed": true }, { "category": "Data ownership clarity", "score": 8, "min": 7, "passed": true }, { "category": "Integration protection", "score": 8, "min": 7, "passed": true }, { "category": "Implementation feasibility", "score": 8, "min": 7, "passed": true }, { "category": "Scalability", "score": 7, "min": 7, "passed": true }, { "category": "Security and compliance", "score": 7, "min": 7, "passed": true }, { "category": "Testing strategy", "score": 8, "min": 7, "passed": true }, { "category": "Operational realism", "score": 7, "min": 7, "passed": true }, { "category": "MVP practicality", "score": 9, "min": 7, "passed": true } ], "pass": true, "average": 8.17 }, "foundry_package": { "version": "1.0.0", "checksum": "mcpv0001", "counts": { "subdomains": 14, "bounded_contexts": 13, "aggregates": 13, "events": 10, "commands": 10, "policies": 6, "ai_agents": 3, "invariants": 10, "integrations": 4, "adrs": 8 }, "subset": { "subdomains": [ "Completeness Pack Fulfillment (evidence-linked extraction + release)", "AI Workbench & Extraction (bounded agents + retrieval)", "Release & Quality Assurance (analyst/consultant release + retraction)", "AHJ Rule Library & Retrieval", "Compliance & Licensing Governance", "Sales & Intake", "Client Onboarding & Tenant Profile", "Client Delivery & Success", "Vendor Chase Desk", "Portfolio & Recurring Programs", "Billing & Revenue", "Identity & Access", "Analytics & Reporting", "External Integrations (Anti-Corruption Layer)" ], "bounded_contexts": [ "Completeness Pack Fulfillment", "AI Workbench & Extraction", "Release & Quality Assurance", "AHJ Rule Library & Retrieval", "Compliance & Licensing Governance", "Sales & Intake", "Client Onboarding & Tenant Profile", "Client Delivery & Success", "Vendor Chase Desk", "Portfolio & Recurring Programs", "Billing & Revenue", "Identity & Access", "Analytics & Reporting" ], "aggregates": [ "EngagementAggregate", "TenantAggregate", "ConveyanceIntakeAggregate", "GapMatrixAggregate", "CompletenessPackAggregate", "ExtractionRunAggregate", "AHJRuleSetAggregate", "ReleaseAggregate", "PackRetractionAggregate", "OwnerActionLedgerAggregate", "VendorChaseCaseAggregate", "PortfolioAggregate", "DeliveryAggregate" ], "events": [ "conveyanceIntakeAccepted", "evidenceIngested", "gapMatrixDrafted", "hardGatesEvaluated", "escalationRaised", "packReleased", "packDelivered", "ownerActionResolved", "hardGapCured", "packRetracted" ], "commands": [ "OpenConveyanceIntake", "IngestEvidence", "StartExtractionRun", "EvaluateHardGates", "ReleasePack", "DeliverCompletenessPack", "ResolveOwnerAction", "DispatchChaseLetter", "ConfirmVendorCure", "RetractPack" ], "policies": [ "Auto-request release on hard-gate evaluation complete", "Escalate on low confidence or missing MCP", "Block delivery on open compliance blocker", "Retract on material finding", "Alert on delivery failure", "Open vendor chase case on vendor-attributable hard gap" ], "ai_agents": [ "Extraction Agent", "Routing & Classification Agent", "Eval Agent" ], "invariants": [ "A Completeness Pack cannot be delivered without a valid analyst or consultant Release.", "Every gap-matrix line cites at least one evidence item or is marked an explicit gap.", "A Release is bound to a live authenticated session, not a form field.", "Released Completeness Packs are immutable; corrections go through PackRetraction.", "No extraction output leaves AI Workbench & Extraction without an OutputValidator pass.", "AHJ retrieval is scoped to the checklist edition adopted by the conveyance's jurisdiction.", "Release cannot flip to 'ready' with open blocking owner actions.", "Every tenant has at least one named compliance analyst of record on file before intake opens.", "A hard gap cannot be marked cured without vendor-sourced cure evidence citing the original clause.", "Roles are stored in a dedicated table and checked server-side." ], "integrations": [ "Vendor invoice inboxes", "Elevator-vendor work-order / CMMS platforms", "Customer document portals", "OpenAI / Anthropic API" ], "adrs": [ "ADR-001", "ADR-002", "ADR-003", "ADR-004", "ADR-005", "ADR-006", "ADR-007", "ADR-008" ] } } } }, "ddd_coverage": { "slug": "elevator-mcp-completeness-pack-engine", "total": 20, "passed": 20, "pct": 100, "checks": [ { "key": "actors", "label": "Actors", "count": 6, "min": 3, "ok": true, "gate": "domain", "unblock": "Not needed -- check passes at current counts." }, { "key": "glossary", "label": "Glossary", "count": 15, "min": 6, "ok": true, "gate": "domain", "unblock": "Not needed -- check passes at current counts." }, { "key": "decisions", "label": "Business decisions", "count": 5, "min": 4, "ok": true, "gate": "domain", "unblock": "Not needed -- check passes at current counts." }, { "key": "events", "label": "Domain events", "count": 10, "min": 6, "ok": true, "gate": "domain", "unblock": "Not needed -- check passes at current counts." }, { "key": "subdomains", "label": "Subdomains", "count": 14, "min": 8, "ok": true, "gate": "core", "unblock": "Not needed -- check passes at current counts." }, { "key": "bcs", "label": "Bounded contexts", "count": 13, "min": 4, "ok": true, "gate": "boundary", "unblock": "Not needed -- check passes at current counts." }, { "key": "ctx_map", "label": "Context map", "count": 14, "min": 3, "ok": true, "gate": "boundary", "unblock": "Not needed -- check passes at current counts." }, { "key": "event_storm", "label": "Event storm rows", "count": 15, "min": 6, "ok": true, "gate": "boundary", "unblock": "Not needed -- check passes at current counts." }, { "key": "aggregates", "label": "Aggregates", "count": 13, "min": 3, "ok": true, "gate": "invariant", "unblock": "Not needed -- check passes at current counts." }, { "key": "invariants", "label": "Invariants", "count": 10, "min": 4, "ok": true, "gate": "invariant", "unblock": "Not needed -- check passes at current counts." }, { "key": "ai_agents", "label": "AI agents", "count": 3, "min": 2, "ok": true, "gate": "ai-safety", "unblock": "Not needed -- check passes at current counts." }, { "key": "use_cases", "label": "Use cases", "count": 4, "min": 3, "ok": true, "gate": "buildability", "unblock": "Not needed -- check passes at current counts." }, { "key": "evidence_reg", "label": "Evidence register", "count": 8, "min": 5, "ok": true, "gate": "domain", "unblock": "Not needed -- check passes at current counts." }, { "key": "assumptions", "label": "Assumption register", "count": 7, "min": 4, "ok": true, "gate": "domain", "unblock": "Not needed -- check passes at current counts." }, { "key": "stress_boundary", "label": "Boundary stress tests", "count": 5, "min": 3, "ok": true, "gate": "boundary", "unblock": "Not needed -- check passes at current counts." }, { "key": "stress_agg", "label": "Aggregate stress tests", "count": 5, "min": 3, "ok": true, "gate": "invariant", "unblock": "Not needed -- check passes at current counts." }, { "key": "stress_agent", "label": "Agent stress tests", "count": 3, "min": 2, "ok": true, "gate": "ai-safety", "unblock": "Not needed -- check passes at current counts." }, { "key": "gates_pass", "label": "Hard gates passing", "count": 7, "min": 7, "ok": true, "gate": null, "unblock": "Not needed -- check passes at current counts." }, { "key": "rubric", "label": "Extended rubric pass", "count": 1, "min": 1, "ok": true, "gate": "buildability", "unblock": "Not needed -- check passes at current counts." }, { "key": "foundry", "label": "Foundry package", "count": 13, "min": 4, "ok": true, "gate": "buildability", "unblock": "Not needed -- check passes at current counts." } ], "failingGates": [ "[PLACEHOLDER] owner to complete" ] }, "architecture": { "slug": "elevator-mcp-completeness-pack-engine", "archetypes": [ "regulated system", "CRUD/workflow application", "internal operations platform" ], "archetype_impact": "AHJ jurisdiction is a global query parameter — every read/write is scoped by building, AHJ edition, and conveyance, not just tenant.", "personality": [ "workflow-heavy", "cost-sensitive", "highly regulated", "highly secure" ], "forces_ranked": [ { "force": "compliance", "why": "Regulated verticals gate release; the architecture must prove, not assert, compliance." }, { "force": "auditability", "why": "Every release decision, every evidence toggle, must be defensible in review." }, { "force": "reliability", "why": "A broken blueprint is a broken release gate — availability is a product feature." }, { "force": "data integrity", "why": "Evidence is the product; a corrupted citation is a shipped defect." }, { "force": "maintainability", "why": "One team maintains dozens of blueprints; the shape must be identical across them." } ], "tradeoffs": [ "Prioritizing auditability slows raw throughput — accepted; the product IS the audit trail.", "Choosing a modular monolith trades independent scaling for a single deploy story — accepted while the team is small.", "Using managed Cloud primitives trades some portability for zero ops — accepted; data is portable, runtime is not the moat." ], "quality_scenarios": [ { "attribute": "Performance (interactive p95)", "target": "600 ms on Blueprint detail routes", "assumption": "Measured from Cloud edge, warm cache." }, { "attribute": "Availability", "target": "99.5% (with March-reporting-window freeze protection)", "assumption": "Rolling 30-day window; excludes announced maintenance." }, { "attribute": "RTO", "target": "24h" }, { "attribute": "RPO", "target": "24h (daily backups)" }, { "attribute": "Latency (edge function warm)", "target": "≤ 800ms p95 excluding upstream AI calls" }, { "attribute": "Data durability", "target": "11 nines via managed Postgres + storage replication" }, { "attribute": "Security", "target": "OWASP ASVS L1 baseline" }, { "attribute": "Auditability", "target": "100% of release decisions + evidence toggles logged with actor + timestamp" }, { "attribute": "Maintainability", "target": "New blueprint reaches validation-microsite state in ≤ 1 working session" }, { "attribute": "Deployment frequency", "target": "≥ 5 deploys/week without incident" }, { "attribute": "Observability", "target": "Every edge function emits correlationId; retries + phases visible in diagnostics drawer" }, { "attribute": "Cost envelope", "target": "Idle per-blueprint cost ≈ $0; active < $5/month at MVP traffic" }, { "attribute": "Scalability", "target": "Horizontal by blueprint count; single blueprint sized for < 10 req/s sustained" } ], "options": [ { "style": "simple monolith", "fits_when": "Single team, low traffic, no independent scaling concerns.", "fits_here": "Matches the per-blueprint scope — one microsite, one schema, one code path.", "wrong_here": "Would couple every blueprint into a single deploy — not acceptable at network scale.", "complexity": "low", "cost": "low", "ops_burden": "low", "security_impact": "Small surface, single audit boundary.", "scaling_path": "Vertical scale only; hits ceiling on team velocity, not compute.", "team_fit": "Ideal for one dev; fine at MVP.", "recommended": false }, { "style": "modular monolith", "fits_when": "Multiple bounded contexts but shared deploy lifecycle acceptable.", "fits_here": "Each blueprint is a module inside the network shell; shared shell, isolated data.", "wrong_here": "Wrong only if a blueprint needs independent SLOs — none currently do.", "complexity": "moderate", "cost": "low", "ops_burden": "low", "security_impact": "Single trust boundary; row-level isolation carries the tenancy load.", "scaling_path": "Modules become services only when SLOs or teams diverge.", "team_fit": "Best fit for a small team maintaining many blueprints.", "recommended": true }, { "style": "serverless", "fits_when": "Bursty, per-request workloads with idle-to-zero cost targets.", "fits_here": "Edge functions already handle sync, docs, legal, seed articles, integrity — pay-per-invoke.", "wrong_here": "Wrong for long-running orchestrations; IDLE_TIMEOUT already bit us on legal docs.", "complexity": "moderate", "cost": "low", "ops_burden": "moderate", "security_impact": "Function-scoped IAM; secrets via managed vault.", "scaling_path": "Auto; watch cold-start p95 and per-invocation cost.", "team_fit": "Good — team already ships functions weekly.", "recommended": false }, { "style": "microservices", "fits_when": "Multiple teams, divergent SLOs, independent release cadence required.", "fits_here": "Nothing here justifies it; single team, single deploy cadence, shared data plane.", "wrong_here": "Adds network, discovery, deploy topology, and observability cost with zero product benefit.", "complexity": "very high", "cost": "high", "ops_burden": "high", "security_impact": "Bigger attack surface, more inter-service auth to get right.", "scaling_path": "Best-in-class if the org can afford it.", "team_fit": "Wrong for this team.", "recommended": false }, { "style": "event-driven", "fits_when": "Async fan-out, decoupled producers/consumers, replayable history required.", "fits_here": "Only the sync + integrity pipeline is fan-out; keep it as background jobs, not a broker.", "wrong_here": "Broker + schema registry + DLQ topology is overkill for current volumes.", "complexity": "high", "cost": "moderate", "ops_burden": "high", "security_impact": "Extra ACLs; message-level auth needed.", "scaling_path": "Excellent for future audit-log fan-out, revisit at 10x volume.", "team_fit": "Team can operate a small in-process queue; not a full broker yet.", "recommended": false }, { "style": "workflow/orchestration", "fits_when": "Long, multi-step, resumable pipelines with human-in-the-loop steps.", "fits_here": "Blueprint pipeline (sources → articles → integrity → smoke test) already smells like this.", "wrong_here": "Full engine (Temporal/Airflow) is heavy; a typed in-app queue with retries covers today's needs.", "complexity": "high", "cost": "moderate", "ops_burden": "moderate", "security_impact": "Central choke point — must be hardened.", "scaling_path": "Adopt engine once we cross ~10 concurrent long-running jobs per blueprint.", "team_fit": "Would require operator ramp-up.", "recommended": false } ], "chosen_style": "modular monolith", "chosen_rationale": "Modular monolith with edge functions for bursty AI/generation — one audit boundary, low ops burden, easy per-team ownership.", "rejected": [ { "style": "microservices", "why_rejected": "Adds network, discovery, deploy topology, and observability cost with zero product benefit." }, { "style": "event-driven", "why_rejected": "Broker + schema registry + DLQ topology is overkill for current volumes." } ], "target": { "overview": "React shell → Lovable Cloud (Postgres + Auth + Storage + Edge Functions). Every blueprint is a module inside the shell; per-vertical differences live in derived DNA, not in separate deploys. Compliance posture: Domain-specific (owner-side MCP and conveyance maintenance records, analyst/consultant release signers, 5-year retention schedules).", "frontend": "Vite + React + TypeScript + Tailwind + shadcn primitives; per-blueprint themed via Design DNA; job queue for background pipelines; URL-persisted filter state on audit + diagnostics.", "backend": "Deno-based edge functions per capability. Long generations split into per-item endpoints to stay under IDLE_TIMEOUT.", "data": "Managed Postgres with RLS + JSONB for shape drift. Object storage for source files + generated artifacts.", "api": "REST-ish RPC over edge functions with typed payloads; correlationId on every call for retry/diagnostics.", "authn_authz": "Managed OAuth (Google default). Roles in a dedicated user_roles table + has_role() SECURITY DEFINER function referenced by RLS policies.", "integrations": "GitHub (public read for sync + sources), Lovable AI Gateway (all LLM calls), Cloud Storage (artifacts). No third-party CRM/email yet.", "background_jobs": "blueprintJobQueue in-app: per-slug concurrency limit, exponential backoff + jitter, cancel + invalidate, retention of last error diagnostics.", "object_storage": "Cloud Storage buckets scoped per blueprint slug; signed URLs for artifact download.", "notifications": "In-app toasts + audit trail entries. Email/webhook deferred until owners request it.", "search": "Postgres FTS on blueprint titles + evidence claims; client-side filter for audit trail. Dedicated index deferred.", "analytics": "Lightweight event log in Postgres; dashboard-grade analytics deferred until we have a paying tenant.", "ai": "not applicable", "observability": "correlationId per request, per-phase timings, retry timeline in diagnostics drawer, per-blueprint pipeline status panel, JSON report export.", "deployment": "Preview + Production environments; edge functions deploy with the app; Postgres migrations shipped via managed migration tool.", "security": "RLS on every public table; roles in user_roles; secrets in managed vault; OWASP ASVS L1 baseline.", "dr": "Daily backups; restore drill twice/year." }, "modules": [ { "name": "Blueprint Core", "responsibility": "Owns the SeedBusiness catalog, release decisions, evidence register, owner actions.", "owned_data": [ "seed business rows", "release_decision", "evidence items", "owner-action state" ], "entities": [ "SeedBusiness", "EvidenceItem", "OwnerAction", "ReleaseDecision" ], "interfaces": [ "React store (StoreProvider)", "public read via microsite route" ], "depends_on": [ "Content Pipeline (for source files + articles)", "Cloud auth" ], "events_produced": [ "release.decision.changed", "evidence.status.changed", "owner.action.resolved" ], "events_consumed": [ "sync.blueprint.applied", "integrity.check.completed" ], "failure_risks": [ "Duplicate slug in seed → React key crash (mitigated by dedupe in mergedSeed)", "Evidence drift after sync" ], "scaling": "Bounded by SEED size; irrelevant even at 10x.", "future_split_trigger": "Split out Blueprint Core into an independent deployment when its throughput or a distinct scaling profile justifies it; not warranted pre-revenue." }, { "name": "Content Pipeline", "responsibility": "Fetches GitHub sources, generates docs/seed articles, runs citation integrity, per slug with concurrency + backoff.", "owned_data": [ "blueprint_sources", "blueprint_seed_articles", "job status per slug", "integrity results" ], "entities": [ "SourceFile", "SeedArticle", "IntegrityReport", "JobState" ], "interfaces": [ "blueprintJobQueue API", "edge functions: fetch-blueprint-sources, generate-seed-articles, generate-blueprint-docs" ], "depends_on": [ "Cloud edge functions", "AI Gateway", "GitHub public read" ], "events_produced": [ "sources.fetched", "articles.generated", "integrity.completed", "cache.invalidated" ], "events_consumed": [ "blueprint.cache.invalidate" ], "failure_risks": [ "Edge IDLE_TIMEOUT on long generations (mitigated: per-doc endpoints + retries)", "Upstream AI 5xx storms" ], "scaling": "Concurrency + backoff configurable in UI; scales with edge function limits.", "future_split_trigger": "If cross-blueprint queueing coordination is needed, promote to a shared job service." }, { "name": "Runtime & Capabilities", "responsibility": "Per-blueprint runtime modules — verification, SEO, legal docs, chatbot — with retry + diagnostic history.", "owned_data": [ "capability status per slug", "runtime module errors", "chatbot threads + FAQ" ], "entities": [ "CapabilityStatus", "RuntimeError", "ChatMessage" ], "interfaces": [ "React Runtime tab", "edge functions: verify-blueprint, generate-seo-posts, generate-legal-docs/*, blueprint-chat" ], "depends_on": [ "Content Pipeline (grounding)", "AI Gateway" ], "events_produced": [ "capability.status.changed", "runtime.error.recorded" ], "events_consumed": [ "cache.invalidated" ], "failure_risks": [ "AI provider outage", "Prompt drift causing ungrounded output" ], "scaling": "Per-slug; independent of network size.", "future_split_trigger": "Split out Runtime & Capabilities into an independent deployment when its throughput or a distinct scaling profile justifies it; not warranted pre-revenue." }, { "name": "Sync & Rollback", "responsibility": "Daily GitHub sync of blueprint definitions with dry-run, partial-apply, and server-backed rollback of last snapshot.", "owned_data": [ "sync_runs", "sync_snapshots per slug", "audit_trail" ], "entities": [ "SyncRun", "SyncDiff", "SyncSnapshot", "AuditEntry" ], "interfaces": [ "/github-sync page", "edge functions: github-sync-blueprints, rollback-blueprint-sync" ], "depends_on": [ "Blueprint Core", "Cloud storage for snapshots" ], "events_produced": [ "sync.run.completed", "sync.blueprint.applied", "sync.blueprint.rolled_back" ], "events_consumed": [], "failure_risks": [ "Partial apply leaving mixed state (mitigated by per-blueprint snapshots)", "Audit trail size growth" ], "scaling": "Paginate audit trail; snapshot retention window is finite.", "future_split_trigger": "Split out Sync & Rollback into an independent deployment when its throughput or a distinct scaling profile justifies it; not warranted pre-revenue." }, { "name": "Design & Architecture DNA", "responsibility": "Deterministic per-blueprint design + architecture briefs used to gate release readiness.", "owned_data": [ "derived only — no persistence" ], "entities": [ "DesignDNA", "ArchitectureDNA" ], "interfaces": [ "React panels in Business Detail" ], "depends_on": [ "Blueprint Core" ], "events_produced": [], "events_consumed": [], "failure_risks": [ "Vertical → profile drift if new verticals are not mapped" ], "scaling": "Pure functions; free.", "future_split_trigger": "Split out Design & Architecture DNA into an independent deployment when its throughput or a distinct scaling profile justifies it; not warranted pre-revenue." } ], "data_architecture": { "primary_db": "Managed Postgres (Cloud)", "secondary": [ "Object storage for artifacts + snapshots", "Client localStorage for UI state (filters, drawer state) — never for auth" ], "cache": "React Query + module-level memoization; no dedicated cache service.", "search": "Postgres FTS on titles + evidence; consider pg_trgm on slugs.", "vector": "not applicable", "object_storage": "Per-slug prefixes; lifecycle rules to prune stale sync snapshots.", "schema_strategy": "Normalized core + JSONB for evolving shapes (evidence details, capability status).", "migrations": "Forward-only migrations reviewed in PR; every CREATE TABLE ships GRANTs + RLS enable + policies in the same migration.", "backups": "Managed daily backups with 30-day retention.", "retention": "Audit trail retained ≥ 1y; sync snapshots retained 90d; error diagnostics retained 30d.", "audit_logs": "audit_trail table + append-only pattern; export CSV from UI.", "soft_delete": "Soft-delete evidence via status transition; hard-delete only via owner-initiated purge.", "privacy": "Only owner-supplied facts persist; service records, attestations, regulator correspondence handled per vertical policy.", "encryption": "TLS 1.2+ in transit; AES-256 at rest via managed storage.", "multi_tenancy": "Row-level tenancy keyed on auth.uid() + blueprint slug; RLS policies enforce isolation." }, "api": { "style": "REST-ish RPC over edge functions with JSON payloads; typed client wrappers.", "public_vs_internal": "Public microsite reads via Postgres RLS-protected queries; internal capability calls via authenticated edge functions.", "versioning": "Version via function name suffix (v1, v2) when breaking; additive changes preferred.", "rate_limiting": "Per-user + per-slug in edge functions; UI-level concurrency caps for AI calls.", "idempotency": "Sync + rollback carry an idempotency key; retries safe.", "pagination": "Cursor pagination on audit trail; offset paging tolerated on small lists.", "error_format": "{ code, message, correlationId, retryable, details? } — normalized in client.", "webhook_security": "HMAC-signed webhooks (deferred until we accept inbound webhooks).", "retries": "Exponential backoff + jitter, capped attempts, respect idempotency keys.", "contract_testing": "Zod schemas shared between client + edge; smoke test runner exercises each endpoint.", "backward_compat": "Additive fields only; deprecations announced in audit trail before removal.", "contract_testing_plan": "Intake, source-result, and delivery payload schemas are contract-tested per consumer; the JSON contract between AI layers is schema-pinned and versioned." }, "security": { "authn": "Managed OAuth (Google default). Session in httpOnly cookie / managed client storage.", "authz": "user_roles table + has_role() SECURITY DEFINER, referenced from RLS policies. Never store roles on profiles.", "tenant_isolation": "RLS on every public table; every query filters by auth.uid() or by an explicit owner grant.", "secrets": "Managed vault; never in client bundle; edge functions read via runtime env.", "encryption": "TLS in transit; AES-256 at rest; column-level encryption only when regulation requires.", "session": "Short-lived access tokens + refresh rotation; SSR cookie parity for edge routes.", "input_validation": "Zod schemas at the edge boundary; reject on unknown fields.", "api_protection": "Rate limits + WAF rules on public endpoints; correlationId logging for abuse forensics.", "audit_log": "Every release decision, evidence toggle, sync, and rollback records actor + timestamp + before/after.", "admin_access": "Admin actions gated behind role check + two-key confirmation on destructive operations.", "supply_chain": "Lockfile pinning + weekly dependency scan; SBOM produced on release.", "threat_model": [ "Prompt injection via ingested source files → sanitize + refuse instructions from ingested content.", "Cross-tenant read via missing RLS on new table → migration checklist blocks merge.", "Rollback abuse to overwrite recent legitimate edits → rollback preview + confirm-typed pattern.", "AI cost DOS by repeated regeneration → per-slug rate limits + concurrency cap." ], "abuse_cases": [ "Malicious owner uploads privileged content into a public microsite field.", "Sync run tampered with to inject a slug that overlaps a real blueprint.", "Attacker triggers regeneration loop to drive AI cost." ], "zero_trust": "Every service call authenticates; no implicit trust between edge functions.", "asvs_notes": "OWASP ASVS L1 baseline." }, "reliability": { "failure_modes": [ "Edge function IDLE_TIMEOUT on long AI generations.", "Upstream AI provider 5xx / rate limit.", "GitHub API rate limit during sync.", "Postgres connection saturation during sync fan-out." ], "graceful_degradation": "Runtime tab modules degrade independently; microsite serves cached last-known-good content when generation fails.", "retry_policy": "Exponential backoff + jitter, max 5 attempts, respect Retry-After.", "timeouts": "Edge function ≤ 120s wall clock (safety margin under 150s limit); client fetch ≤ 60s per call.", "circuit_breaker": "Client-side per-endpoint breaker: after 3 consecutive IDLE_TIMEOUTs, pause 5m and surface to UI.", "queueing": "In-app blueprintJobQueue with concurrency limits per slug.", "idempotency": "Sync + rollback idempotent via key; generation endpoints idempotent per (slug, doc_key).", "dlq": "Failed jobs recorded in error diagnostics; user re-triggers manually (no auto-DLQ needed at current volume).", "transactions": "Multi-row writes wrapped in single transaction; audit entry written in the same transaction as the mutation.", "dr": "Daily backup + semi-annual restore drill.", "incident_response": "correlationId in every log line; on-call runbook per capability module; smoke test replays post-incident.", "slos": [ { "name": "Interactive p95", "target": "600 ms on blueprint detail" }, { "name": "Availability", "target": "99.5% (with March-reporting-window freeze protection)" }, { "name": "Sync success rate", "target": "≥ 99% per daily run over rolling 7 days" }, { "name": "Generation success rate", "target": "≥ 95% per doc across last 7d (excludes provider outages)" } ] }, "scaling": { "mvp_can_stay_simple": [ "Single Postgres, single region.", "No dedicated search or vector index.", "In-app job queue; no message broker." ], "modular_now": [ "Content Pipeline is already isolated behind blueprintJobQueue — future extraction is a 1-day job.", "Runtime capabilities are one function per module — swap in isolation." ], "deferrable": [ "Workflow engine (Temporal/Airflow).", "Vector DB / RAG.", "Multi-region replication.", "Feature flag service (env-based toggle covers MVP)." ], "breaks_first": "Edge function IDLE_TIMEOUT under multi-doc generation — already addressed by per-doc endpoints; watch for regression.", "db_path": "Vertical scale → read replica → partition by tenant if a single tenant dominates load.", "jobs_path": "In-app queue → dedicated worker → workflow engine, gated by concurrency + resumability need.", "cache_path": "React Query only → HTTP cache headers → CDN edge cache for microsite content.", "search_path": "Postgres FTS → pg_trgm → dedicated search only when p95 breaches SLO.", "files_path": "Managed object storage → CDN → per-region cache if traffic warrants.", "api_path": "Vertical edge function scale → per-capability autoscaling → extract hot module to its own service.", "multi_region": "Not planned; introduce only on customer contract with residency requirement.", "cost_control": "Per-blueprint AI budget, concurrency cap, smoke-test cache; monthly cost review with per-blueprint attribution." }, "ai": { "provider": "Frontier LLM via API with provider-agnostic prompt contracts; a second vendor is configured for failover so a released deliverable never depends on a single model.", "prompt_mgmt": "Extraction, drafting, and matrix prompts are held in versioned files with eval-gated deploys and one-step rollback; prompt changes require diff review.", "rag": "A versioned, jurisdiction-scoped rule pack for Regulatory compliance is retrieved with source-scoped filters; drafting is grounded and citation-anchored to the source text, never free-form generation.", "vector": "Not warranted pre-revenue — the rule pack is small and structured, so section/keyword lookups suffice until a larger corpus justifies similarity search.", "embeddings": "Deferred with the vector store; rule-pack keys are structured (element, source, subsection), not semantic.", "eval": "A gold set of specialist-released packs measures element-extraction F1 and completeness-gate agreement per model release; accuracy vs specialist labels is reviewed on a fixed cadence.", "hitl": "Specialist release is never automated; a domain expert signs off on the exception queue, with sampling QA on a fraction of outputs and expert red-team on the first releases.", "guardrails": "Field-locked templates, source-tie reconciliation, and completeness rules mean a draft missing a required field emits a MISSING_ELEMENT exception rather than inventing content.", "prompt_injection": "Source documents are treated as data, never instructions; the red-team suite includes injected-instruction files disguised as legitimate inputs.", "leakage": "Client and subject identifiers are scoped per case; retrieval is scoped per client; provider training-use is disabled; there is no cross-client corpus.", "fallback": "A manual specialist workbench runbook plus the second LLM vendor keep production moving if the primary model is unavailable.", "latency_cost": "Inference cost per deliverable is bounded at launch and trends down with volume; the standard SLA leaves generous headroom over model latency.", "memory": "Agents are stateless per case; durable knowledge lives in the versioned rule pack and SOP library, not in model memory.", "tool_permissions": "The prompt runner has no tool access beyond returning JSON; search ordering, document assembly, and delivery are deterministic code.", "auditability": "Every prompt+output pair is logged to the per-case audit trail with version tags alongside the specialist release record.", "citation": "Every drafted element carries the source provision it satisfies, and every matrix entry carries the search or record it came from." }, "devops": { "environments": [ "Preview (per branch)", "Production" ], "cicd": "Lovable build pipeline; deploys on merge; edge functions ship atomically with the app.", "iac": "Cloud managed; migrations + config in-repo.", "secrets": "Managed vault; separate values per environment.", "preview_envs": "Automatic per branch; seeded with anonymized fixtures.", "migrations": "Forward-only; migrations reviewed for GRANT + RLS + policies; every table gated by the migration checklist.", "rollback": "App: redeploy previous build. Data: server-backed rollback per blueprint via rollback-blueprint-sync.", "release_style": "Continuous deploy with feature flags; canary only when a change touches shared shell.", "feature_flags": "Env-based booleans at MVP; consider a flag service when we have > 20 flags in flight.", "monitoring": "Cloud platform metrics + per-function logs + client error reporting.", "alerting": "SLO burn-rate alerts + IDLE_TIMEOUT rate alert + AI cost anomaly alert.", "logs": "Structured JSON with correlationId; retained per platform defaults.", "error_tracking": "Client-side error capture wired to console + in-app diagnostics drawer.", "uptime": "Synthetic checks on microsite + shell login every 5 minutes.", "cost_monitoring": "Per-blueprint cost view; alert on 3x baseline over 24h." }, "testing": { "unit": "Vitest for pure derivations (DNA, business helpers).", "integration": "Edge function contract tests with recorded fixtures.", "contract": "Zod schemas shared client + edge; smoke test runner as continuous contract check.", "e2e": "Playwright against localhost preview for critical flows (sign in, evidence toggle, sync apply).", "security": "Weekly dependency scan; RLS policy audit script; abuse-case checklist per release.", "a11y": "Axe checks + keyboard-only smoke on shell components; WCAG 2.2 AA target.", "load": "k6 scenarios against edge functions before enabling a new capability network-wide.", "chaos": "Manual fault injection on AI provider (simulate 500s) during release rehearsal.", "migration": "Every migration runs in preview + dry-run on prod snapshot before apply.", "backup_restore": "Semi-annual restore drill.", "ai_eval": "not applicable", "test_data": "Deterministic fixtures per vertical; no real PHI/PII ever in fixtures." }, "observability": { "logs": "Structured JSON with correlationId, phase, attempt, doc_key, slug.", "metrics": "Per-endpoint latency, error rate, retry count, AI token spend.", "traces": "Cross-function trace via correlationId propagation.", "audit_events": "Release decision, evidence toggle, sync, rollback, cache invalidation.", "business_events": "Blueprint promoted to ready, first microsite view, first customer-visible export.", "error_tracking": "In-app diagnostics drawer + persistent per-slug error history.", "security_monitoring": "Failed auth + rate-limit breach + admin action logs.", "cost_monitoring": "Per-blueprint + per-capability cost attribution.", "dashboards": [ "SLO burn", "AI cost per blueprint", "Sync success rate", "Generation success rate" ], "alert_thresholds": [ "IDLE_TIMEOUT rate > 3/day for one blueprint.", "Sync run failure > 1 in rolling 7 days.", "AI cost > 3x rolling 7-day baseline over 24h.", "p95 breach on Blueprint detail > 800ms for 15 min." ], "triage": "correlationId → diagnostics drawer → retry timeline → JSON report export → runbook link." }, "cost": { "drivers": [ { "name": "AI generation", "note": "Dominant driver; capped by concurrency + per-slug budget." }, { "name": "Edge function invocations", "note": "Bursty at sync + generation; idle-to-zero otherwise." }, { "name": "Managed Postgres", "note": "Small; scales with audit trail retention." }, { "name": "Object storage", "note": "Snapshots + artifacts; lifecycle rules prevent growth." }, { "name": "Bandwidth", "note": "Low; static microsite content." } ], "likely_traps": [ "Regeneration loops on failure (mitigated by circuit breaker).", "Audit trail unbounded growth (mitigated by retention policy).", "Storing large HTML snapshots per sync (mitigated by delta snapshots)." ], "controls": [ "Per-blueprint AI budget with hard cap.", "Smoke-test result caching in localStorage.", "Concurrency cap in blueprintJobQueue.", "Retention policy on audit + diagnostics." ] }, "multi_tenancy": { "model": "Row-level tenancy: one shared Postgres, tenant scope by auth.uid() + blueprint slug.", "isolation": "RLS policies on every public table; policies reference has_role() where role checks are needed.", "tenant_aware_authz": "Every query filters by auth.uid(); admin overrides go through explicit role check + audit entry.", "tenant_config": "Per-slug config stored as JSONB on the blueprint row; no per-tenant deploy.", "branding": "Per-blueprint Design DNA drives theme; no runtime branding upload at MVP.", "tenant_export": "Owner can export evidence + audit trail as JSON/CSV from the UI.", "tenant_deletion": "Owner-initiated purge cascades across blueprint rows + storage prefix; soft-delete window of 30 days.", "tenant_audit": "Per-slug audit trail table view with actor + timestamp on every mutation.", "noisy_neighbor": "Per-slug concurrency cap in blueprintJobQueue; per-slug AI budget.", "tenant_rate_limits": "Edge functions apply per-slug + per-user rate limits.", "billing": "Not billed at MVP; per-blueprint cost attribution feeds the future billing model.", "why_this_fits": "Team size and blueprint scale don't justify schema/db-per-tenant; RLS covers the isolation requirement with negligible ops burden." }, "privacy_compliance": { "data_classification": "Owner-supplied facts and evidence citations are the sensitive classes; service records, attestations, regulator correspondence per vertical.", "minimization": "Only owner-supplied facts persist; no third-party enrichment; no PII scraping.", "consent": "Consent captured at intake for owner-supplied contact info; microsite visitors get standard cookie/consent banner where required.", "access_logs": "Every admin + edge function invocation logged with correlationId + actor.", "audit_trails": "Immutable append-only audit_trail table; export from UI.", "retention": "Audit ≥ 1y; sync snapshots 90d; error diagnostics 30d; artifacts per lifecycle rule.", "legal_hold": "Deferred until a matter requires it.", "right_to_delete": "Owner-initiated purge honored within 30 days; downstream copies pruned by lifecycle rules.", "right_to_export": "JSON + CSV export for evidence, audit trail, and generated artifacts.", "sensitive_handling": "No PHI/PII in prompts; owner-supplied facts only; secrets in managed vault.", "boundaries": "Domain-specific (owner-side MCP and conveyance maintenance records, analyst/consultant release signers, 5-year retention schedules)", "residency": "Single region at MVP; residency contract triggers per-tenant residency planning.", "vendor_risk": "Lovable Cloud + AI Gateway are the only critical vendors; both reviewed for security posture.", "breach_response": "correlationId + audit trail enables scope determination; disclosure per compliance policy within statutory window.", "admin_controls": "Admin actions gated by role check + two-key confirm for destructive operations; every admin session logged.", "evidence_collection": "Access reviews, change management, restore drills produce artifacts filed into the evidence pipeline." }, "frontend": { "framework": "React 18 + Vite + TypeScript.", "rendering": "SPA with per-route code-split; microsite routes prerender-friendly.", "routing": "react-router-dom v6 with URL-persisted filter/drawer state.", "state": "React context + useSyncExternalStore for the job queue; localStorage only for UI state, never for auth.", "server_state": "@tanstack/react-query for cache + retries.", "forms": "Controlled components + Zod validation on submit; RHF only where forms grow.", "error_handling": "Error boundary at shell + per-panel skeletons + retry affordances.", "components": "shadcn primitives + per-blueprint themed panels; deterministic Design DNA drives look.", "design_system": "Tailwind semantic tokens (index.css); no hardcoded color utilities in components.", "auth_ui": "Managed OAuth callback via Cloud client; session hydration before protected routes render.", "authz_aware_ui": "UI hides actions the current role cannot perform; server-side check is authoritative.", "a11y": "WCAG 2.2 AA target; visible focus rings; keyboard shortcuts in diagnostics drawer.", "i18n": "Copy budgets assume +35% expansion for DE/FR; Intl APIs for dates/currencies.", "performance": "Route-level code split; lazy-load Runtime tab; memoize DNA derivations.", "bundling": "Vite defaults; per-route lazy imports for heavy panels.", "testing": "Vitest for unit; Playwright for critical flows.", "offline": "Not required; last-known-good served from React Query cache.", "realtime": "Not required at MVP; audit trail is polled on interaction." }, "backend": { "framework": "Deno-based edge functions on Lovable Cloud, one function per capability.", "layering": "Handler → validator (Zod) → service → repository → Postgres.", "domain": "Blueprint, Evidence, OwnerAction, SyncRun, RuntimeCapability, ChatMessage.", "services": "Pure functions kept out of edge boundary; shared logic imported from a common module.", "repositories": "Thin Postgres wrappers; RLS enforces tenant scope.", "validation": "Zod at the edge boundary; reject unknown fields.", "authorization": "has_role() SECURITY DEFINER in Postgres; edge function also asserts role for defense in depth.", "jobs": "In-app blueprintJobQueue on the client for user-triggered pipelines; server-side cron only for daily sync.", "events": "Domain events emitted to audit_trail; no external broker.", "files": "Signed URLs from Cloud Storage; virus scan on upload (deferred until user uploads exist).", "email_sms": "Deferred; owner-configured inbox required before enabling outbound mail.", "scheduled": "Daily GitHub sync via scheduled function; retention prune weekly.", "errors": "Normalized error envelope { code, message, correlationId, retryable, details? }.", "logging": "Structured JSON logs with correlationId, phase, attempt, slug.", "config": "Env-based; secrets from managed vault.", "di": "Not required at current size; explicit imports.", "testing": "Contract tests per function with recorded fixtures + smoke-test runner." }, "diagrams": { "context_mermaid": "flowchart LR\n Owner([Blueprint Owner]) --> Shell[Network Shell]\n Reviewer([Reviewer]) --> Shell\n Public([Public Visitor]) --> Micro[Public Microsite elevator-mcp-completeness-pack-engine]\n Shell --> Cloud[(Lovable Cloud: DB + Auth + Storage + Edge)]\n Cloud --> AI[[AI Gateway]]\n Cloud --> GH[[GitHub API]]\n Micro --> Cloud", "container_mermaid": "flowchart TB\n subgraph Client\n UI[React Shell + Blueprint Detail]\n Queue[blueprintJobQueue]\n end\n subgraph Cloud[Lovable Cloud]\n DB[(Postgres + RLS)]\n Store[(Object Storage)]\n subgraph Edge[Edge Functions]\n Sync[github-sync-blueprints]\n Roll[rollback-blueprint-sync]\n Src[fetch-blueprint-sources]\n Seed[generate-seed-articles]\n Docs[generate-blueprint-docs]\n Legal[generate-legal-docs/*]\n Verify[verify-blueprint]\n SEO[generate-seo-posts]\n Chat[blueprint-chat]\n end\n end\n UI --> DB\n Queue --> Src\n Queue --> Seed\n UI --> Docs\n UI --> Legal\n UI --> Verify\n UI --> SEO\n UI --> Chat\n UI --> Sync\n UI --> Roll\n Seed --> AI[[AI Gateway]]\n Docs --> AI\n Legal --> AI\n Chat --> AI\n Src --> GH[[GitHub]]", "data_flow_mermaid": "flowchart LR\n A[Owner edits Evidence] --> B[Store: evidence.custom]\n B --> C{Release Gate}\n C -- ready --> D[Business marked Ready]\n C -- blocker --> E[Owner Actions queue]\n F[GitHub Sync] --> G[Diff + Snapshot]\n G --> H[(Postgres)]\n H --> I[Audit trail]\n H --> J[React store]", "auth_flow_mermaid": "sequenceDiagram\n participant U as User\n participant UI as Network Shell\n participant Auth as Cloud Auth\n participant API as Edge Function\n participant DB as Postgres+RLS\n U->>UI: sign in\n UI->>Auth: OAuth (Google)\n Auth-->>UI: session (JWT)\n UI->>API: call with JWT\n API->>DB: query as auth.uid()\n DB-->>API: rows filtered by RLS\n API-->>UI: response", "authz_flow_mermaid": "flowchart LR\n Req[Request w/ JWT] --> Fn[Edge Function]\n Fn --> Role[has_role user_id, role]\n Role --> DB[(user_roles + RLS policies)]\n DB -- allow --> Ok[Return rows]\n DB -- deny --> Err[403 + audit entry]", "deployment_mermaid": "flowchart LR\n Dev[Developer] --> Repo[Git]\n Repo --> CI[Lovable Build]\n CI --> Preview[Preview Env]\n CI --> Prod[Production]\n Prod --> Cloud[(Lovable Cloud)]\n Prod --> CDN[[Edge CDN]]", "background_job_mermaid": "flowchart LR\n UI[Blueprint Detail] --> Enq[blueprintJobQueue.enqueue]\n Enq --> Slot{Concurrency slot?}\n Slot -- yes --> Run[Run job]\n Slot -- no --> Queued[queued]\n Run -->|success| Done[Persist result + emit event]\n Run -->|error| Back[Exponential backoff + jitter]\n Back -->|attempts left| Run\n Back -->|exhausted| Fail[Record diagnostic + expose retry button]", "event_flow_mermaid": "flowchart LR\n Sync[sync.blueprint.applied] --> Core[Blueprint Core]\n Integ[integrity.completed] --> UI\n CacheInv[cache.invalidated] --> Pipe[Content Pipeline]\n Pipe --> Sources[sources.fetched]\n Sources --> Articles[articles.generated]\n Articles --> Integ", "failure_flow_mermaid": "flowchart LR\n Call[Edge Function call] --> Timeout{Timeout / 5xx?}\n Timeout -- no --> Ok[Success]\n Timeout -- yes --> Retry[Backoff + retry]\n Retry --> Cap{Attempts cap?}\n Cap -- no --> Call\n Cap -- yes --> Breaker[Open circuit]\n Breaker --> Cache[Serve last-known-good]\n Breaker --> Owner[Surface diagnostic + owner action]", "multi_tenant_flow_mermaid": "flowchart LR\n Owner1([Owner A]) --> UI\n Owner2([Owner B]) --> UI\n UI --> API[Edge Function w/ JWT]\n API --> Policy{RLS: auth.uid + slug scope}\n Policy -- match --> Rows[Owner-scoped rows]\n Policy -- no match --> Deny[403]", "ai_flow_mermaid": "graph LR; SRC[Source documents as DATA]-->EX[Extract + normalize]-->SR[Order source searches]-->MTX[Build matrix]-->DR[Draft locked-field elements]-->GT[Deterministic completeness gates]-->SP[Specialist release]-->DL[Deliver]; GT-.exception.->SP; SP-.high-risk.->EXP[Expert review]" }, "adrs": [ { "id": "ADR-001", "decision": "Adopt modular monolith as the network-wide architecture style", "context": "Small team maintaining many blueprints with shared shell, evidence discipline, and per-vertical trust variation.", "options": [ "simple monolith", "modular monolith", "microservices", "serverless-only", "hybrid" ], "chosen": "modular monolith", "why": "Preserves a single audit boundary and deploy cadence while allowing edge functions for burst workloads.", "consequences": [ "Shared deploy lifecycle across blueprints", "Row-level tenant isolation carries the security load" ], "risks": [ "A rogue blueprint can regress network shell performance" ], "reversal": "Extract a module to its own deploy only when its SLO diverges from the network shell.", "revisit_when": "A blueprint acquires a divergent SLO, a second team joins, or the shell deploy time exceeds 10 minutes." }, { "id": "ADR-002", "decision": "Managed Postgres as the sole primary datastore", "context": "All entities are relational (blueprints, evidence, sync runs, articles, audit).", "options": [ "Postgres", "Postgres + DocumentDB", "Postgres + vector DB", "Firestore" ], "chosen": "Postgres (Cloud managed) with JSONB for semi-structured fields", "why": "Relational integrity + row-level security satisfies audit, tenancy, and reporting; JSONB absorbs shape drift.", "consequences": [ "RLS policies are the primary tenancy control", "Full-text search via Postgres FTS until it stops scaling" ], "risks": [ "Complex joins under growth" ], "reversal": "Introduce a read-replica or a dedicated search index only when p95 breaches SLO.", "revisit_when": "FTS p95 > SLO for 2 consecutive weeks, or a genuine RAG surface appears." }, { "id": "ADR-003", "decision": "Per-document edge functions for long-running AI generation", "context": "IDLE_TIMEOUT (150s) on monolithic legal-docs generator forced this split.", "options": [ "Single long function", "Chunked per-doc functions", "Background job with polling" ], "chosen": "Per-document endpoints with client-side fan-out + retries", "why": "Keeps each invocation under the timeout, isolates failures, enables partial success reporting.", "consequences": [ "More endpoints to maintain", "Client must own orchestration" ], "risks": [ "Client back-pressure if fan-out is too wide" ], "reversal": "Move to a real workflow engine when we cross ~10 concurrent long jobs per blueprint.", "revisit_when": "Concurrent long-running jobs > 10 per blueprint, or client-side orchestration becomes buggy." }, { "id": "ADR-004", "decision": "Evidence-first release gate", "context": "Vertical compliance posture: Domain-specific (owner-side MCP and conveyance maintenance records, analyst/consultant release signers, 5-year retention schedules).", "options": [ "Owner-declared ready", "Auto-ready via checklist", "Evidence-gated ready" ], "chosen": "Evidence-gated ready — release requires resolved owner actions + verified evidence", "why": "Regulated verticals cannot ship on self-declaration; evidence provides defensibility.", "consequences": [ "Slower path to ready", "Higher confidence at ready" ], "risks": [ "Owners abandon incomplete blueprints" ], "reversal": "Introduce a 'ready-with-caveats' state only if the network stalls on this gate.", "revisit_when": "> 30% of blueprints stuck in owner-action state for > 30 days." }, { "id": "ADR-005", "decision": "Defer AI adoption until a specific evidence-generation need arises", "context": "AI is powerful but adds cost, latency, and auditability burden.", "options": [ "No AI", "Grounded AI only", "Agentic AI" ], "chosen": "No AI in this vertical", "why": "Vertical does not currently justify AI-shaped complexity.", "consequences": [ "No prompt catalog to maintain" ], "risks": [], "reversal": "Introduce AI only for a scoped generation task.", "revisit_when": "A specific generation task appears with clear source grounding." }, { "id": "ADR-006", "decision": "Managed OAuth (Google) with roles in a dedicated user_roles table", "context": "Storing roles on the profile row invites privilege-escalation bugs; RLS policies must reference a stable role source.", "options": [ "Roles on profiles", "user_roles + has_role() SECURITY DEFINER", "External IdP with JIT claims" ], "chosen": "user_roles table + has_role() SECURITY DEFINER, referenced by RLS", "why": "Prevents recursive RLS, isolates authz decisions, satisfies audit review.", "consequences": [ "One extra join in policies", "Explicit role grants required" ], "risks": [ "Role drift if grants are not audited" ], "reversal": "Swap SECURITY DEFINER function for an IdP claim without changing policies.", "revisit_when": "Enterprise SSO / SAML contract signed, or role count exceeds ~10." }, { "id": "ADR-007", "decision": "Single-tenant per blueprint slug with row-level isolation", "context": "Blueprints share infra but must never cross-read evidence, sync history, or generated artifacts.", "options": [ "Shared DB + RLS", "Schema-per-tenant", "DB-per-tenant" ], "chosen": "Shared DB + RLS keyed on auth.uid() and blueprint slug", "why": "Simplest operable model at current scale; migration cost stays near zero.", "consequences": [ "RLS is load-bearing security" ], "risks": [ "A missing policy = a leak" ], "reversal": "Extract a specific tenant to its own schema when contract requires it.", "revisit_when": "First enterprise customer with a residency or dedicated-DB clause." } ], "roadmap": [ { "phase": "MVP", "build": [ "Network shell + Blueprint Core module", "Content Pipeline with concurrency + backoff", "Design + Architecture DNA per blueprint", "Sync + rollback + audit trail" ], "avoid": [ "Any per-blueprint deploy pipeline", "Message brokers", "Vector DBs", "Multi-region" ], "defer": [ "A workflow engine", "Full-text search infra", "Dedicated CDN rules" ], "monitor": [ "Edge function IDLE_TIMEOUT rate", "AI cost per generation", "Duplicate-slug regressions" ], "triggers_to_change": [ "p95 breach on Blueprint detail > 800ms", "≥ 3 IDLE_TIMEOUTs/day sustained" ], "acceptable_debt": [ "Client-owned job orchestration", "localStorage-backed UI state" ], "dangerous_debt": [ "Missing RLS on any public table", "Ungrounded AI in customer-visible surfaces" ] }, { "phase": "Stabilization", "build": [ "Automated smoke test per blueprint on cache invalidation", "Per-slug retention + audit trail export", "Contract tests for every edge function" ], "avoid": [ "Premature module extraction" ], "defer": [ "Multi-tenant admin console" ], "monitor": [ "SLO burn rate", "Cost per blueprint per week" ], "triggers_to_change": [ "A single blueprint accounts for > 30% of AI spend" ], "acceptable_debt": [ "Manual runbook execution for rare failures" ], "dangerous_debt": [ "Untested rollback path", "Backups without a restore drill" ] }, { "phase": "Growth", "build": [ "Optional workflow engine adapter behind the current queue interface", "Read replica for Postgres if analytics queries interfere", "Feature flags per capability module" ], "avoid": [ "Splitting Blueprint Core into services without SLO justification" ], "defer": [ "Real-time collaboration" ], "monitor": [ "Fan-out concurrency vs edge function limits" ], "triggers_to_change": [ "> 10 concurrent long jobs per blueprint", "New team joins with independent release cadence" ], "acceptable_debt": [ "Env-based feature flags" ], "dangerous_debt": [ "Skipping migration reviews", "Unaudited role grants" ] }, { "phase": "Scale", "build": [ "Extract Content Pipeline to a dedicated service if it dominates deploys", "Search index (Postgres FTS → dedicated) once FTS p95 breaches SLO" ], "avoid": [ "Microservices per blueprint" ], "defer": [ "Multi-region until a customer contract requires it" ], "monitor": [ "DB CPU + IO under peak", "Search p95" ], "triggers_to_change": [ "Regional compliance contract signed" ], "acceptable_debt": [ "Single-region deployment" ], "dangerous_debt": [ "Unbounded audit trail growth", "Missing DR drill evidence" ] }, { "phase": "Enterprise/Compliance", "build": [ "Formal SOC 2 evidence pipeline (access reviews, change management)", "Tenant-scoped encryption keys where regulation requires", "DR drill quarterly with restore proof" ], "avoid": [ "Custom compliance frameworks; ride managed platform attestations" ], "defer": [ "FedRAMP unless a customer commits" ], "monitor": [ "Access review completion", "Restore-test success rate" ], "triggers_to_change": [ "Signed contract with SOC 2 clause", "PHI/PII scope change" ], "acceptable_debt": [ "Manual quarterly access review with checklist" ], "dangerous_debt": [ "Ad-hoc admin access without approval trail" ] } ], "anti_overengineering": { "flagged": [ { "item": "Introducing Kubernetes", "why": "Team size + workload shape don't justify it.", "simpler": "Managed Cloud primitives." }, { "item": "Adopting microservices", "why": "Single deploy cadence + shared audit boundary.", "simpler": "Modular monolith with edge functions." }, { "item": "Adopting a vector DB", "why": "Sources are small + structured; deterministic retrieval works.", "simpler": "Direct source fetch + Postgres FTS." }, { "item": "Adopting event sourcing", "why": "Audit trail table already provides the needed reconstructibility.", "simpler": "Append-only audit_trail + snapshots." }, { "item": "Multi-region from day one", "why": "No customer contract requires it.", "simpler": "Single region + documented DR plan." }, { "item": "Custom workflow engine", "why": "In-app queue covers current concurrency needs.", "simpler": "blueprintJobQueue with backoff." }, { "item": "Premature message queue", "why": "In-app queue + audit trail cover the fan-out cases.", "simpler": "Keep blueprintJobQueue; revisit at 10x volume." }, { "item": "Custom auth", "why": "Managed OAuth + user_roles cover the model.", "simpler": "Cloud Auth + user_roles table." }, { "item": "Premature caching layer", "why": "React Query covers the read-heavy paths.", "simpler": "React Query + HTTP cache headers." }, { "item": "Data warehouse", "why": "No analytics contract; Postgres analytics queries suffice.", "simpler": "Read replica if the primary is hurt." } ] }, "risks": [ { "risk": "Edge function IDLE_TIMEOUT on long generations", "likelihood": "moderate", "impact": "high", "mitigation": "Per-document endpoints + client-side retries with exponential backoff.", "detection": "Smoke test runner + diagnostics drawer flags IDLE_TIMEOUT.", "owner": "engineering", "escalation": "Sustained > 3/day for one blueprint → open incident.", "fallback": "Fall back to last-known-good cached artifact; pause auto-generation for the affected blueprint.", "category": "technical" }, { "risk": "Duplicate slugs in SEED causing UI regressions", "likelihood": "moderate", "impact": "moderate", "mitigation": "mergedSeed dedupes by slug; add lint on SEED at build time.", "detection": "React duplicate-key warning; per-slug uniqueness assertion in tests.", "owner": "engineering", "escalation": "Ship-block if reproduced on main.", "fallback": "Runtime dedupe in mergedSeed keeps first occurrence.", "category": "technical" }, { "risk": "Ungrounded AI output shipped to microsite", "likelihood": "low", "impact": "high", "mitigation": "Citation-first prompts; integrity check gates Seed Articles view.", "detection": "Integrity report failing count > 0 blocks display.", "owner": "engineering", "escalation": "Any customer-visible ungrounded claim → rollback the blueprint.", "fallback": "Auto-hide the article + surface owner action to regenerate with stricter prompt.", "category": "product" }, { "risk": "Cross-tenant data leak via missing RLS on new table", "likelihood": "low", "impact": "critical", "mitigation": "Every CREATE TABLE ships with GRANT + ENABLE RLS + policies in the same migration.", "detection": "Security scanner + migration checklist.", "owner": "engineering", "escalation": "Immediate lockdown + audit.", "fallback": "Revoke Data API grants on affected table; restore from PITR if data was modified.", "category": "security" }, { "risk": "AI cost runaway on a single blueprint", "likelihood": "moderate", "impact": "moderate", "mitigation": "Per-slug rate limits + smoke-test cache + concurrency cap in UI.", "detection": "Cost monitoring dashboard; per-blueprint spend alert at 3x baseline.", "owner": "SRE", "escalation": "Auto-pause generation; require manual re-enable.", "fallback": "Disable AI for the offending blueprint via feature flag; serve last-known-good.", "category": "cost" }, { "risk": "AI provider outage or model deprecation", "likelihood": "moderate", "impact": "moderate", "mitigation": "Per-capability fallback model + retry with backoff; abstract via Lovable AI Gateway.", "detection": "Elevated 5xx or empty completions; smoke test failing across blueprints.", "owner": "engineering", "escalation": "Sustained > 30 min → switch fallback model; notify owners.", "fallback": "Serve cached artifacts + disable AI-only capabilities until restored.", "category": "vendor" }, { "risk": "Compliance evidence gap during audit", "likelihood": "low", "impact": "high", "mitigation": "Evidence-first release gate + audit trail export from UI.", "detection": "Missing audit entries surfaced in periodic reconciliation report.", "owner": "legal", "escalation": "Regulator-visible gap → incident + disclosure per policy.", "fallback": "Freeze affected blueprint's release state; produce backfill evidence pack.", "category": "compliance" }, { "risk": "Solo/small-team key-person dependency", "likelihood": "moderate", "impact": "high", "mitigation": "Deterministic DNA modules keep decisions in code, not in one head; runbooks per capability.", "detection": "Bus-factor review each quarter.", "owner": "owner", "escalation": "> 1 critical path with no backup → hire or contract.", "fallback": "Freeze non-critical changes; document current state before further work.", "category": "team" }, { "risk": "Audit trail gaps on release decisions", "likelihood": "low", "impact": "critical", "mitigation": "Every mutation writes audit entry in the same transaction.", "detection": "Audit trail row count vs mutation count reconciliation.", "owner": "engineering", "escalation": "Regulator-visible gap → incident + disclosure.", "fallback": "Reconstruct from Postgres WAL + application logs; disclose per compliance policy.", "category": "compliance" } ], "rules": [ "Keep business logic out of UI components — derivations live in lib/*, panels only render.", "Do not introduce a new service without a clear owner and a scaling reason.", "All external integrations must have retries, timeouts, and failure handling.", "All sensitive actions must be auditable in the same transaction that performs them.", "All background jobs must be idempotent.", "All APIs must return the normalized error envelope.", "All tenant-scoped queries must enforce tenant isolation via RLS — never trust the client.", "All expensive AI calls must be logged, capped, and observable.", "All schema changes must be reversible or safely migratable — no destructive drops without a rollout plan.", "All critical workflows must have observability: correlationId, phase timings, retry timeline.", "Every public table ships with GRANT + ENABLE RLS + policies in the same migration.", "Every AI span carries a citation; no citation, no ship.", "Every destructive action requires typed confirmation." ], "audit": { "product_fit": "Architecture matches an evidence-first, regulated-adjacent workflow product per blueprint.", "simplicity": "One shell, one DB, edge functions for bursts — near the simplicity floor for the product's ambitions.", "security": "RLS + role table + audit trail; meets ASVS L1 baseline.", "reliability": "SLOs defined; per-module degradation; retries + diagnostics in place.", "scalability": "Horizontal by blueprint count is the growth axis; per-blueprint scaling is comfortably in headroom.", "maintainability": "Deterministic derivations (Design DNA, Architecture DNA) keep per-vertical drift out of components.", "performance": "p95 target 600ms is realistic on Cloud edge with warm cache.", "cost": "Idle-to-zero for cold blueprints; per-blueprint attribution keeps AI spend controllable.", "compliance": "Domain-specific (owner-side MCP and conveyance maintenance records, analyst/consultant release signers, 5-year retention schedules)", "dx": "Single stack (React + Vite + Tailwind + Cloud); new blueprint reaches microsite state in one session.", "ops_burden": "Managed platform absorbs infra ops; SRE work is limited to SLO watch + runbooks.", "extensibility": "New capability = new edge function + new Runtime tab entry; no shell changes required.", "team_suitability": "Fits a small team; every added component must retire an older one.", "time_to_market": "New blueprint reachable to validation-microsite state within one working session.", "recommendation": { "style": "modular monolith", "stack": "React + Vite + TypeScript + Tailwind + shadcn on the client; Deno edge functions + managed Postgres (RLS) + object storage on the server; Lovable AI Gateway (unused in this vertical).", "hosting": "Lovable Cloud managed hosting; preview + production environments; edge functions co-deploy with the app.", "database": "Managed Postgres with RLS + JSONB; PITR enabled for critical-tier tenants.", "auth": "Managed OAuth (Google default) + user_roles table + has_role() SECURITY DEFINER referenced from RLS policies.", "integrations": "GitHub (public read) for sync + sources; Lovable AI Gateway for LLM calls; Cloud Storage for artifacts. No third-party CRM/email/SMS at MVP.", "ai_approach": "No AI at MVP for this vertical; revisit only when a scoped generation task with clear sources appears.", "build_first": [ "Blueprint Core (evidence + release gate) — vertical-agnostic.", "Content Pipeline (sources → articles → integrity) — required for any evidence claim.", "Sync + rollback — required to safely onboard the network." ], "avoid": [ "Any per-blueprint deploy pipeline.", "Autonomous AI agents that mutate data without owner confirmation.", "Bespoke workflow engines before the in-app queue is exhausted." ], "revisit_later": [ "Workflow engine adoption when > 10 concurrent long jobs per blueprint.", "Search index dedicated infra when Postgres FTS p95 breaches SLO.", "Multi-region on the first residency-bound contract." ], "biggest_risks": [ "Missing RLS on a new public table (critical).", "Ungrounded AI output reaching a customer-visible surface.", "AI cost runaway on a single blueprint.", "Solo/small-team key-person dependency." ], "first_10_steps": [ "Confirm managed OAuth + user_roles table + has_role() function are in place.", "Enable RLS + policies on every existing public table; add the migration checklist to CI.", "Wire correlationId end-to-end across every edge function call.", "Ship the smoke test runner as a required post-deploy gate.", "Enable PITR + schedule the first restore drill on the calendar.", "Add per-slug AI budget caps and cost dashboards.", "Enforce evidence-first release gate for every blueprint.", "Set SLO burn-rate alerts on the top 3 SLIs.", "Document the per-capability runbook (retry, cancel, invalidate).", "Publish this Architecture DNA per blueprint as part of the release evidence pack." ], "top_10_rules": [ "Every public table ships with GRANT + RLS + policies in the same migration.", "Every mutation writes an audit entry in the same transaction.", "Every AI span carries a citation; no citation, no ship.", "Every long AI call is per-item, never monolithic.", "Every edge function call carries a correlationId end-to-end.", "Every retry uses exponential backoff + jitter with a hard attempt cap.", "Every destructive action requires typed confirmation.", "No microservice extraction without a divergent SLO.", "No new dependency without a supply-chain scan.", "Signature element (Pack-binder tabs with regime chip) and accent (register-slate) are network invariants — respect them." ] } } }, "design": { "slug": "elevator-mcp-completeness-pack-engine", "archetypes": [ "compliance/regulatory tool", "workflow tool", "operations system" ], "user_mindset": { "goals": "Prove, in minutes, that a building's MCP and 5-year records are complete — often while an AHJ reinspection date or a vendor changeover is already on the calendar.", "session_length": "Bursty around inspection cycles and vendor changeovers; otherwise a quarterly portfolio check-in.", "confidence": "Expert users (facilities coordinators, PM directors); will not accept an opaque AI verdict without a cited clause.", "interface_needs": "Print-parity pack layouts, clause-cited gap rows, freeze/release states, a portfolio view for 5-40 buildings." }, "posture": [ "authoritative", "trustworthy", "operational" ], "density": "compact", "trust_level": { "tier": "high", "sensitive_domains": [ "building maintenance and vendor-service records", "conveyance/unit registry data", "AHJ inspection and red-tag history" ], "implications": [ "Every destructive action confirmed with typed intent, never a single click.", "Errors carry remediation copy + owner, not just a message.", "Focus rings visible on every interactive element (WCAG 2.2 AA minimum).", "Named releaser (analyst or consultant) on any outbound pack.", "Explicit unsaved-changes gate on navigation away from an open pack." ] }, "differentiation": { "avoid": [ "Material Design defaults", "shadcn stock look (unstyled cards + slate ring)", "Purple/indigo gradient heroes", "Stripe/Linear/Notion mimicry", "Vertical cliché: elevator-shaft stock photography and alarm-red penalty banners" ], "strategy": "Anchor on the machine-room register — a ledger of conveyances, each with a status stamp — as the recurring signature element; every page must include it at least once. Reserve the brass/amber accent for release-state and deadline signals only." }, "territories": [ { "name": "Machine Room Register", "color_mood": "graphite steel + brass indicator", "typography": "Fraunces + Inter", "density": "ledger rows", "component_feel": "logbook you'd find bolted inside the machine room", "motion": "row-reveal", "fits": "per-building pack review and release", "risks": "could read as too industrial without warm neutrals" }, { "name": "Portfolio Panel Board", "color_mood": "control-panel navy + amber", "typography": "Neue Haas Grotesk", "density": "grid-driven", "component_feel": "elevator dispatch panel: one lamp per building", "motion": "status-pulse on change", "fits": "5-40 building Portfolio Desk view", "risks": "grid can overwhelm at very large portfolios without grouping" }, { "name": "Chase Timeline", "color_mood": "slate + brass", "typography": "Inter", "density": "timeline", "component_feel": "vendor demand-letter thread with dated follow-ups", "motion": "scroll-sync", "fits": "Chase Desk vendor cure-cycle tracking", "risks": "timeline fatigue on long-running disputes" } ], "chosen_territory": "Machine Room Register", "chosen_rationale": "The Completeness Pack is the deliverable and the building is the unit of work; a register/ledger metaphor keeps every screen artifact-shaped — the way an AHJ inspector or insurer would actually ask to see it — without borrowing another launched business's binder-tab motif.", "prioritized_components": [ { "name": "AHJ chip", "why": "every building is scoped by its Authority Having Jurisdiction and adopted ASME A17.1 edition" }, { "name": "Gap row with clause citation", "why": "every line in the gap matrix must show the exact §8.6 / AHJ clause it fails or satisfies" }, { "name": "Completeness Pack assembler", "why": "the release output is a bundle: gap matrix + evidence inventory + chase kit + vault index" } ], "patterns": [ { "name": "AHJ switcher", "description": "Global AHJ/jurisdiction selector (Colorado, Fairfax/VA, expandable); every query and checklist respects it." }, { "name": "Pack release stamp", "description": "Named compliance analyst or licensed elevator consultant/QEI attestation; red (escalated) packs cannot release without the consultant." } ], "states": [ "default", "hover", "active", "focus", "disabled", "loading", "skeleton", "empty", "error", "warning", "success", "offline", "permission-denied", "partial-data", "syncing", "unsaved-changes", "ai-generating" ], "localization": [ "Copy budgets assume +35% expansion for DE/FR translations.", "RTL mirror verified for AR/HE (icons flipped, numerals kept LTR).", "Dates/times/currencies use Intl APIs, never hardcoded formats.", "Touch targets ≥ 44px; keyboard tab order matches visual order.", "Density modes: comfortable (default), compact (power users), spacious (accessibility)." ], "uniqueness_audit": { "app_specific_decisions": [ "Machine-room register motif (ledger rows, not binder tabs)", "Gap-row-cites-clause-or-explicit-gap copy discipline — never invented data" ], "cliches_avoided": [ "Elevator-shaft stock photography", "Green-check compliance theatre", "Penalty-scare banners" ], "scale_notes": "New blueprints inherit the network shell but MUST declare their own signature element, accent role, and anti-reference before they can be marked ready. Enforced by the release gate." }, "tokens": { "brand": "212 24% 20%", "brand-fg": "40 20% 96%", "surface": "35 18% 96%", "ink": "215 22% 13%", "muted": "215 8% 43%", "accent": "38 78% 48%" }, "type": { "display": "'Fraunces', ui-serif, serif", "body": "'Inter', system-ui, sans-serif", "fonts_url": "https://fonts.googleapis.com/css2?family=Fraunces:opsz,wght@9..144,500;9..144,700&family=Inter:wght@400;500;600&display=swap" }, "signature": { "motif": "Machine-room register rows · AHJ chip", "render": "ledger-rows" } }, "seo": { "slug": "elevator-mcp-completeness-pack-engine", "archetype": "regulator-fluent authority site", "archetype_impact": "Search fit is a regulator-fluent authority site. That means depth over breadth: each page cites the specific ASME A17.1 §8.6 clause or AHJ rule it addresses, and thin variants are refused.", "authority_dna": { "site_archetype": "regulator-fluent authority site", "monetization_model": "B2B lead → validation call → paid Completeness Pack engagement (not ad revenue; not affiliate).", "main_search_intents": [ "informational", "commercial" ], "topical_authority_opportunity": "Own the \"ASME A17.1 §8.6 elevator MCP\" topic cluster by covering the entire owner-side duty — the written equipment-specific MCP, on-site accessibility instructions, 5-year maintenance/callback/FEO-test record retention (§8.6.1.4), gap matrices, vendor MCP custody at vendor change, and AHJ-specific rules (Colorado 7 CCR 1101-8, Fairfax County Elevator Program) — better than any single-post competitor.", "local_seo_opportunity": "Not justified as city pages. Buyers search by AHJ/regulator (Colorado OPS, Fairfax County Elevator Program), not by city; that AHJ-scoped content belongs in the rule library, not as location doorway pages.", "global_national_opportunity": "National (US-first) with two named beachhead AHJs (Colorado Front Range; Fairfax County VA / Northern Virginia). Expand the AHJ rule library market-by-market as new jurisdictions are added — not a global/international play.", "easiest_ranking_path": "Long-tail, clause-specific how-to and edge-case queries (\"MCP walks with vendor,\" \"gap matrix worked example,\" \"generic MCP red flags\") where the SERP is dominated by elevator-consultant marketing pages, OEM vendor boilerplate, or aged SaaS-tracker blogs.", "hardest_ranking_path": "Head terms like \"elevator compliance software\" — dominated by aged SaaS vendor domains (KomplyOS, AuditMate, Elevator App, BRYCER). Defer until authority is established.", "trust_credibility_requirements": [ "Named human authors with role + credentials", "ASME/AHJ statute and rule citations on every claim", "Last-reviewed date + change log on regulatory pages", "Direct links to primary AHJ/code source (not aggregators)", "Licensed elevator consultant / QEI reviewer attribution on YMYL pages" ], "ymyl": true, "expert_review_needed": true, "site_structure": "Authority hub + narrow high-intent service page + linkable evidence assets. Not a directory. Not a marketplace.", "seo_moat": "always-current ASME A17.1 §8.6 + AHJ-mapped pages (Colorado 7 CCR 1101-8, Fairfax County Elevator Program) with change-log timestamps tracking the Colorado rule update effective Jan 1, 2026" }, "search_market": { "primary_markets": [ "ASME A17.1 §8.6 elevator MCP completeness workflow", "Colorado 7 CCR 1101-8 conveyance MCP compliance" ], "secondary_markets": [ "elevator maintenance-records inspection-readiness", "vendor MCP custody documentation", "elevator MCP gap matrix" ], "low_competition_subtopics": [ "MCP walks with vendor edge cases", "missing FEO-test record handling", "elevator MCP for multifamily portfolios" ], "high_commercial_intent": [ "elevator MCP completeness pack service", "done-for-you elevator MCP documentation", "pre-inspection elevator MCP rush review", "elevator compliance documentation consultant" ], "informational": [ "what is an elevator Maintenance Control Program", "ASME A17.1 §8.6 explained", "what happens if an elevator MCP is missing" ], "local_intent": [ "[PLACEHOLDER] owner to complete" ], "transactional": [ "MCP completeness pack pricing", "book an elevator MCP gap scan", "elevator MCP compliance service demo" ], "comparison": [ "completeness pack vs elevator consulting firm", "completeness pack vs elevator compliance SaaS tracker", "MCPVault Clear vs DeviceClear vs ClosePack Clear" ], "problem_solution": [ "how to survive an elevator inspection with missing records", "MCP walked away with the old vendor — what to do", "red-tag elevator recovery documentation" ], "near_me": [ "[PLACEHOLDER] owner to complete" ], "long_tail": [ "ASME A17.1 §8.6.1.4 five-year maintenance record retention explained", "Colorado 7 CCR 1101-8 missing MCP inspection failure", "Fairfax County elevator MCP on-site accessibility requirement" ], "questions": [ "what does an elevator MCP need to include?", "who owns the elevator MCP when vendors change?", "how long must elevator maintenance records be retained?", "how long does an MCP Completeness Pack take?" ], "emerging": [ "AI-assisted elevator MCP gap scoring", "automated vendor chase-letter drafting for elevator records" ], "seasonal": [ "Colorado 7 CCR 1101-8 rule effective January 1, 2026", "annual pre-inspection MCP re-scan season" ], "underserved_serps": [ "MCP walks with vendor edge cases", "missing FEO-test record handling" ], "weak_serps": [ "elevator MCP records checklist", "ASME A17.1 §8.6 retention requirements" ], "forum_dominated_serps": [ "what happens if an elevator fails inspection for missing MCP", "elevator red-tag removal process" ], "winnable_authoritative_serps": [ "elevator MCP completeness definitive guide", "ASME A17.1 §8.6 MCP evidence requirements" ], "avoid_initially": [ "elevator compliance software", "elevator maintenance tracking platform", "best elevator compliance tools" ], "easy_wins": [ "MCP walks with vendor edge cases", "elevator MCP records checklist", "Colorado 7 CCR 1101-8 rule update summary" ], "moderate": [ "elevator MCP completeness definitive guide", "elevator maintenance-records inspection-readiness" ], "long_term_plays": [ "elevator compliance software", "portfolio MCP registers for large owners" ], "do_not_pursue": [ "generic \"how to start a compliance business\" content", "celebrity or trend-jacking posts", "AI-generated listicles" ] }, "keyword_clusters": [ { "primary": "ASME A17.1 §8.6 MCP completeness evidence requirements", "related": [ "audit-ready elevator MCP records", "MCP evidence checklist" ], "intent": "commercial", "user_problem": "An inspection, insurer, or lender diligence request is coming and MCP/records are scattered across vendor files", "funnel": "BOFU", "business_value": "high", "ranking_difficulty": "medium", "conversion_potential": "high", "content_effort": "medium", "serp_weakness": "SERP dominated by elevator-consultant marketing pages and generic OEM boilerplate", "local_relevance": "low", "global_relevance": "high", "suggested_page_type": "Pillar / evidence guide", "reason": "High buyer intent + weak SERP + our unique released-pack proof", "priority_score": 17, "priority": "P0", "bucket": "easy-win" }, { "primary": "completeness pack vs elevator consulting firm vs SaaS tracker", "related": [ "elevator compliance service alternatives", "elevator MCP SaaS comparison" ], "intent": "commercial", "user_problem": "Evaluating a bespoke consulting engagement or a dashboard nobody will operate vs a documentation service", "funnel": "BOFU", "business_value": "high", "ranking_difficulty": "medium", "conversion_potential": "high", "content_effort": "medium", "serp_weakness": "Weak — mostly self-serving SaaS vendor pages and consultant firm sites", "local_relevance": "low", "global_relevance": "high", "suggested_page_type": "Comparison page (honest, evidence-based)", "reason": "Late-funnel intent with weak competition", "priority_score": 16, "priority": "P0", "bucket": "easy-win" }, { "primary": "MCPVault Clear vs DeviceClear vs ClosePack Clear", "related": [ "elevator MCP pack vs AHJ certificate filing", "elevator MCP vs sprinkler deficiency closure pack" ], "intent": "commercial", "user_problem": "A buyer researching one AINBIS compliance-pack business lands on the wrong one and needs to route to the right outcome", "funnel": "MOFU", "business_value": "medium", "ranking_difficulty": "low", "conversion_potential": "medium", "content_effort": "low", "serp_weakness": "Thin — essentially unclaimed branded/disambiguation query", "local_relevance": "low", "global_relevance": "high", "suggested_page_type": "Comparison page (disambiguation)", "reason": "Prevents brand confusion and misrouted leads; cheap to rank; explicitly required by risk register", "priority_score": 15, "priority": "P0", "bucket": "easy-win" }, { "primary": "elevator MCP records checklist", "related": [ "ASME A17.1 §8.6 owner checklist", "elevator MCP audit checklist" ], "intent": "informational", "user_problem": "Wants a concrete one-page artifact covering the records an AHJ inspector asks for", "funnel": "MOFU", "business_value": "medium", "ranking_difficulty": "low", "conversion_potential": "medium", "content_effort": "low", "serp_weakness": "Weak — thin listicles and vendor PDFs", "local_relevance": "low", "global_relevance": "high", "suggested_page_type": "Resource / lead magnet page", "reason": "Easy win + strong lead-magnet fit", "priority_score": 14, "priority": "P0", "bucket": "easy-win" }, { "primary": "Colorado 7 CCR 1101-8 rule update and Jan 2026 deadlines", "related": [ "Colorado eDocket 2025-00489", "Colorado conveyance MCP inspection-failure rule" ], "intent": "informational", "user_problem": "Needs authoritative detail on the Colorado rule update effective January 1, 2026 and what it means for MCP completeness", "funnel": "TOFU", "business_value": "medium", "ranking_difficulty": "low", "conversion_potential": "medium", "content_effort": "low", "serp_weakness": "Weak — outdated pages ranking", "local_relevance": "medium", "global_relevance": "medium", "suggested_page_type": "Data table / rule-change page", "reason": "Recurring beachhead-AHJ traffic + easy freshness moat", "priority_score": 14, "priority": "P0", "bucket": "easy-win" }, { "primary": "MCP walks with vendor: custody edge cases", "related": [ "vendor change elevator MCP custody", "no MCP exists escalation", "Fairfax red-tag MCP custody guidance" ], "intent": "informational", "user_problem": "Facing a scenario the standard guides do not cover (vendor switch, no MCP ever authored, contested code interpretation)", "funnel": "MOFU", "business_value": "medium", "ranking_difficulty": "low", "conversion_potential": "medium", "content_effort": "medium", "serp_weakness": "SERP is thin and forum-heavy", "local_relevance": "low", "global_relevance": "high", "suggested_page_type": "How-to cluster page", "reason": "Easy win + high assist to product page", "priority_score": 13, "priority": "P0", "bucket": "easy-win" }, { "primary": "elevator compliance software", "related": [ "elevator compliance platform", "best elevator compliance tracking tools" ], "intent": "commercial", "user_problem": "Ready to buy a tracking tool", "funnel": "BOFU", "business_value": "high", "ranking_difficulty": "high", "conversion_potential": "high", "content_effort": "high", "serp_weakness": "Strong — aged SaaS vendor domains (KomplyOS, AuditMate, Elevator App, BRYCER)", "local_relevance": "low", "global_relevance": "high", "suggested_page_type": "Product page (defer)", "reason": "Long-term play — do not chase before authority is built", "priority_score": 9, "priority": "P1", "bucket": "medium" }, { "primary": "ASME A17.1 §8.6 elevator MCP definitive guide", "related": [ "what is an elevator Maintenance Control Program", "who is responsible for the elevator MCP" ], "intent": "informational", "user_problem": "Just inherited elevator/conveyance compliance responsibility and needs to orient", "funnel": "TOFU", "business_value": "medium", "ranking_difficulty": "medium", "conversion_potential": "low", "content_effort": "high", "serp_weakness": "Moderate — mostly generic OEM and consultant vendor content", "local_relevance": "low", "global_relevance": "high", "suggested_page_type": "Pillar page", "reason": "Anchors topical authority for the whole cluster", "priority_score": 7, "priority": "P1", "bucket": "medium" } ], "topical_authority_map": { "core_topics": [ "ASME A17.1 §8.6 elevator MCP — definitive guide", "MCP evidence & inspection-readiness", "AHJ rule library (ASME §8.6, Colorado 7 CCR 1101-8, Fairfax County Elevator Program)" ], "pillars": [ { "name": "ASME A17.1 §8.6 elevator MCP — definitive guide", "core_intent": "informational", "audience": "facilities directors, property managers, and risk/ownership asset managers", "conversion_goal": "Owner checklist download → later validation call", "supporting_pages": [ "The equipment-specific MCP requirement explained", "5-year maintenance-record retention under §8.6.1.4", "MCP custody at vendor change (edge cases)", "ASME A17.1 §8.6 FAQs" ], "internal_links": [ "/product", "/rules/asme/a17-1-8-6/", "/resources/checklist" ], "schema": [ "Article", "BreadcrumbList", "FAQPage (where genuine)" ], "evidence_needed": [ "Named reviewer", "Primary-source citations", "Worked example" ], "local_variants": [ "[PLACEHOLDER] owner to complete" ], "national_variants": [ "US-national (default)" ] }, { "name": "MCP evidence & inspection-readiness", "core_intent": "commercial", "audience": "facilities directors, property managers, and risk/ownership asset managers", "conversion_goal": "Book validation call", "supporting_pages": [ "ASME A17.1 §8.6 MCP completeness evidence requirements", "Elevator MCP records audit checklist", "Common MCP evidence gaps (the generic, non-equipment-specific MCP)" ], "internal_links": [ "/product", "/guides/elevator-mcp/", "/resources/evidence-checklist" ], "schema": [ "Article", "FAQPage", "BreadcrumbList", "HowTo (only for real workflow)" ], "evidence_needed": [ "Worked evidence artifact", "AHJ citation", "Reviewer credential" ], "local_variants": [], "national_variants": [ "US-national" ] }, { "name": "AHJ rule library", "core_intent": "informational", "audience": "facilities directors, property managers, and risk/ownership asset managers", "conversion_goal": "Assisted conversion via internal linking", "supporting_pages": [ "ASME A17.1 §8.6 — MCP requirement, rules and citations", "ASME A17.1 §8.6.1.4 — 5-year record retention, rules and citations", "Colorado 7 CCR 1101-8 — conveyance MCP definition and inspection-failure rule", "Colorado eDocket 2025-00489 rule update (eff. Jan 1, 2026)", "Fairfax County Elevator Program — owner/contractor shared MCP responsibility", "Fairfax County 5-year maintenance-records acknowledgment form", "A17.1-2025 networked-control cybersecurity module (AHJ-conditional only)" ], "internal_links": [ "/guides/elevator-mcp/", "/product" ], "schema": [ "Article", "BreadcrumbList" ], "evidence_needed": [ "Primary source link", "Visited-on date", "Reviewer sign-off" ], "local_variants": [], "national_variants": [ "US-national" ] } ], "supporting_page_types": [ "definition / glossary", "how-to workflow", "edge-case handling", "rule-change explainer", "worked example", "FAQ", "comparison (only when honest)", "case study (only with permission)", "evidence artifact / template", "regulator update log" ] }, "site_architecture": { "homepage_strategy": "Above-the-fold: one-sentence purpose + primary CTA (validation call). Below: 3 problem-cards linking to pillars, 1 evidence-asset teaser, 1 authority statement with named reviewer.", "main_nav": [ "Product", "How it works", "Pillars", "Resources", "About", "Contact" ], "footer_nav": [ "Editorial policy", "Contact", "Privacy", "Terms", "Sitemap", "Changelog" ], "hubs": [ { "name": "Product / service", "url": "/product", "purpose": "High-intent commercial page" }, { "name": "Guides pillar", "url": "/guides", "purpose": "Topical authority hub" }, { "name": "Rule library", "url": "/rules", "purpose": "Entity/regulation reference" }, { "name": "Resources", "url": "/resources", "purpose": "Linkable assets (templates, checklists)" }, { "name": "Changelog", "url": "/changelog", "purpose": "Freshness + trust signal" } ], "url_patterns": [ "/product", "/guides/[topic]/", "/guides/[topic]/[subtopic]/", "/rules/[regulator]/[rule]/", "/resources/[asset]/", "/compare/[a]-vs-[b]/", "/glossary/[term]/" ], "avoid_url_patterns": [ "/[city]/[service]/ (no local intent for this buyer)", "/blog/[year]/[month]/[slug]/ (dated slugs decay CTR)", "/tag/[tag]/ (thin archive pages)", "Any duplicate /service/ and /solutions/ trees" ] }, "global_national": { "national_clusters": [ "ASME A17.1 §8.6 elevator MCP — definitive guide", "MCP completeness evidence workflow", "Colorado 7 CCR 1101-8 conveyance MCP rule", "elevator maintenance-records inspection-readiness" ], "linkable_assets": [ "One-page ASME A17.1 §8.6 owner MCP checklist (downloadable, gated by email is OK)", "AHJ rule-to-record mapping table (Colorado + Fairfax County, HTML + PDF)", "Change-log / AHJ rule update tracker (incl. Colorado eff. Jan 1, 2026)", "Worked gap-matrix examples (redacted, fixture data labeled illustrative)" ], "original_research_ideas": [ "Annual multi-portfolio MCP completeness readiness benchmark (survey of ~50 property managers)", "Evidence completeness index: share of vendor-supplied MCPs missing equipment-specific detail (anonymized intake data)", "AHJ expansion variation index (Colorado vs Fairfax County vs future AHJs)" ], "international_needed": false, "international_notes": "Not needed. US-first. Do not build hreflang variants." }, "local_seo": { "justified": false, "reason": "Buyers search by AHJ/regulator (Colorado OPS, Fairfax County Elevator Program), not by city. City-level local pages would be doorway pages; AHJ jurisdiction content belongs in the rule library instead.", "gbp_categories_primary": [ "[PLACEHOLDER] owner to complete" ], "gbp_categories_secondary": [ "[PLACEHOLDER] owner to complete" ], "location_page_rules": [ "Do not build city-level location pages for this blueprint.", "AHJ jurisdiction pages (Colorado, Fairfax County) live under /rules/, not as location doorway pages." ], "citations": [ "[PLACEHOLDER] owner to complete" ], "review_strategy": "Reviews are not a Local ranking factor here; use case studies and reviewer credibility instead.", "local_schema": [ "[PLACEHOLDER] owner to complete" ] }, "programmatic": { "recommended": false, "reason": "Programmatic pages almost always become doorway pages in regulated niches. Prefer a small number of deeply-researched pages per AHJ.", "rules": [ "Only allowed for genuinely differentiated data (e.g., an AHJ-by-AHJ rule table where each jurisdiction truly differs)", "Every programmatic page must include: unique data field + unique regulatory content + human review before publish", "noindex until minimum quality threshold met", "Rel=canonical to the pillar when a page falls below threshold" ], "per_page_requirements": [ "≥1 unique data point not present on sibling pages", "≥1 unique paragraph of human-written analysis", "Verified last-reviewed date" ], "quality_gates": [ "Editorial review before indexation", "Quarterly re-review or noindex", "Automated thin-content detector (<300 words unique) blocks publish" ] }, "page_templates": [ { "page_type": "Homepage", "purpose": "State the offer + route to validation call.", "target_intent": "commercial", "url_pattern": "/", "h1_pattern": "[One-sentence purpose]", "title_pattern": "[Brand] — [One-sentence purpose]", "meta_description_pattern": "One sentence outcome + CTA verb. ≤ 155 chars.", "above_the_fold": [ "H1", "Sub-headline (audience + outcome)", "Primary CTA (validation call)", "1 trust chip (reviewer / cite)" ], "outline": [ "Problem framing", "3 pillar cards", "Evidence asset teaser", "Named reviewer statement", "Contact" ], "internal_links": [ "/product", "/guides", "/resources", "/about" ], "conversion_elements": [ "Calendar CTA", "Checklist download secondary" ], "schema": [ "Organization", "WebSite", "SearchAction" ], "trust_elements": [ "Reviewer name", "Editorial policy link" ], "media": [ "Original workflow diagram (SVG)" ], "faq_opportunities": [ "Top 3 buyer questions" ], "cta_strategy": "Above-the-fold soft + end-of-page primary", "quality_requirements": [ "Loads < 2.5s LCP", "Named reviewer visible" ], "anti_thin_rules": [ "No stock hero", "No generic 'we help X do Y' filler" ] }, { "page_type": "Pillar page", "purpose": "Anchor a topic cluster with a definitive explanation.", "target_intent": "informational", "url_pattern": "/guides/[topic]/", "h1_pattern": "[Topic] — Definitive Guide", "title_pattern": "[Topic] — Definitive Guide | [Brand]", "meta_description_pattern": "Definition + what the reader will learn + reviewer credential.", "above_the_fold": [ "H1", "40–60 word definition block", "TOC", "Last-reviewed date + reviewer" ], "outline": [ "Definition", "Who this applies to", "Workflow", "Rules & citations", "Edge cases", "FAQs", "Related pages" ], "internal_links": [ "Cluster sub-pages", "Rule library", "Product" ], "conversion_elements": [ "End-of-page checklist download", "Sidebar validation call CTA" ], "schema": [ "Article", "BreadcrumbList", "FAQPage (only real FAQs)" ], "trust_elements": [ "Named author + reviewer", "Primary source cites" ], "media": [ "Original diagrams", "Rule comparison table" ], "faq_opportunities": [ "Real questions from practitioners" ], "cta_strategy": "Assist conversion via internal link to product; primary CTA end-of-page.", "quality_requirements": [ "≥ 1500 words unique", "≥ 3 primary sources cited", "Reviewer credential visible" ], "anti_thin_rules": [ "No listicles padded with keyword variants", "No AI-generated body" ] }, { "page_type": "How-to cluster page", "purpose": "Answer a specific workflow question inside a cluster.", "target_intent": "informational", "url_pattern": "/guides/[topic]/[subtopic]/", "h1_pattern": "[Specific action or question]", "title_pattern": "[Specific action] — [Pillar topic] | [Brand]", "meta_description_pattern": "Concrete outcome + who it applies to + one caveat.", "above_the_fold": [ "H1", "Direct answer paragraph", "Numbered steps preview" ], "outline": [ "Direct answer", "Steps", "Edge cases", "Common mistakes", "Related pages" ], "internal_links": [ "Pillar page", "Sibling clusters", "Product" ], "conversion_elements": [ "End-of-page checklist download", "Related tool link" ], "schema": [ "Article", "HowTo (only if real workflow)", "BreadcrumbList" ], "trust_elements": [ "Named author", "Reviewer for YMYL" ], "media": [ "Screenshots of the actual workflow" ], "faq_opportunities": [ "Follow-up questions" ], "cta_strategy": "Contextual link to product mid-page; primary CTA end-of-page.", "quality_requirements": [ "Unique steps not duplicated from pillar", "Reviewer date visible" ], "anti_thin_rules": [ "No spun variants of the pillar" ] }, { "page_type": "Product / service page", "purpose": "Convert commercial intent.", "target_intent": "commercial", "url_pattern": "/product", "h1_pattern": "[Outcome-focused headline]", "title_pattern": "[Brand] — [Outcome]", "meta_description_pattern": "State the outcome + primary CTA verb.", "above_the_fold": [ "H1", "Sub-headline", "Primary CTA", "Trust chip" ], "outline": [ "Problem", "How we solve it", "Proof / worked example", "Objection handling", "FAQ", "CTA" ], "internal_links": [ "Case study", "Pillar guide", "Evidence checklist" ], "conversion_elements": [ "Calendar", "Secondary checklist" ], "schema": [ "Service or SoftwareApplication (whichever fits)", "Organization", "FAQPage" ], "trust_elements": [ "Named reviewer", "Primary-source cites", "Contact info" ], "media": [ "Screenshot of the actual gap-matrix workflow, not marketing composites" ], "faq_opportunities": [ "Buyer objections" ], "cta_strategy": "Above-the-fold + repeated end-of-page", "quality_requirements": [ "Unique per audience segment (no doorway variants)" ], "anti_thin_rules": [ "No thin '/services/X/' spin-offs of the same page" ] }, { "page_type": "Rule / regulation reference page", "purpose": "Serve as the site's citation-grade reference for a specific ASME clause or AHJ rule.", "target_intent": "informational", "url_pattern": "/rules/[regulator]/[rule]/", "h1_pattern": "[Regulator] — [Rule] explained", "title_pattern": "[Rule] — [Regulator] Requirements | [Brand]", "meta_description_pattern": "What the rule requires + last-reviewed date.", "above_the_fold": [ "H1", "Definition", "Last-reviewed + reviewer" ], "outline": [ "What the rule says", "Who it applies to", "Deadlines", "Evidence required", "Change log" ], "internal_links": [ "Pillar guide", "Product" ], "conversion_elements": [ "Subscribe to change-log", "Sidebar validation call" ], "schema": [ "Article", "BreadcrumbList" ], "trust_elements": [ "Primary-source link", "Visited-on date", "Reviewer credential" ], "media": [ "Rule comparison table" ], "faq_opportunities": [ "Real practitioner questions" ], "cta_strategy": "Assist conversion via internal link", "quality_requirements": [ "Primary source link required", "Quarterly re-review" ], "anti_thin_rules": [ "No auto-generated rule scraping without human review" ] }, { "page_type": "Comparison page", "purpose": "Serve genuine BOFU comparison intent, including disambiguation from sibling AINBIS businesses.", "target_intent": "commercial", "url_pattern": "/compare/[a]-vs-[b]/", "h1_pattern": "[A] vs [B] — Honest Comparison", "title_pattern": "[A] vs [B] | [Brand]", "meta_description_pattern": "Honest side-by-side + when to pick which.", "above_the_fold": [ "H1", "TL;DR verdict", "When-to-pick block" ], "outline": [ "Criteria", "Side-by-side table", "Where each wins", "Where each loses", "Recommendation" ], "internal_links": [ "Product", "Pillar guide" ], "conversion_elements": [ "Calendar CTA", "Evidence checklist" ], "schema": [ "Article", "BreadcrumbList" ], "trust_elements": [ "Disclose the reviewer's relationship to each option", "Never disparage sibling AINBIS businesses — state the different workflow/outcome only" ], "media": [ "Feature comparison table" ], "faq_opportunities": [ "'Which one do I need?' style" ], "cta_strategy": "End-of-page primary CTA to the fitting option", "quality_requirements": [ "Honest even when it hurts", "Disclose relationship" ], "anti_thin_rules": [ "No manufactured 'X vs Y' pages for every pair" ] }, { "page_type": "FAQ page", "purpose": "Aggregate genuine practitioner questions.", "target_intent": "informational", "url_pattern": "/faq", "h1_pattern": "FAQ", "title_pattern": "[Topic] FAQ | [Brand]", "meta_description_pattern": "Answers to the questions we hear most.", "above_the_fold": [ "H1", "Table of contents" ], "outline": [ "Grouped questions", "Each answer 40–120 words" ], "internal_links": [ "Relevant pillars and rule pages" ], "conversion_elements": [ "End-of-page CTA" ], "schema": [ "FAQPage (only for genuine FAQs visible on-page)" ], "trust_elements": [ "Named reviewer" ], "media": [], "faq_opportunities": [ "Real questions only — never invented" ], "cta_strategy": "Related-block links, not inline mid-answer", "quality_requirements": [ "No invented questions" ], "anti_thin_rules": [ "No 'is X the best' padding" ] }, { "page_type": "Glossary term page", "purpose": "Definition-grade authority for a single ubiquitous-language term.", "target_intent": "informational", "url_pattern": "/glossary/[term]/", "h1_pattern": "[Term]", "title_pattern": "[Term] — Definition | [Brand]", "meta_description_pattern": "Concise definition + who uses the term.", "above_the_fold": [ "H1", "40-word definition" ], "outline": [ "Definition", "Related terms", "Where it applies", "Common misuses" ], "internal_links": [ "Pillar", "Rule pages" ], "conversion_elements": [ "Sidebar related-tool link" ], "schema": [ "Article", "BreadcrumbList", "DefinedTerm" ], "trust_elements": [ "Cite the primary source of the definition" ], "media": [], "faq_opportunities": [], "cta_strategy": "Assist via internal link", "quality_requirements": [ "Never duplicate the pillar's intro" ], "anti_thin_rules": [ "No glossary spam" ] }, { "page_type": "Case study page", "purpose": "Concrete outcome-based proof.", "target_intent": "commercial", "url_pattern": "/case-studies/[slug]/", "h1_pattern": "[Outcome achieved for [customer type]]", "title_pattern": "Case Study — [Outcome] | [Brand]", "meta_description_pattern": "Concrete outcome + timeframe + method.", "above_the_fold": [ "H1", "Outcome metric", "Approved-for-publication chip" ], "outline": [ "Context", "Approach", "Outcome", "Reviewer quote" ], "internal_links": [ "Product", "Pillar guide" ], "conversion_elements": [ "End-of-page CTA" ], "schema": [ "Article", "BreadcrumbList" ], "trust_elements": [ "Named customer contact (with permission)" ], "media": [ "Redacted artifact screenshots" ], "faq_opportunities": [], "cta_strategy": "End-of-page primary CTA", "quality_requirements": [ "Written approval on file" ], "anti_thin_rules": [ "No fabricated case studies" ] } ], "on_page_rules": { "title_tag": "Pattern: [Primary keyword] — [Angle] | MCPVault Clear. ≤ 60 chars. Front-load the keyword. No clickbait.", "meta_description": "≤ 155 chars. State the specific outcome. Include a verb + a rule citation when applicable. No stuffing.", "headings": "One H1. H2s follow the workflow steps or the searcher's questions. H3s for edge cases. No decorative headings.", "intro": "First 100 words: define the topic in the searcher's language + name the specific ASME clause/AHJ + preview what the page delivers.", "snippet_targeting": "Add a 40–60 word definition block and a numbered how-to block near the top for featured snippet + AI overview eligibility.", "tables_lists": "Use tables for rule comparisons, deadlines, and retention thresholds. Lists for steps. Never use tables for layout.", "images": "Original diagrams/screenshots preferred. Descriptive alt text. WebP. Explicit width/height. Never AI slop stock art.", "internal_links": "Every page: ≥3 contextual links up to pillar, ≥2 to sibling cluster pages, ≥1 to a commercial page.", "external_citations": "Cite the primary source (ASME code text, AHJ PDF, eDocket) — not aggregators — with the visited-on date.", "author_attribution": "Named author + role + linked bio page. Reviewer for YMYL.", "freshness": "Last-reviewed date at top; change log at bottom for regulator pages; quarterly review cadence.", "cta_placement": "Above the fold (soft), mid-page (contextual to the section), end-of-page (primary).", "mobile": "Single-column, tap targets ≥44px, no interstitials, no autoplay video.", "avoid": [ "Keyword stuffing", "AI-generated body copy without human edit", "Doorway variants", "Unsupported superlatives ('best', 'top-rated') without evidence", "Meta descriptions duplicated across pages", "Marking up invisible content in schema" ] }, "entity_seo": { "main_entities": [ "ASME A17.1 §8.6", "Maintenance Control Program (MCP)", "Colorado 7 CCR 1101-8", "Fairfax County Elevator Program", "gap matrix", "vendor MCP custody", "5-year maintenance records", "conveyance" ], "related_entities": [ "QEI (Qualified Elevator Inspector)", "on-site accessibility instructions", "FEO test records", "hard gap / hard-fail", "vault index" ], "people": [ "Named practitioners (role-titles)", "Licensed elevator consultant / QEI reviewers", "AHJ officials referenced (Colorado OPS, Fairfax County Elevator Program)" ], "orgs": [ "Colorado Division of Oil and Public Safety (OPS)", "Fairfax County Elevator Program", "ASME (code body)", "AHJs (state and county conveyance regulators)" ], "tools": [ "AHJ rule library", "Gap-matrix worksheets", "Change-log tracker" ], "regulations": [ "ASME A17.1 §8.6 (MCP requirement)", "ASME A17.1 §8.6.1.4 (5-year record retention)", "Colorado 7 CCR 1101-8 (conveyance MCP rule)", "Colorado eDocket 2025-00489 (eff. Jan 1, 2026)", "Fairfax County Elevator Program policies", "A17.1-2025 networked-control cybersecurity module (AHJ-conditional)" ], "problems": [ "MCP completeness risk", "Inspection failure / red-tag risk", "MCP custody loss at vendor change", "Missing 5-year record retention", "Evidence gap across vendors" ], "solutions": [ "Completeness Pack workflow", "Portfolio Desk", "AHJ-mapped gap matrices", "Vendor chase kit" ], "processes": [ "Intake normalization", "AHJ checklist matching", "Gap scoring", "Analyst release", "Vendor chase", "Re-scan / vault update" ], "alternatives": [ "elevator consulting firms (Argon, KDA, TEC)", "OEM/service vendors (Otis, KONE, TKE, Schindler)", "SaaS trackers (KomplyOS, AuditMate, Elevator App, BRYCER)" ], "synonyms": [ "elevator maintenance control program records", "MCP completeness documentation", "elevator compliance binder", "audit-ready MCP" ] }, "schema_strategy": [ { "type": "Organization", "where": "Site-wide in head", "required_fields": [ "name", "url", "logo", "sameAs" ], "caution": "Keep in sync with visible About / contact." }, { "type": "WebSite + SearchAction", "where": "Homepage", "required_fields": [ "name", "url", "potentialAction" ], "caution": "Only if on-site search actually exists." }, { "type": "BreadcrumbList", "where": "All hub / cluster / rule / glossary pages", "required_fields": [ "itemListElement" ], "caution": "Order must match visible breadcrumbs." }, { "type": "Article", "where": "Guides, pillars, rule pages", "required_fields": [ "headline", "author", "datePublished", "dateModified" ], "caution": "Author must exist as a real person." }, { "type": "FAQPage", "where": "Genuine FAQ pages only", "required_fields": [ "mainEntity[]" ], "caution": "Only mark up FAQs visible on the page." }, { "type": "HowTo", "where": "Real step-by-step workflows only", "required_fields": [ "name", "step[]" ], "caution": "Google narrowed HowTo eligibility; use sparingly." }, { "type": "Person", "where": "Author bio pages", "required_fields": [ "name", "jobTitle", "sameAs" ], "caution": "Credentials must be real and verifiable." } ], "internal_linking": { "pillar_to_cluster": "Pillar links to every direct cluster page in a curated section (not a mega-menu dump).", "cluster_to_pillar": "Every cluster page links back to its pillar in the intro and in-context.", "cluster_to_cluster": "Link between sibling clusters only where the user's next question naturally leads there.", "service_to_location": "Not applicable.", "faq_to_commercial": "Answer the question first, then link to the commercial page in a 'related' block — never inline mid-answer.", "breadcrumbs": "Structured breadcrumbs on all guide, rule, and glossary pages.", "anchor_text_rules": [ "Descriptive — match the target page's H1 concept", "Vary phrasing across links to the same target", "Never exact-match keyword stuffing", "Anchor must make sense read aloud" ] }, "technical_seo": { "crawlability": "Flat depth (≤3 clicks from homepage). No orphan pages. HTML sitemap on /sitemap.", "indexability": "Index all real content. noindex utility pages, thank-you pages, and gated-asset landing pages.", "sitemaps": "XML sitemap generated at build time. Split by section if > 5k URLs.", "robots": "robots.txt allows all; disallow /admin/, /api/. Reference sitemap.", "canonicals": "Self-referencing canonical on every page. Filter/sort variants canonical to the base.", "pagination": "Prefer 'load more' or a single long page; if paginated, use rel=next/prev semantics via internal linking.", "faceted_nav": "Not applicable for this blueprint (no product catalog).", "duplicate_control": "One URL per topic. Consolidate before publishing new variants. No www/non-www split.", "redirects": "301 for permanent moves; audit chains monthly; never 302 for SEO redirects.", "core_web_vitals": "LCP ≤ 2.5s, INP ≤ 200ms, CLS ≤ 0.1. Test with real-user monitoring.", "mobile": "Mobile-first design. No tap-target failures. No horizontal scroll.", "accessibility": "WCAG AA. Semantic HTML. Landmarks. Focus states. Alt text.", "js_seo": "Content in the initial HTML. Client hydration for interactivity only.", "rendering": "Static generation preferred; SSR only where personalized. Never client-only for indexable pages.", "gsc_setup": "Verify both www and apex; submit sitemap; monitor Coverage and Enhancements weekly.", "analytics_setup": "GA4 + server-side event stream. Consent Mode v2. Event schema documented.", "rank_tracking": "Semrush or Ahrefs project set to US database; track pillar + top-20 clusters weekly." }, "eeat": { "author_bios": "Every content page has a named author with role, credentials, and a linked author page.", "expert_reviewers": "Every YMYL page reviewed by a named expert with disclosed credentials.", "editorial_policy": "Public /editorial-policy page: sourcing rules, review cadence, correction policy.", "fact_checking": "Every ASME clause/AHJ reference has a link + visited-on date; corrections dated and disclosed.", "credentials": [ "Licensed elevator consultant / QEI (Qualified Elevator Inspector) reviewer", "Relevant professional licensure where public" ], "citations": "Cite primary sources (ASME code text, AHJ PDF, eDocket). No citation of aggregator blogs.", "first_hand_proof": [ "Screenshots of the actual gap-matrix workflow", "Redacted worked examples", "Signed reviewer statement" ], "update_cadence": "Regulatory pages reviewed quarterly; commercial pages reviewed twice yearly.", "monetization_disclosure": "Public disclosure that leads convert to paid engagements; no undisclosed affiliate content.", "ymyl_notes": "This is YMYL. Language stays cautious (\"may\", \"depends on facts\"); documentation-readiness support only — never claims to inspect elevators, certify conveyances safe, or guarantee inspection pass; the owner remains the responsible party and physical maintenance stays with licensed elevator contractors; disclaimer near every CTA." }, "ai_search": { "principles": [ "Answer the exact question in the first paragraph", "Provide a 40–60 word extractable definition near the top", "Structured lists and tables for facts", "Cite named primary sources", "Author + reviewer names on-page" ], "tactics": [ "FAQPage schema for genuine FAQs (not stuffed)", "HowTo schema for real workflow pages", "Consistent entity naming across the site", "Concise summaries at the top of long guides" ], "do_not": [ "Write pages targeting AI systems instead of humans", "Insert hidden 'AI-only' content", "Create bespoke llms.txt / manifests that bypass normal quality", "Mass-generate answers to invented questions" ] }, "conversion": { "primary_cta": "Start a pack run from your most recent MCP and vendor logs (or book a validation call).", "secondary_cta": "Run the free MCP Gap Scan / download the ASME A17.1 §8.6 owner MCP checklist (email capture).", "lead_magnets": [ "Free MCP Gap Scan (human-reviewed, scored checklist preview — not a certificate)", "One-page ASME A17.1 §8.6 owner MCP custody checklist (PDF)", "Quarterly AHJ rule change-log subscription (Colorado + Fairfax County)" ], "trust_elements": [ "Named reviewer + credentials", "AHJ/ASME citations visible on-page", "Change-log timestamps", "Contact + address in footer" ], "per_page_paths": [ { "page_type": "Homepage", "path": "Hero CTA → validation call. Secondary → guides pillar." }, { "page_type": "Pillar", "path": "TOC → deep sub-pages. End-of-page → validation call." }, { "page_type": "Cluster / how-to", "path": "In-content 'related tool' link → product. End-of-page → checklist download." }, { "page_type": "Product / service", "path": "Above-the-fold CTA → calendar. Objection-handling block → FAQ." }, { "page_type": "Rule page", "path": "Sidebar → related workflow (product). Bottom → subscribe to change-log." } ], "tracking": "GA4 events: cta_click, checklist_download, calendar_book. Server-side dedupe. Weekly funnel review." }, "link_earning": { "digital_pr_ideas": [ "Annual \"elevator MCP completeness readiness\" benchmark report", "Evidence completeness index with a shareable result page", "AHJ rule-change tracker with an RSS feed" ], "original_research": [ "Small property-manager survey (n≥30) once per year", "AHJ-by-AHJ rule variation index (Colorado vs Fairfax County vs future AHJs)" ], "directories": [ "G2 / Capterra category pages (facilities compliance)", "Property-management association member lists", "AHJ resource pages when eligible" ], "expert_contributions": [ "HARO / Qwoted / Featured expert responses", "Bylined articles in property-management trade press", "Podcast interviews with facilities/risk practitioners" ], "partnerships": [ "Elevator-consultant referral partnerships (non-competing, authorship-only scope)", "Co-authored guides with adjacent (non-competing) vendors" ], "avoid": [ "Paid link schemes", "PBNs", "Mass guest posting", "Fake reviews", "Reciprocal link exchanges" ] }, "roadmap_90d": [ { "phase": "Days 0–30: Foundation", "goal": "Establish trust + ship product page + first pillar.", "pages": [ "Homepage", "Product page", "Pillar: ASME A17.1 §8.6 elevator MCP — definitive guide", "About + reviewer bio (role-titles)", "Editorial policy", "Contact" ], "keywords_targeted": [ "ASME A17.1 §8.6 elevator MCP", "what is an elevator Maintenance Control Program" ], "why_first": "Without a trust surface + a real product page, everything else is unmoored.", "difficulty": "medium", "business_value": "high", "required_assets": [ "Reviewer bio", "Editorial policy", "One workflow diagram" ], "internal_links": [ "Homepage ↔ Product ↔ Pillar" ], "conversion_goal": "First validation calls booked" }, { "phase": "Days 31–60: Topical authority core", "goal": "Publish the first cluster of 5–7 supporting pages under the pillar + evidence checklist lead magnet.", "pages": [ "MCP walks with vendor: custody edge cases", "Elevator MCP records checklist (lead magnet)", "ASME A17.1 §8.6 FAQs", "5-year maintenance-record retention explained", "MCPVault Clear vs DeviceClear vs ClosePack Clear" ], "keywords_targeted": [ "MCP walks with vendor", "elevator MCP records checklist", "who owns the elevator MCP when vendors change" ], "why_first": "Easy-win SERPs that assist conversion to the product page and resolve sibling-brand confusion early.", "difficulty": "low", "business_value": "medium", "required_assets": [ "Checklist PDF", "Rule table" ], "internal_links": [ "All clusters ↔ pillar ↔ product" ], "conversion_goal": "Checklist downloads + assisted conversions" }, { "phase": "Days 61–90: Reference & freshness", "goal": "Ship the AHJ rule library + first change-log post + first comparison page.", "pages": [ "Rule page: ASME A17.1 §8.6", "Rule page: Colorado 7 CCR 1101-8", "Rule page: Fairfax County Elevator Program", "Comparison: completeness pack vs elevator consulting firm vs SaaS tracker", "Q1 AHJ rule change-log" ], "keywords_targeted": [ "ASME A17.1 8.6", "Colorado 7 CCR 1101-8", "Fairfax County elevator MCP" ], "why_first": "Reference pages compound in authority; change-log establishes freshness signal ahead of the Jan 2026 Colorado effective date.", "difficulty": "medium", "business_value": "medium", "required_assets": [ "Primary-source citations", "Reviewer sign-off" ], "internal_links": [ "Rule pages ↔ pillar ↔ product; comparison → product" ], "conversion_goal": "BOFU comparison conversions" } ], "roadmap_12m": [ { "phase": "Months 4–6: Linkable assets", "goal": "Ship the annual benchmark, the evidence-completeness index, and the AHJ variation index.", "pages": [ "Annual elevator MCP completeness readiness benchmark", "Evidence completeness index", "AHJ expansion variation index" ], "keywords_targeted": [ "elevator MCP completeness benchmark", "elevator compliance documentation cost", "AHJ rule variation comparison" ], "why_first": "Linkable assets drive referring domains and topical authority signals.", "difficulty": "medium", "business_value": "high", "required_assets": [ "Survey data", "Named methodology", "Reviewer sign-off" ], "internal_links": [ "From every pillar + product" ], "conversion_goal": "Benchmark → validation call handoff" }, { "phase": "Months 7–9: Depth + freshness cadence", "goal": "Expand each pillar with 3 more cluster pages + quarterly AHJ change-log.", "pages": [ "Additional cluster pages (per pillar)", "Q3 AHJ rule change-log", "First case study (with permission)" ], "keywords_targeted": [ "Long-tail cluster expansions" ], "why_first": "Compounding topical coverage + freshness moat.", "difficulty": "low", "business_value": "medium", "required_assets": [ "Customer approval for case study" ], "internal_links": [ "Sibling cluster interlinking" ], "conversion_goal": "Assisted conversions" }, { "phase": "Months 10–12: Scale + prune", "goal": "Consolidate weak pages, refresh top pages, expand into 1 adjacent AHJ only if authority is proven.", "pages": [ "Consolidation redirects", "Top-10 page refreshes", "Adjacent AHJ scoping (third jurisdiction)" ], "keywords_targeted": [ "Existing top-10 clusters" ], "why_first": "Optimization > net-new after a critical mass is reached.", "difficulty": "low", "business_value": "high", "required_assets": [ "Analytics review", "Consolidation plan" ], "internal_links": [ "Redirect audit" ], "conversion_goal": "CTR + conversion-rate lift" } ], "priority_pages": [ { "rank": 1, "page_title": "ASME A17.1 §8.6 MCP completeness evidence requirements", "slug": "/guides/asme-a17-1-8-6-mcp-completeness-evidence-requirements/", "page_type": "Pillar / evidence guide", "primary_keyword": "ASME A17.1 §8.6 MCP completeness evidence requirements", "secondary_keywords": [ "audit-ready elevator MCP records", "MCP evidence checklist" ], "intent": "commercial", "scope": "national", "funnel": "BOFU", "difficulty": "medium", "business_value": "high", "conversion_potential": "high", "required_proof": [ "Named reviewer", "Primary-source cites", "Worked example" ], "internal_links": [ "/guides/elevator-mcp/", "/product", "/rules/asme/a17-1-8-6/" ], "schema": [ "Article", "BreadcrumbList" ], "cta": "Book validation call", "production_priority": "P0", "why_opportunity": "High buyer intent + weak SERP + our unique released-pack proof" }, { "rank": 2, "page_title": "Completeness pack vs elevator consulting firm vs SaaS tracker", "slug": "/compare/completeness-pack-vs-consultant-vs-saas-tracker/", "page_type": "Comparison page (honest, evidence-based)", "primary_keyword": "completeness pack vs elevator consulting firm vs SaaS tracker", "secondary_keywords": [ "elevator compliance service alternatives", "elevator MCP SaaS comparison" ], "intent": "commercial", "scope": "national", "funnel": "BOFU", "difficulty": "medium", "business_value": "high", "conversion_potential": "high", "required_proof": [ "Named reviewer", "Primary-source cites", "Worked example" ], "internal_links": [ "/guides/elevator-mcp/", "/product", "/rules/asme/a17-1-8-6/" ], "schema": [ "Article", "BreadcrumbList" ], "cta": "Book validation call", "production_priority": "P0", "why_opportunity": "Late-funnel intent with weak competition" }, { "rank": 3, "page_title": "MCPVault Clear vs DeviceClear vs ClosePack Clear", "slug": "/compare/mcpvault-clear-vs-deviceclear-vs-closepack-clear/", "page_type": "Comparison page (disambiguation)", "primary_keyword": "MCPVault Clear vs DeviceClear vs ClosePack Clear", "secondary_keywords": [ "elevator MCP pack vs AHJ certificate filing", "elevator MCP vs sprinkler deficiency closure pack" ], "intent": "commercial", "scope": "national", "funnel": "MOFU", "difficulty": "low", "business_value": "medium", "conversion_potential": "medium", "required_proof": [ "Named reviewer", "Accurate, non-disparaging description of each sibling business's actual workflow" ], "internal_links": [ "/guides/elevator-mcp/", "/product" ], "schema": [ "Article", "BreadcrumbList" ], "cta": "Book validation call", "production_priority": "P0", "why_opportunity": "Prevents brand confusion and misrouted leads flagged in the risk register" }, { "rank": 4, "page_title": "Elevator MCP records checklist", "slug": "/guides/elevator-mcp-records-checklist/", "page_type": "Resource / lead magnet page", "primary_keyword": "elevator MCP records checklist", "secondary_keywords": [ "ASME A17.1 §8.6 owner checklist", "elevator MCP audit checklist" ], "intent": "informational", "scope": "national", "funnel": "MOFU", "difficulty": "low", "business_value": "medium", "conversion_potential": "medium", "required_proof": [ "Named reviewer", "Primary-source cites", "Worked example" ], "internal_links": [ "/guides/elevator-mcp/", "/product", "/rules/asme/a17-1-8-6/" ], "schema": [ "Article", "BreadcrumbList" ], "cta": "Download checklist", "production_priority": "P0", "why_opportunity": "Easy win + strong lead-magnet fit" }, { "rank": 5, "page_title": "Colorado 7 CCR 1101-8 rule update and Jan 2026 deadlines", "slug": "/guides/colorado-7-ccr-1101-8-rule-update/", "page_type": "Data table / rule-change page", "primary_keyword": "Colorado 7 CCR 1101-8 rule update Jan 2026", "secondary_keywords": [ "Colorado eDocket 2025-00489", "Colorado conveyance MCP inspection-failure rule" ], "intent": "informational", "scope": "national", "funnel": "TOFU", "difficulty": "low", "business_value": "medium", "conversion_potential": "medium", "required_proof": [ "Named reviewer", "Primary-source cites", "Worked example" ], "internal_links": [ "/guides/elevator-mcp/", "/product", "/rules/colorado/7-ccr-1101-8/" ], "schema": [ "Article", "BreadcrumbList" ], "cta": "Download checklist", "production_priority": "P0", "why_opportunity": "Recurring beachhead-AHJ traffic + easy freshness moat" }, { "rank": 6, "page_title": "MCP walks with vendor: custody edge cases", "slug": "/guides/mcp-walks-with-vendor-custody-edge-cases/", "page_type": "How-to cluster page", "primary_keyword": "MCP walks with vendor custody edge cases", "secondary_keywords": [ "vendor change elevator MCP custody", "no MCP exists escalation", "Fairfax red-tag MCP custody guidance" ], "intent": "informational", "scope": "national", "funnel": "MOFU", "difficulty": "low", "business_value": "medium", "conversion_potential": "medium", "required_proof": [ "Named reviewer", "Primary-source cites", "Worked example" ], "internal_links": [ "/guides/elevator-mcp/", "/product", "/rules/fairfax-county/elevator-program/" ], "schema": [ "Article", "BreadcrumbList" ], "cta": "Download checklist", "production_priority": "P0", "why_opportunity": "Easy win + high assist to product page" }, { "rank": 7, "page_title": "Elevator compliance software (deferred)", "slug": "/guides/elevator-compliance-software/", "page_type": "Product page (defer)", "primary_keyword": "elevator compliance software", "secondary_keywords": [ "elevator compliance platform", "best elevator compliance tracking tools" ], "intent": "commercial", "scope": "national", "funnel": "BOFU", "difficulty": "high", "business_value": "high", "conversion_potential": "high", "required_proof": [ "Named reviewer", "Primary-source cites", "Worked example" ], "internal_links": [ "/guides/elevator-mcp/", "/product" ], "schema": [ "Article", "BreadcrumbList" ], "cta": "Book validation call", "production_priority": "P1", "why_opportunity": "Long-term play — do not chase before authority is built" }, { "rank": 8, "page_title": "ASME A17.1 §8.6 elevator MCP — definitive guide", "slug": "/guides/asme-a17-1-8-6-elevator-mcp-definitive-guide/", "page_type": "Pillar page", "primary_keyword": "ASME A17.1 §8.6 elevator MCP definitive guide", "secondary_keywords": [ "what is an elevator Maintenance Control Program", "who is responsible for the elevator MCP" ], "intent": "informational", "scope": "national", "funnel": "TOFU", "difficulty": "medium", "business_value": "medium", "conversion_potential": "low", "required_proof": [ "Named reviewer", "Primary-source cites", "Worked example" ], "internal_links": [ "/guides/elevator-mcp/", "/product", "/rules/asme/a17-1-8-6/" ], "schema": [ "Article", "BreadcrumbList" ], "cta": "Download checklist", "production_priority": "P1", "why_opportunity": "Anchors topical authority for the whole cluster" } ], "competitor_gaps": { "typical_competitor_types": [ "elevator consulting firms (Argon, KDA, TEC, ATIS — project-priced)", "OEM/service vendors (Otis, KONE, TKE, Schindler)", "SaaS compliance trackers (KomplyOS, AuditMate, Elevator App, BRYCER)" ], "common_weaknesses": [ "Outdated AHJ/ASME citations", "Missing last-reviewed date", "No named author or reviewer", "Copy-paste content across AHJ / product variants", "No worked gap-matrix examples", "Thin FAQ padded with generic questions", "Poor mobile Core Web Vitals", "Customer left operating the dashboard with no released, dated deliverable" ], "how_to_beat_them": [ "Fresh citations with visited-on dates", "Named licensed-consultant/QEI reviewer + credentials visible", "Real, redacted worked gap-matrix examples", "Better structured tables for AHJ rule comparisons", "A released, dated Completeness Pack instead of a self-serve dashboard", "Faster + more accessible pages" ] }, "metrics": { "weekly": [ "GSC impressions/clicks by pillar", "Top-20 keyword position", "New indexed pages", "Core Web Vitals regressions" ], "monthly": [ "Organic sessions by hub", "Assisted conversions", "CTR by template", "Content decay list (positions dropped)", "Backlink net-new" ], "quarterly": [ "Pillar coverage audit", "AHJ rule-freshness audit", "Consolidation / prune list", "Conversion path funnel review" ], "annual": [ "Full topical authority audit", "Benchmark report refresh", "Editorial policy refresh" ] }, "risks": [ { "risk": "Thin content", "applies": true, "mitigation": "Minimum-word + reviewer-sign-off gate before publish." }, { "risk": "Duplicate content across AHJ/product variants", "applies": true, "mitigation": "One URL per topic; no auto-generated variants; canonical to pillar." }, { "risk": "Doorway city/location pages", "applies": true, "mitigation": "Local pages are refused for this vertical — buyers search by AHJ, not city." }, { "risk": "Keyword cannibalization", "applies": true, "mitigation": "Topic ownership map; kill or 301 the weaker duplicate." }, { "risk": "AI-generated body without human edit", "applies": true, "mitigation": "Editorial policy forbids it; reviewer sign-off required." }, { "risk": "Unsupported YMYL claims (implied guaranteed inspection pass)", "applies": true, "mitigation": "Cautious language + primary-source cites + reviewer credential; contract and page copy state documentation-readiness only, no pass guarantee." }, { "risk": "Bad schema (marking up invisible content)", "applies": true, "mitigation": "Schema linter in CI; only markup what is on-page." }, { "risk": "Link spam / paid link schemes", "applies": true, "mitigation": "Editorial link-earning only; documented policy." }, { "risk": "Review manipulation", "applies": false, "mitigation": "Post-engagement organic prompts only; no incentives; no gating negatives." }, { "risk": "Index bloat from tag/archive pages", "applies": true, "mitigation": "noindex utility archives; canonical to hub." }, { "risk": "Compliance risk in claims (mis-selling as engineering/QEI services)", "applies": true, "mitigation": "Licensing-boundary training; legal review of marketing claims; disclaimer near CTAs; escalation SOP to licensed consultant." }, { "risk": "Programmatic doorway pages", "applies": true, "mitigation": "Programmatic refused unless per-page uniqueness rules are met." }, { "risk": "DeviceClear / ClosePack Clear brand confusion", "applies": true, "mitigation": "Explicit, non-disparaging disambiguation comparison page; consistent 'Completeness Pack' / 'MCP' vocabulary never applied to the other businesses' artifacts." } ], "first_20_pages": [ "Homepage", "Product / service page", "About + reviewer bio (role-titles)", "Editorial policy", "Contact", "Privacy", "Pillar: ASME A17.1 §8.6 elevator MCP — definitive guide", "MCP walks with vendor: custody edge cases", "5-year maintenance-record retention under §8.6.1.4", "ASME A17.1 §8.6 FAQs", "Pillar: MCP evidence & inspection-readiness", "ASME A17.1 §8.6 MCP completeness evidence requirements", "Elevator MCP records audit checklist", "Colorado 7 CCR 1101-8 rule update and Jan 2026 deadlines", "Elevator MCP records checklist (lead magnet)", "Rule page: ASME A17.1 §8.6", "Rule page: Colorado 7 CCR 1101-8", "Rule page: Fairfax County Elevator Program", "Comparison: completeness pack vs elevator consulting firm vs SaaS tracker", "Comparison: MCPVault Clear vs DeviceClear vs ClosePack Clear" ], "first_10_tech_fixes": [ "XML sitemap generated at build", "robots.txt reviewed + sitemap referenced", "Self-referencing canonicals", "GSC + GA4 verified with server-side events", "Core Web Vitals baseline (LCP, INP, CLS)", "Structured breadcrumbs sitewide", "Author + editorial-policy pages published", "404 + 410 patterns defined", "Redirect audit (no chains)", "Semantic HTML + accessibility landmarks" ], "first_10_authority_actions": [ "Publish named licensed-consultant/QEI reviewer bio(s)", "Public editorial policy + correction policy", "Cite primary ASME/AHJ sources with visited-on dates", "Launch MCP records checklist lead magnet", "Pitch 3 HARO / Qwoted responses per week", "Publish 1 original data point / benchmark", "Reach out to 5 non-competing directories / associations", "Guest post on 1 property-management trade publication", "Podcast interview outreach (5 shows)", "Set up quarterly AHJ rule change-log post cadence" ], "final_recommendation": "Build a regulator-fluent authority site around \"ASME A17.1 §8.6 elevator MCP completeness\". Ship the first 20 pages in 90 days (product + pillar + AHJ rule library + evidence assets + sibling-brand disambiguation), then compound with quarterly AHJ rule-change posts and one annual benchmark. Refuse doorway pages, refuse mass AI content, treat named-reviewer (licensed elevator consultant / QEI, role-titled until owner facts close) + primary-source citations as non-negotiable, and never publish inspection-pass-rate claims without the physical-equipment/AHJ-discretion caveat.", "disclaimers": [ "All volume/difficulty/CPC labels are RELATIVE ESTIMATES (low/medium/high), not exact numbers. Validate with Semrush, Ahrefs, or Google Search Console before committing spend.", "This brief is deterministic per blueprint — it will not shift between renders. Any changes should be made in code, not in prompts.", "YMYL topic: language must stay cautious; documentation-readiness support only — nothing here is legal, engineering, or inspection-pass advice." ] }, "microsite": { "category": "Regulatory compliance", "shortTitle": "MCPVault Clear", "audience": "regional multifamily and mixed-use property managers with 3-40 elevator-equipped buildings (Colorado Front Range beachhead, Fairfax County VA secondary)", "problem": "Every elevator and escalator an owner operates needs a written, equipment-specific Maintenance Control Program under ASME A17.1 §8.6, with maintenance, callback, and FEO-test records retained roughly five years and viewable on-site. But the MCP usually lives with whichever vendor wrote it, most owners have never reviewed it, and Colorado and Fairfax County both now treat a missing or incomplete MCP as an inspection-failure condition — not a footnote.", "offer": "On MCPVault Clear, facilities coordinators stop guessing whether their elevators will pass a documentation review and start proving it. Upload the MCP, vendor logs, callback history, and machine-room photos; AI extracts and gap-scores the file against the adopted ASME A17.1 §8.6 / AHJ checklist, and a compliance analyst — with a licensed elevator consultant/QEI on escalation for missing-MCP-authorship or contested code interpretation — releases a Completeness Pack, a vendor chase kit, and a dated vault index.", "faq": [ { "q": "Is MCPVault Clear for the facilities desk or for risk/compliance?", "a": "Both, because at 3-40 buildings they're usually the same person: the facilities coordinator who herds Otis, KONE, TKE, and Schindler vendors, reporting to a VP of Property Management or Director of Facilities/Risk. If your building's MCP is a PDF somewhere on a vendor's server and nobody has checked it against the current AHJ checklist, the workflow will match your reality immediately." }, { "q": "How is an MCPVault Clear pack release-ready?", "a": "Every extracted field carries a source citation from the MCP, vendor log, or inspection report you uploaded — missing items ship as explicit gaps on the punch list, never invented log lines. Hard gaps (no MCP, no on-site accessibility instructions, under-5-year retention, missing FEO tests) run through deterministic rules, not a language model. A compliance analyst releases every green and yellow pack; a licensed elevator consultant/QEI releases every red pack." }, { "q": "What arrives at the end of a pack run?", "a": "A Completeness Pack PDF — gap matrix mapped to ASME A17.1 §8.6 / the adopted AHJ checklist, inventory of the MCP and 5-year maintenance/callback/FEO-test records, a punch list, vendor demand-letter drafts (the chase kit), an accessibility-instruction template, and a dated vault index — released the same cycle as your intake is complete." }, { "q": "How does MCPVault Clear pricing work?", "a": "Flat, never hourly, never contingent on an inspection pass. The MCP Completeness Pack runs $1,450-$2,850 per building (1-4 elevators; +$350/elevator beyond 4). Pre-Inspection Rush adds $450-$750 for a 5-business-day turnaround. The Vendor Cure Chase Desk runs $650-$1,200 per open hard-gap cycle, and the Portfolio Desk — 5-40 buildings with quarterly re-scans — runs $899-$2,499/month. The MCP Gap Scan is free." }, { "q": "How do I get started on MCPVault Clear?", "a": "Run the free MCP Gap Scan — upload one building's MCP and up to two elevators' worth of records for a scored checklist preview, not a released pack or a certificate — or go straight to a paid Completeness Pack if you already have a trigger: a failed inspection, a vendor change, or an insurer or lender diligence request." }, { "q": "Do you certify our elevators as safe or file with the AHJ on our behalf?", "a": "No — and that boundary is the design. MCPVault Clear does not inspect elevators, certify conveyances safe, practice engineering, act as an AHJ agent, or guarantee an inspection pass or insurance outcome. Our analyst releases the pack's completeness attestation; the licensed elevator consultant/QEI authors or certifies a new technical MCP and interprets contested code citations only on escalation. The owner remains the responsible party; physical maintenance stays with your licensed elevator contractors." }, { "q": "How long is the vault index retained?", "a": "The vault index and its underlying evidence are retained to mirror the ASME A17.1 §8.6.1.4 five-year record duty, dated and versioned per building. Because the vault can be a discovery target in litigation, we offer a client-owned export option and a documented retention/legal-review policy in the MSA." }, { "q": "What if our elevator vendor won't hand over the old MCP or service logs?", "a": "That's exactly the vendor-change scenario the Chase Desk is built for. We draft templated vendor demand letters — the chase kit — and track cure evidence until the hard gap closes. If the vendor stays silent, the pack ships at the quoted tier with the gap explicitly flagged, never filled in with invented dates or procedures." }, { "q": "What if we manage a mixed portfolio across Colorado and Fairfax County?", "a": "The AHJ edition library is checklist-card based and expandable per jurisdiction — Colorado 7 CCR 1101-8 and the Fairfax County Elevator Program are both loaded today. Every hard gap cites the specific adopted edition, so a Colorado pack and a Fairfax pack are never scored against the wrong checklist." } ], "process": [ { "title": "Intake: upload the building file", "body": "Upload the MCP, vendor logs, callback history, inspection reports, and machine-room photos for one building or conveyance. Each document gets a document ID on arrival, and unit IDs and vendor names are canonicalized against your building roster — ambiguous matches go to a human, not a guess." }, { "title": "Extract and match against the AHJ checklist", "body": "AI OCRs and classifies the file, matches it to the adopted ASME A17.1 §8.6 checklist for your AHJ edition (Colorado 7 CCR 1101-8, Fairfax County Elevator Program), and checks the MCP for equipment-specificity and coverage-timeline completeness." }, { "title": "Score hard gaps in deterministic rules", "body": "No MCP, no on-site accessibility instructions, under-5-year retention where required, and missing FEO tests where required all run through versioned deterministic gates — never a language model's judgment call — and each hard gap cites its checklist clause and evidence pointer." }, { "title": "Human release gate", "body": "A compliance analyst reviews the gap matrix and releases green and yellow packs. Missing-MCP-authorship and contested code-interpretation cases escalate — a hand-off, not a rejection — to a licensed elevator consultant/QEI, who releases the red pack." }, { "title": "Deliver the pack and chase kit", "body": "The Completeness Pack PDF, vendor chase kit, and dated vault index land in your folder the same release cycle. QA runs a second-pass sample against anti-fabrication checks before anything ships." }, { "title": "Watch the vendor cure and the next re-scan", "body": "If you've purchased the Chase Desk, we track vendor cure evidence until hard gaps close. Portfolio Desk buildings get a quarterly re-scan on the calendar, and every failed inspection or AHJ comment feeds back into the checklist library." } ], "northStarCta": { "label": "Start a pack run", "href": "/contact", "secondary_label": "See how a pack is built", "secondary_href": "/how-it-works" }, "ubiquitousLanguage": { "audience": "regional multifamily and mixed-use property managers with 3-40 elevator-equipped buildings (Colorado Front Range beachhead, Fairfax County VA secondary)", "domain": "ASME A17.1 §8.6 elevator Maintenance Control Program documentation completeness", "deliverable": "Completeness Pack + analyst release (licensed elevator consultant/QEI release on red)", "reviewer": "Licensed elevator consultant / QEI", "record": "dated, versioned vault index per building/conveyance", "unit_of_work": "pack run", "cta_primary": "Start a pack run", "cta_secondary": "See how a pack is built", "regulator": "AHJ", "regulator_full": "Authority Having Jurisdiction (Colorado OPS, Fairfax County Elevator Program, etc.)", "statute": "ASME A17.1 §8.6", "trigger_moment": "a failed or near-fail inspection citing MCP/records, a vendor change, or an insurer/lender diligence request", "event_intake_started": "elevator_mcp_completeness_pack_engine_intake_started", "event_conversation_requested": "elevator_mcp_completeness_pack_engine_conversation_requested" }, "trust": { "standards": [ "Every gap matrix entry traces to a source citation from the MCP, vendor log, or inspection report you uploaded — missing items ship as explicit gaps on the punch list, never invented log lines", "Hard gaps (no MCP, no on-site accessibility instructions, under-5-year retention, missing FEO tests) run through versioned deterministic rules, never a language model; a compliance analyst signs every release and a licensed elevator consultant/QEI releases every red pack", "Vault index and evidence are retained to mirror the ASME A17.1 §8.6.1.4 five-year record duty, dated and versioned per building, with a client-owned export option" ], "response_time": "We reply within one business day — a failed-inspection re-inspection clock does not wait for a sales rep.", "data_handling": "Your building documents stay in per-customer isolated folders and are never used to train models. MCPVault Clear provides documentation-readiness support only; it is not an AHJ agent, does not inspect elevators or certify conveyances safe, and the owner remains the responsible party. It does not guarantee an inspection pass or insurance outcome." }, "hook": "The next AHJ inspection, insurer questionnaire, or vendor-change handoff lands on a vault index, not a scramble — MCPVault Clear holds the dated record at rest. Facilities coordinators stop chasing vendor PDFs and start releasing Completeness Packs — the register is where the §8.6 evidence already lines up.", "sub_headline": "MCPVault Clear stores every §8.6 gap-matrix decision — clause citation, evidence pointer, releaser — in a dated vault index an AHJ inspector can walk without your help. Every pack run maps each checklist item to a source at intake, deterministic rules score the hard gaps, a human releases the pack, and the vault index stays reconstructable on the day the request arrives.", "dream_outcome": "You answer the week: hand over a dated, per-conveyance MCP completeness record in an afternoon instead of chasing three vendors for a month. The vault index is the answer — clause-cited, versioned, and reproducible the day the inspector, insurer, or acquiring owner asks.", "specific_pains": [ "An inspector cites 'MCP not on file for Conveyance 2' at Riverbend Commons, and the vendor who wrote it left with last year's contract — nobody knows if that's a hard gap or a filing mix-up.", "Ask for the five-year maintenance and callback record on one elevator and someone starts a search across three vendors' invoicing portals — that's the record an AHJ, insurer, or lender diligence team would find first.", "A general-purpose model can produce a plausible-looking gap summary from a PDF; only a checklist-card-cited deterministic rule set, with a human release gate, produces one an AHJ will not challenge.", "The MCP 'walks' with the outgoing vendor when a contract changes, and the new vendor inherits a building with no on-site accessibility instructions and no proof the old records exist.", "An AHJ inspector reads the file as a package: written equipment-specific MCP, five-year records, callback and FEO-test history, on-site accessibility instructions. Miss any leg and undocumented means unprovable." ], "cost_of_inaction": "An MCP you can't produce today is a record that AHJs in Colorado and Fairfax County both treat as an inspection-failure condition, independent of the elevator's physical condition. A vendor change without an owner-retained MCP means starting the documentation trail over. Litigation after an incident turns sparse contemporaneous records into a weaker defense — but a missing MCP at a routine inspection has a cost of its own, before anything goes wrong mechanically.", "mechanism": { "name": "The MCPVault Clear §8.6 Completeness Pack engine", "steps": [ { "title": "Intake: upload the building file", "body": "Upload the MCP, vendor logs, callback history, inspection reports, and machine-room photos for one building or conveyance. Each document gets a document ID on arrival, and unit IDs and vendor names are canonicalized against your building roster — ambiguous matches go to a human, not a guess." }, { "title": "Extract and match against the AHJ checklist", "body": "AI OCRs and classifies the file, matches it to the adopted ASME A17.1 §8.6 checklist for your AHJ edition, and checks the MCP for equipment-specificity and coverage-timeline completeness." }, { "title": "Score hard gaps in deterministic rules", "body": "No MCP, no on-site accessibility instructions, under-5-year retention where required, and missing FEO tests where required all run through versioned deterministic gates, each citing its checklist clause and evidence pointer." }, { "title": "Human release gate", "body": "A compliance analyst reviews the gap matrix and releases green and yellow packs. Missing-MCP-authorship and contested code-interpretation cases escalate to a licensed elevator consultant/QEI, who releases the red pack." }, { "title": "Deliver, register, watch", "body": "The Completeness Pack PDF, chase kit, and dated vault index land in your folder the same release cycle, and each failed inspection or AHJ comment feeds back into the checklist library — plus a quarterly re-scan on the calendar for Portfolio Desk buildings." } ] }, "offer_stack": [ { "item": "Completeness Pack per building", "note": "gap matrix mapped to ASME A17.1 §8.6 / AHJ checklist, MCP and 5-year maintenance/callback/FEO-test record inventory, punch list, accessibility-instruction template, dated vault index" }, { "item": "Gap matrix with clause citations", "note": "the line-by-line comparison of required checklist items vs. what evidence exists — no MCP on file means the pack is capped, never a guessed completeness score" }, { "item": "Human release on every pack", "note": "compliance analyst signature on green/yellow; licensed elevator consultant/QEI release on every red pack (missing-MCP-authorship, contested code interpretation)" }, { "item": "Vendor chase kit", "note": "drafted demand-letter templates to recover missing vendor records, with the Chase Desk tracking cure evidence until hard gaps close" }, { "item": "Dated vault index", "note": "the versioned index of every evidence item behind a pack, mirrored to your own storage, export handoff available" }, { "item": "Portfolio Desk quarterly re-scan", "note": "5-40 buildings, recurring re-scan and vault refresh so a portfolio-wide completeness scorecard replaces spreadsheet panic" } ], "guarantee": "The Release-Ready Guarantee: if a Completeness Pack is rejected from your binder for a completeness defect of our making — wrong clause citation, missing required section, unsourced gap — we re-issue free and credit the pack fee. Explicitly not guaranteed: AHJ inspection outcomes, insurance outcomes, vendor cooperation, or the accuracy of owner-attested facts like MCP custody.", "urgency": "Release capacity is gated by the human chokepoint — every pack is signed by a compliance analyst and every red pack by the licensed elevator consultant/QEI — and pre-inspection rush requests consume analyst hours first. We stop taking new logos when the release desk is full, protecting the release discipline rather than filling a pipeline.", "objections": [ { "q": "\"Doesn't our elevator vendor already handle the MCP?\"", "a": "They usually write it — but ASME A17.1 §8.6 and both Colorado and Fairfax County guidance put legal accountability for the MCP on the owner, and it can walk with the vendor when a contract changes. Your vendor's incentive is to keep the service contract, not to prove independent documentation completeness." }, { "q": "\"Isn't this what a compliance tracking SaaS already does?\"", "a": "A SaaS seat logs what your team types into it, and at 3-40 buildings, coordinators rarely have time to operate a dashboard. MCPVault Clear is a pack engine, not a dashboard: we do the extraction, the gap scoring, the vendor chase, and the release — you receive a finished, dated pack and vault index." }, { "q": "\"Are we going to be defending an AI-drafted compliance record?\"", "a": "No hard-gap determination comes from a language model. AI extracts and classifies documents and drafts chase letters and briefing memos from structured input; hard-fail gates run on versioned deterministic rules; a named compliance analyst — or, on escalation, a licensed elevator consultant/QEI — releases every pack. Anything without a source citation ships as an explicit gap." }, { "q": "\"Can you guarantee we'll pass the next inspection?\"", "a": "No — and we won't sell that. Inspection pass depends on the physical condition of the equipment and AHJ discretion, neither of which we control. What we guarantee is documentation-readiness support: a released, clause-cited Completeness Pack and a punch list of exactly what to fix." }, { "q": "\"Where does our building's evidence vault live, and what about a subpoena?\"", "a": "In per-customer isolated folders with least-privilege access, never used for model training. Because the vault can be a discovery target in litigation, we offer a client-owned export option and document retention terms in the MSA — reviewed by counsel before any commercial engagement." }, { "q": "\"How is MCPVault Clear priced?\"", "a": "Flat per building, published tiers, never hourly, never contingent on an inspection pass or on avoided fines — that framing is prohibited here. Anchor it against a full elevator-consulting engagement, a coordinator's hours chasing three vendors, and the cost of a red-tagged conveyance." } ], "who_this_is_not_for": [ "Owners who want elevators physically inspected, repaired, or modernized — that work belongs with your licensed elevator contractor or a full-service consultant, and we will refer you to one.", "Buyers looking for a guarantee that they'll pass the next AHJ inspection — we decline that engagement and document the ask; inspection outcomes depend on physical equipment and AHJ discretion, not paperwork.", "Single-building owners with no elevators, or Class-A towers already retaining a full-service elevator consultant for ongoing VT program management — the pack format won't fit either end of that range." ], "proof_pillars": [ { "title": "Deterministic hard-gap rules, checklist-cited", "body": "Every hard gap — no MCP, no on-site accessibility instructions, under-5-year retention, missing FEO tests — runs through versioned rule tables against the adopted AHJ checklist edition, never a language model's judgment call. The record doesn't summarize the gap; it cites the clause and the evidence pointer." }, { "title": "Human-released, every time", "body": "No pack auto-releases. A compliance analyst signs every green and yellow pack; a licensed elevator consultant/QEI releases every red pack — missing-MCP-authorship, contested code interpretation — and does so as a hand-off, never a rejection of the owner's file." }, { "title": "Dated vault index — no rebuild", "body": "Every pack carries the dated, versioned index of the evidence that produced it. Reconstruction for an AHJ inspector, insurer, lender, or acquiring owner is a read operation, not a month of vendor emails." } ], "stakes_line": "The machine room register is the truth. Everything else — the vendor's memory, the old contract's paperwork, the binder nobody has opened since the last inspection — is the story you tell yourself.", "deliverable": "Completeness Pack + analyst release (licensed elevator consultant/QEI release on red)", "unit_of_work": "pack run", "lexicon": { "regulator": "AHJ", "regulator_full": "Authority Having Jurisdiction (Colorado OPS, Fairfax County Elevator Program, etc.)", "statute": "ASME A17.1 §8.6", "statute_frame": "the intake-to-pack workflow where an unreleased Completeness Pack is a self-inflicted inspection risk.", "persona": "Facilities Coordinator", "persona_moment": "You're a facilities coordinator. An inspector just cited a missing MCP on one conveyance, and the vendor who wrote it left with the old contract. Someone needs to know whether that's a hard gap — with every clause tied to a source you can point to.", "trigger_moment": "a failed or near-fail inspection citing MCP/records, a vendor change, or an insurer/lender diligence request", "enforcement_stakes": "AHJ inspection-failure and red-tag exposure under Colorado 7 CCR 1101-8 and Fairfax County's elevator program (actual outcomes vary case-by-case and are never predictable or guaranteed)", "retention": "5 years", "cta_verb": "Start a pack run", "intake_checklist": [ "The MCP itself — paper or electronic, exactly as currently held, unedited", "Vendor service logs, callback history, and FEO-test records for the last 5 years, per conveyance", "The most recent AHJ inspection report and any citations received", "Machine-room photos showing the MCP's on-site accessibility (binder location, login instructions, or posted access)", "The internal owner name and inbox we should copy on status updates", "Current vendor of record and any known upcoming vendor change", "Any prior Gap Scan results or Completeness Packs for this building, even partial" ], "trust_standards_specific": [ "Every gap matrix entry traces to a source citation from the MCP, vendor log, or inspection report uploaded — gaps ship explicit, never invented", "A compliance analyst signs every release; a licensed elevator consultant/QEI releases every red pack before it ships", "Vault index and evidence are retained to mirror the ASME A17.1 §8.6.1.4 five-year duty, dated and versioned per building", "ASME A17.1 §8.6 / AHJ checklist requirements are mapped to your evidence line-by-line; hard gaps (no MCP, no accessibility instructions, under-5-year retention, missing FEO tests) block a green release", "AI drafting is bounded to extraction, gap-scoring, and chase-letter drafting from structured input, disclosed, and gated on compliance analyst or consultant release before any pack leaves the workspace" ], "regulator_faqs": [ { "q": "Do you certify our elevators as safe or act as our AHJ agent?", "a": "No — you remain the responsible party for the conveyance and its maintenance. Our analyst releases the pack's completeness attestation; the licensed elevator consultant/QEI authors or certifies a new technical MCP and interprets contested code citations only on escalation. Physical maintenance stays with your licensed elevator contractors." }, { "q": "How long is the vault index retained?", "a": "To mirror the ASME A17.1 §8.6.1.4 five-year maintenance-record duty, dated and versioned per building, with a client-owned export option given the vault's potential litigation-discovery exposure." }, { "q": "What if the MCP was never written for this conveyance?", "a": "That's an escalation, not a rejection. The pack routes to a licensed elevator consultant/QEI, who can author or certify a new technical MCP — work outside the AI/analyst boundary, priced and scoped separately from the standard Completeness Pack." }, { "q": "What if we started the MCP file in-house?", "a": "Send what exists. We pick up mid-workflow, keep your work product intact, register what's usable as evidence, and only chase the pieces the §8.6 record is missing — no rework, no re-scoring what's already sourced." } ] }, "proof_angle": { "id": "inspection-readiness", "headline": "The next AHJ inspection lands on a vault index, not a scramble — MCPVault Clear holds the dated record at rest.", "lever": "MCPVault Clear stores every §8.6 gap-matrix decision — clause citation, evidence pointer, releaser — in a dated vault index an AHJ inspector can walk without your help.", "outcome_verb": "answer", "outcome_frame": "answer an AHJ inspection or vendor-change request in an afternoon instead of a month", "proof_promise": "The vault index is the inspection-readiness answer — clause-cited, versioned, and reproducible the day the inspector or insurer asks." }, "indexable": true }, "evidence": [ { "id": "elevator-mcp-completeness-pack-engine-e1", "business_slug": "elevator-mcp-completeness-pack-engine", "area": "Identity", "claim_or_finding": "Legal entity, registered address, and jurisdiction of formation are not yet declared.", "status": "owner-action", "evidence": "No owner-supplied facts on file.", "verification_command": "Owner submits entity + jurisdiction pack.", "fix_owner": "owner", "remediation": "Provide entity name, registration number, and jurisdiction of formation.", "severity": "blocker" }, { "id": "elevator-mcp-completeness-pack-engine-e2", "business_slug": "elevator-mcp-completeness-pack-engine", "area": "Trust boundary", "claim_or_finding": "Public page is a validation microsite for a documentation-readiness support service; not an AHJ agent, not an elevator inspector, and not an engineering firm.", "status": "verified", "evidence": "Microsite carries explicit trust-boundary and documentation-support-only disclaimer block.", "verification_command": "Inspect /microsites/elevator-mcp-completeness-pack-engine for trust boundary.", "fix_owner": "engineering", "remediation": "None — enforced by template.", "severity": "low" }, { "id": "elevator-mcp-completeness-pack-engine-e3", "business_slug": "elevator-mcp-completeness-pack-engine", "area": "SEO integrity", "claim_or_finding": "No fake review, rating, LocalBusiness, or Organization identity schema is emitted; no inspection-pass or penalty-avoidance claims without the actual-outcomes-vary caveat.", "status": "verified", "evidence": "Only WebPage + FAQPage schema is generated; marketing compliance gate applied.", "verification_command": "View SEO Factory row for elevator-mcp-completeness-pack-engine", "fix_owner": "engineering", "remediation": "None — enforced by SEO factory.", "severity": "low" }, { "id": "elevator-mcp-completeness-pack-engine-e4", "business_slug": "elevator-mcp-completeness-pack-engine", "area": "Regulated claims", "claim_or_finding": "Elevated trust burden — ASME A17.1 §8.6 / AHJ-adjacent claims gated on owner facts: named licensed elevator consultant/QEI engagement letter, entity identity, and counsel review of engagement terms and disclaimers.", "status": "release-blocker", "evidence": "Trust burden = Medium-high", "verification_command": "Complete Prompt B owner facts.", "fix_owner": "owner", "remediation": "Provide consultant engagement letter (role-title until then), professional review, and disclosure facts.", "severity": "high" }, { "id": "elevator-mcp-completeness-pack-engine-e5", "business_slug": "elevator-mcp-completeness-pack-engine", "area": "Manifest coverage", "claim_or_finding": "Manifest-backed blueprint present in source repository (2026-07-13 build, Elevator MCP Completeness Pack Engine run).", "status": "assumed", "evidence": "manifest.json entry", "verification_command": "Cross-check manifest entry for elevator-mcp-completeness-pack-engine in the builds repository.", "fix_owner": "engineering", "remediation": "Attach the manifest run to the evidence register.", "severity": "medium" } ], "seo_pages": { "id": "seo-elevator-mcp-completeness-pack-engine", "business_slug": "elevator-mcp-completeness-pack-engine", "route": "/microsites/elevator-mcp-completeness-pack-engine", "title": "Elevator MCP Completeness Pack En… · k7qm", "description": "MCPVault Clear for regional multifamily and mixed-use property managers with 3-40 elevator buildings. Release-ready ASME A17.1 §8.6 Completeness Packs from your vendor…", "canonical": "/microsites/elevator-mcp-completeness-pack-engine", "og_title": "MCPVault Clear — Elevator MCP Completeness Pack Engine", "og_description": "MCPVault Clear for regional multifamily and mixed-use property managers with 3-40 elevator buildings. Release-ready ASME A17.1 §8.6 Completeness Packs from your vendor…", "schema_type": "FAQPage", "schema_status": "pending-owner-facts", "sitemap_include": false, "noindex": true }, "vertical_style": { "accent": "brass-indicator", "signature": "Machine-room register rows with AHJ chip", "layout": "Conveyance ledger", "anti": "Elevator-shaft stock photography and alarm-red penalty banners" }, "canva": { "slug": "elevator-mcp-completeness-pack-engine", "territory": "Machine Room Register", "family": { "id": "legal-compliance", "name": "Legal / Compliance", "motion": "calm" }, "tokens": { "brand": "212 24% 20%", "brand-fg": "40 20% 96%", "surface": "35 18% 96%", "ink": "215 22% 13%", "muted": "215 8% 43%", "accent": "38 78% 48%" }, "type": { "display": "Fraunces", "body": "Inter", "fonts_url": "https://fonts.googleapis.com/css2?family=Fraunces:opsz,wght@9..144,500;9..144,700&family=Inter:wght@400;500;600&display=swap" }, "scale": { "h1": "clamp(2.5rem, 5.5vw, 4.25rem)", "h2": "clamp(1.75rem, 3vw, 2.5rem)", "h3": "clamp(1.25rem, 2vw, 1.5rem)", "body": "clamp(1rem, 1.1vw, 1.125rem)", "small": "0.8125rem", "tracking_display": "-0.01em", "tracking_body": "-0.003em", "weight_display": 600, "weight_body": 430 }, "spacing": { "card_padding": "1.75rem", "card_radius": "0.375rem", "card_shadow": "0 0 0 1px hsl(var(--ink) / 0.08)", "section_gap": "clamp(3.5rem, 8vw, 6.5rem)", "hero_gap": "clamp(1.25rem, 2vw, 2rem)" }, "layout": { "hero": "split-primary", "card": "elevated-soft", "cta": "solid-brand", "archetype": "ledger", "card_silhouette": "flat-outline", "button_geometry": "rounded-sm" }, "background": { "hero_gradient": "radial-gradient(1200px 600px at 10% -10%, hsl(38 78% 48% / 0.16), transparent 60%), radial-gradient(900px 500px at 90% 10%, hsl(212 24% 20% / 0.14), transparent 55%)", "cta_gradient": "linear-gradient(135deg, hsl(212 24% 20%), hsl(38 78% 48%))", "section_wash": "linear-gradient(180deg, hsl(35 18% 96%) 0%, hsl(212 24% 20% / 0.05) 100%)" }, "motif": "Register rows + AHJ chip" }, "capabilities": { "marketing": true, "portal": true, "ops": true, "chatbot": true, "payments": false }, "generated_at": "2026-07-13T20:05:00.000Z", "checksum": "214ec1ad3db3bbb7" }