# Product Architect > Complete product development system with 80 agents and 36 frameworks. Use when the user wants to build a product, write a PRD, plan an MVP or roadmap, design an app, research a market or check whether a feature already exists or is novel, do competitive analysis, run a security audit, build a financial model, plan hiring, launch, set up operations, prepare for IPO, or write a compliance policy. Also triggers on market research, does this exist, product marketing, positioning, pricing, packaging, sales, RevOps, partnerships, developer relations, user research, growth, PLG, data engineering, data governance, privacy, DPO, DSAR, incident management, OKRs, program management, docs, localization, investor relations, M&A, procurement, RAG, LangGraph, AI agents, LLM features, customer support, backend and distributed systems, enterprise architecture, developer productivity, FinOps and cloud cost, business continuity, physical security, facilities, regulatory affairs, hardware, internal comms, vendor risk, market exp - Skill: `ankitjha67/product-architect` (Agent Skill, multi-file: 9 files) - Install (CLI): `npx skillmds@latest add ankitjha67/product-architect` - Raw SKILL.md: https://api.skillmd.com/api/skills/ankitjha67/product-architect/raw - Safety review: pending - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: Product & Planning - License: MIT - Author: ankitjha67 (https://skillmd.com/u/ankitjha67) - Updated: 2026-09-17 - Page: https://skillmd.com/skills/ankitjha67/product-architect --- # Product Architect 80 specialized agents covering every department from solo founder Day 0 to IPO. 36 frameworks with tactical playbooks, compliance guides, process maps, and a modern AI-engineering stack (LangGraph, RAG, agents) applied across every department. ## Depth Promise: Research-First, Never Surface-Level This system goes deep "until the Mariana Trench." Before recommending building ANY feature, product, or bet, agents run the **Deep Research Protocol** (`frameworks/deep-research-protocol.md`, owned by Agent 47): they investigate the market end to end and return a grounded verdict - **"this already exists, here are the competitors + citations, refine it"** or **"this is white-space, no competition or citations found in this niche"** (with the honest caveat that absence of evidence is not proof of novelty). Every agent inherits this via `references/agent-standards.md` and must grade its output L3+ on the Depth Rubric. Agents never fabricate a company, statistic, study, patent, or URL; when live-search tools are unavailable they say so and label market claims as hypotheses. Every agent also reasons through the **Enterprise Reasoning Protocol** (`references/agent-standards.md`): frame → options (≥2, incl. do-nothing) → evidence → quantified trade-offs → recommendation with sensitivity → risks + reversal condition → verify against KDRs and governance. In enterprise/regulated contexts, agents add the six enterprise lenses (compliance & audit trail, scale/SLA, integration with the existing stack, procurement/security review, change management, 3-year TCO). Each agent file carries its own Decision Framework specializing this protocol for its domain's hardest calls. ## Critical: Read SMART-LOADER.md First Before loading any agent files, consult `SMART-LOADER.md`. It contains: - Request classification and agent routing (which agents to load) - Context budget rules (never load more than 5 agents per turn) - Multi-intent decomposition (handling complex requests) - KDR memory system (Key Decision Records that survive chat compaction) - Conflict detection protocol (what to do when agents disagree) ## Instructions ### Step 0: Research Gate (for any build/bet) If the request is to build a feature/product, validate an idea, or make a market/ pricing/architecture bet, load `agents/47-deep-research.md` + `frameworks/deep-research-protocol.md` FIRST. Establish whether it already exists (cite competitors → refine) or is white-space (no citations found → say so + why it's empty) BEFORE designing the solution. Then proceed to Step 1. For pure questions, checklists, or continuations, skip the gate but still apply the Depth Rubric. ### Step 1: Route the Request Read `SMART-LOADER.md` to classify the request and identify which agents to load. ``` QUICK ROUTING: "Write a PRD" → agents/04-prd.md + frameworks/prd-framework.md "Design an app" → agents/05-design.md (+ anti-slop-design skill) "Product roadmap" → agents/02-discovery.md + agents/03-strategy.md "Financial model" → agents/18-finance.md "Security audit" → agents/09-security.md + agents/11-compliance-ethics.md "Marketing plan" → agents/15-marketing-sales.md + frameworks/30-day-launch-engine.md "How to start" → frameworks/founders-playbook.md "Checklist for [X]" → frameworks/universal-checklists.md "Positioning/messaging" → agents/31-product-marketing.md + frameworks/brand-messaging.md "Pricing/packaging" → agents/36-pricing-monetization.md + frameworks/pricing-packaging.md "Sales motion/RevOps" → agents/32-sales-revops.md + frameworks/sales-playbook.md "Partnerships" → agents/33-partnerships-bizdev.md + frameworks/partnership-framework.md "Growth/PLG" → agents/37-growth.md + frameworks/growth-model.md "User research" → agents/35-user-research.md "Developer relations" → agents/34-developer-relations.md + agents/30-platform-ecosystem.md "Docs/tech writing" → agents/42-content-docs.md "Localization/i18n" → agents/43-localization-i18n.md + frameworks/accessibility-i18n.md "Data pipelines" → agents/38-data-engineering.md + frameworks/data-governance.md "Privacy/DSAR/DPO" → agents/39-privacy-dpo.md + references/compliance/*.md "Internal IT/SSO" → agents/40-it-corporate-engineering.md "Program management" → agents/41-technical-program-management.md "OKRs/goals" → frameworks/okr-goal-setting.md "Incident/on-call" → frameworks/incident-management.md + agents/08-devops-sre.md "Investor updates" → agents/44-investor-relations.md "M&A/acquisition" → agents/45-corporate-development.md + frameworks/physical-ops-pmi.md "Procurement/vendors" → agents/46-procurement-supply-chain.md "Customer journey" → frameworks/customer-journey.md + agents/17-customer-success.md "Mobile/iOS/Android" → agents/48-mobile-engineering.md "ML model/MLOps/deploy" → agents/49-ml-engineering.md + frameworks/ai-engineering-stack.md "Frontend/web perf/SEO" → agents/50-frontend-web-platform.md "Demo/POC/RFP/security questionnaire" → agents/51-solutions-engineering.md "Implementation/onboarding/SOW" → agents/52-professional-services.md "Customer training/certification" → agents/53-customer-education.md "Community/forum/ambassadors" → agents/54-community.md "Billing/subscriptions/usage metering" → agents/55-billing-monetization-engineering.md "Revenue recognition/close/audit" → agents/56-revenue-accounting.md "Tax/GST/VAT/nexus" → agents/57-tax.md "Cash/FX/runway/banking"→ agents/58-treasury.md "Internal audit/SOX/ERM"→ agents/59-internal-audit-risk.md + frameworks/risk-matrix.md "Recruiting/hiring process" → agents/60-talent-acquisition.md "Compensation/equity/benefits" → agents/61-total-rewards.md + frameworks/compensation-bands.md "Chief of staff/BizOps/operating cadence" → agents/62-chief-of-staff-bizops.md "AI evals/red-team/is it safe to ship" → agents/63-ai-evaluation-red-teaming.md "Support queue/tickets/deflection/CSAT" → agents/64-customer-support.md "Backend/API/distributed/consistency" → agents/65-backend-distributed-systems.md "Enterprise architecture/ARB/tech radar"→ agents/66-enterprise-architecture.md "Dev productivity/DORA/build times/platform" → agents/67-developer-productivity-platform.md "Cloud cost/FinOps/unit economics of infra" → agents/68-finops-cloud-economics.md "Business continuity/DR/RTO/RPO/resilience" → agents/69-business-continuity-resilience.md "Physical security/badging/travel risk" → agents/70-corporate-physical-security.md "Office/facilities/lease/real estate" → agents/71-workplace-facilities.md "Regulatory approval/QMS/medical device"→ agents/72-regulatory-affairs-quality.md "Hardware/manufacturing/BOM/NPI" → agents/73-hardware-manufacturing.md "Internal comms/all-hands/change comms" → agents/74-internal-communications.md "Vendor risk/third-party/SOC 2 review" → agents/75-third-party-risk.md "Market entry/new country/expansion" → agents/76-market-expansion.md "Design ops/research ops/design system" → agents/77-design-research-ops.md "Accessibility/WCAG/VPAT/inclusive" → agents/78-accessibility-inclusive-design.md "Data science/causal/experiment design" → agents/79-data-science-experimentation.md "What could go wrong/pre-mortem/org risk" → frameworks/enterprise-edge-cases.md "LangGraph/RAG/AI agent"→ frameworks/ai-engineering-stack.md + agents/29-data-ai-strategy.md + agents/06-engineering.md "AI feature/LLM/embed" → frameworks/ai-engineering-stack.md + frameworks/ai-department-playbooks.md "AI for [department]" → frameworks/ai-department-playbooks.md "Does this exist?" → agents/47-deep-research.md + frameworks/deep-research-protocol.md "Is this novel?" → agents/47-deep-research.md + frameworks/deep-research-protocol.md "Market research" → agents/47-deep-research.md + agents/02-discovery.md "Build [any feature]" → agents/47-deep-research.md FIRST (research gate), then route "Full product" → Phased execution (see SMART-LOADER.md Phase Plan) ``` ### Step 2: Load and Execute Load the primary agent file, then apply quality standards from `references/agent-standards.md` which contains: - Quality protocol (before/during/after checklist for every agent) - Iterative refinement loop (draft → self-review → refine → deliver) - Cross-reference table (which frameworks support which agents) - Standard example format and error handling patterns ``` LOADING PRIORITY: 1. SMART-LOADER.md (routing - always) 2. Primary agent (produces the deliverable) 3. Relevant framework (template/structure - see agent-standards.md cross-reference table) 4. Secondary agent (validation - if budget allows) ``` ### Step 2b: Apply the Edge-Case Doctrine (three layers) Most plans do not fail on the thing that was specified. They fail on the thing that was not. Three separate layers of edge case exist, they fail independently, and covering one does not cover the others. ``` LAYER 1 - PRODUCT EDGE CASES frameworks/stress-test-framework.md What breaks in the product: empty/loading/error states, boundary values, concurrency, offline, partial failure, adversarial input, scale. LAYER 2 - ORGANISATIONAL EDGE CASES frameworks/enterprise-edge-cases.md What breaks around the product: sponsor departure, mid-year budget cut, approval-gate latency, change freeze, reorg, M&A, regulatory examination, competing internal mandates, scale pathologies. Every agent file also carries its own "Organisational Edge Cases" section for its function. LAYER 3 - ROUTING & SESSION EDGE CASES SMART-LOADER.md What breaks in this system: ambiguous or contradictory requests, governance deadlocks, circular dependencies, stale or divergent KDRs, context pressure, and outputs that are fluent but unsourced. ``` ``` THE RULE: □ Any deliverable that describes product behaviour → run Layer 1 □ Any plan spanning >1 team or >1 quarter → run Layer 2's Pre-Mortem Sweep and name the top 3 to 5 organisational risks, each with a trigger, an owner, a pre-agreed 48-hour move, and a reversal condition □ Every turn → Layer 3 applies ⛔ A plan with zero named organisational risks has not been pre-mortemed. It has been written optimistically. ``` ### Step 3: Enforce Cross-Agent Governance When multiple agents are active, apply the authority hierarchy: ``` Level 5 (highest): Agent 11 (Compliance) - OVERRIDE on legal/regulatory risk Level 4: Agent 39 (Privacy/DPO) - OVERRIDE on personal-data processing & rights Level 3: Agent 09 (Security) - OVERRIDE on security vulnerabilities Level 2: Agent 18 (Finance) - VETO on budget/cost violations Level 1: Agent 00 (Chief Reviewer) - VETO on quality/consistency ``` Note: Privacy (39) and Compliance (11) are adjacent authorities. When a question is about *whether* data may be processed at all (lawful basis, consent, rights, transfers), Privacy leads. When it is about *which statute/regulator* governs and broader legal/ regulatory exposure, Compliance leads. If they disagree, the stricter control wins. If two agents produce conflicting recommendations: 1. STOP - do not proceed with either 2. STATE the conflict explicitly 3. APPLY the hierarchy (higher authority wins) 4. DOCUMENT in KDR with decision number 5. FLAG for user review ### Step 4: Output Key Decision Records After every phase, output a structured KDR block capturing all decisions, specs, open items, and artifacts. KDRs survive chat compaction. Full KDR format is in `SMART-LOADER.md`. ## Agent Directory Audit: `00-chief-reviewer` `01-proactive-advisor` Product: `02-discovery` `03-strategy` `04-prd` `05-design` `06-engineering` Build: `07-testing-qa` `08-devops-sre` Protect: `09-security` `10-legal-ip` `11-compliance-ethics` `12-trust-safety` `13-fraud-operations` Launch: `14-launch-gtm` `15-marketing-sales` `16-analytics` `17-customer-success` Operate: `18-finance` `19-operations` `20-bau` `21-innovation-programs` People: `22-people-hr` `23-learning-development` `24-wellness-performance` Corporate: `25-pr-communications` `26-governance-ipo` `27-esg-sustainability` `28-government-relations` Specialized: `29-data-ai-strategy` `30-platform-ecosystem` Commercial: `31-product-marketing` `32-sales-revops` `33-partnerships-bizdev` `36-pricing-monetization` `37-growth` Developer & Research: `34-developer-relations` `35-user-research` `42-content-docs` `43-localization-i18n` Data & Privacy: `38-data-engineering` `39-privacy-dpo` Internal & Delivery: `40-it-corporate-engineering` `41-technical-program-management` Corporate Finance: `44-investor-relations` `45-corporate-development` `46-procurement-supply-chain` Research: `47-deep-research` (research-first gate - invoked before any build/bet) Engineering Specialisms: `48-mobile-engineering` `49-ml-engineering` `50-frontend-web-platform` Customer-Facing Delivery: `51-solutions-engineering` `52-professional-services` `53-customer-education` `54-community` Revenue Systems: `55-billing-monetization-engineering` Finance Specialisms: `56-revenue-accounting` `57-tax` `58-treasury` Risk & People: `59-internal-audit-risk` `60-talent-acquisition` `61-total-rewards` Executive: `62-chief-of-staff-bizops` AI Assurance: `63-ai-evaluation-red-teaming` (gates whether an AI feature is good/safe enough to ship) Support & Platform Eng: `64-customer-support` `65-backend-distributed-systems` `66-enterprise-architecture` `67-developer-productivity-platform` Infra Economics & Resilience: `68-finops-cloud-economics` `69-business-continuity-resilience` Corporate Security & Workplace: `70-corporate-physical-security` `71-workplace-facilities` Regulated Product & Hardware: `72-regulatory-affairs-quality` `73-hardware-manufacturing` Comms & Vendor Risk: `74-internal-communications` `75-third-party-risk` Expansion, Ops & Insight: `76-market-expansion` `77-design-research-ops` `78-accessibility-inclusive-design` `79-data-science-experimentation` All agent files are in `agents/` directory. ## Framework Directory All framework files are in `frameworks/` directory: `founders-playbook` `30-day-launch-engine` `scenario-playbooks` `sop-process-maps` `compensation-bands` `consulting-frameworks` `stress-test-framework` `universal-checklists` `global-compliance` `corporate-scaling` `institutional-memory` `prd-framework` `mvp-framework` `roadmap-framework` `user-flows-framework` `risk-matrix` `ab-testing-framework` `accessibility-i18n` `product-lifecycle` `competitive-war-room` `continuous-improvement` `physical-ops-pmi` `coverage-audit` `okr-goal-setting` `pricing-packaging` `growth-model` `sales-playbook` `data-governance` `incident-management` `partnership-framework` `brand-messaging` `customer-journey` `deep-research-protocol` `ai-engineering-stack` `ai-department-playbooks` `enterprise-edge-cases` Country compliance: `references/compliance/` - india, us, eu, uk, sea. ## Examples Example 1: Single-topic request ``` User: "Write a PRD for a payment feature" → Load agents/04-prd.md + frameworks/prd-framework.md → Produce PRD with: happy path, error states, edge cases, acceptance criteria → Output KDR with all decisions ``` Example 2: Full product build ``` User: "Build me a food delivery app for Bangalore" → Phase A: agents/02 + 03 → Discovery brief + strategy + KDR-A → Phase B: agents/04 + 05 → PRD + design + KDR-B → Phase C: agents/06 + 07 + 08 → Architecture + testing + DevOps + KDR-C → Phase D: agents/18 + 19 + 15 → Finance + ops + marketing + KDR-D → Phase E: agents/11 + 22 + 26 → Compliance + hiring + governance + KDR-E → Phase F: agents/00 + 01 → Final 6-pass audit + proactive suggestions ``` Example 3: Quick reference ``` User: "What salary should I pay a senior engineer in Bangalore?" → Load frameworks/compensation-bands.md → Answer: L3 Senior, Tier 1 India, ₹22-38 LPA generic / ₹30-55 LPA niche ``` ## Troubleshooting Skill triggers on unrelated queries: - This skill scopes to product development only - Should NOT trigger for general coding, creative writing, or factual queries - Description includes negative triggers for common false positives Context window fills up: - Never load more than 5 agent files per turn - Free tier: max 3 agents per turn - Use phased execution in SMART-LOADER.md for complex requests Inconsistent outputs across agents: - Apply cross-agent governance hierarchy (Step 3) - Chief Reviewer (Agent 00) runs 6-pass consistency audit with 14 cross-checks - Conflict detection protocol prevents contradictions Context lost after chat compaction: - KDR system outputs structured state after every phase - User pastes MASTER KDR into new conversation to restore full context Request is ambiguous, contradictory, or built on a false premise: - Ask ONE disambiguating question, or state the contradiction and recommend a resolution - Never silently pick a reading, and never build on a premise you know is wrong - Full handling in `SMART-LOADER.md` section A (Request-Level Edge Cases) Two governance agents disagree, or the hierarchy does not resolve it: - Compliance (11) and Privacy (39) are adjacent: the stricter control wins - Authority is scoped to domain. Security has no veto over pricing - True deadlock is a user decision, not a routing decision. Present both positions and stop - Full handling in `SMART-LOADER.md` section C (Governance Hierarchy Edge Cases) The right agent does not exist, or too many agents match: - Never invent an agent number or cite a file that is not in `agents/` - 6+ agents scoring high means the request is a programme. Phase it, do not load 6 - Full handling in `SMART-LOADER.md` section B (Routing Engine Edge Cases) Research returns nothing, or sources contradict each other: - No sources found is Verdict D (white-space) only if the absence is meaningful, otherwise Verdict E (inconclusive). Absence of evidence in one search is not evidence of absence - Report source disagreement and tier it. Do not silently pick the convenient one - Full handling in `SMART-LOADER.md` section D and `frameworks/deep-research-protocol.md` A plan is about to ship with no organisational risks named: - That is not a low-risk plan, it is an un-pre-mortemed one - Run the Pre-Mortem Sweep in `frameworks/enterprise-edge-cases.md` section 9 - See Step 2b above for the three-layer Edge-Case Doctrine ## Important All legal, financial, security, and HR content requires professional review before real-world use. See `references/DISCLAIMER.md` for full details.