AutoPM turns abstract ideas into shipping roadmaps. 18 specialist PM robots run market sizing, competitive intel, personas, financial models and execution specs — inside Claude, Cursor or ChatGPT, saving every artifact to your own disk.
“I can get AI to write a PRD.
I need help knowing whether it is the right PRD.”
— every PM using generic AI chat, 2026
Chat assistants produce polished documents on demand — and skip the discipline that makes documents worth trusting. No market gate before the spec. No evidence trail behind the verdict. No way to tell fresh thinking from stale. AutoPM is a product judgment system, not a text generator: a gated, two-phase method that forces the hard questions in order, scores its own confidence, and leaves an auditable file trail for every decision.
The most common PM failure is rushing into solution design without a validated strategy. AutoPM makes that impossible — Phase 2 stays locked until every Phase 1 analysis is fresh.
Eight robots interrogate the idea: demand, competitors, personas, unit economics, features, roadmap, priorities.
Every robot output carries a staleness window and a machine-readable verdict block. Preliminary evidence caps the verdict at CONDITIONAL GO. No fresh strategy, no Phase 2.
Ten robots translate validated strategy into engineering-ready constraints: stories, scope, journeys, feasibility, KPIs, privacy, GTM, risks, DACI.
pdd-<product>-v1.0.0.md
Notion-ready Product Definition Doc
strategy-presentation.html
pitch-ready HTML deck
Each robot is a prompt-engineered expert with a mandate, guardrails and a required output schema — not a generic assistant with a nickname.
Locks the product idea with a dynamic PM interview.
Sizes demand — TAM/SAM/SOM, growth signals, validation.
Maps competitors, gaps, moat and positioning.
Builds personas — pains, motivations, buying triggers.
Models unit economics and 3-scenario forecasts.
Splits must-have from nice-to-have, with WHY and WHEN.
Lays a phased 18-month roadmap with dependencies.
RICE-scores the backlog with principled reasoning.
Epics and stories with acceptance criteria.
Hard scope lines and out-of-scope boundaries.
End-to-end journey narratives per persona.
Architecture, constraints, vendors, infra deps.
UX guardrails, wireflow, accessibility.
Metrics, instrumentation, target baselines.
GDPR/CCPA, security and certification impact.
Rollout waves, channels, preview→GA gates.
Structured risk matrix across 5 categories.
Driver, approver, contributors, informed.
Most landing pages show you five-star quotes. We show you the score our own product gave our own hypothesis — vanity-free, straight from the Scout robot's saved output.
{
"robot": "scout",
"verdict": "MODERATE",
"hypothesisSupportScore": { "low": 66, "base": 72, "high": 78 },
"evidenceMaturityScore": { "low": 52, "base": 61, "high": 66 },
"confidenceStatus": "preliminary",
"evidenceTier": "researched-cited"
}A tool built to stop PMs from believing their own hype shouldn't ship with hype. Every AutoPM robot ends its analysis with a machine-readable verdict block like this one — scored, ranged, and capped when evidence is thin. This is the actual block from AutoPM's self-analysis.
Every AutoPM run ends in a pitch-ready strategy presentation and a Notion-ready PDD. Here's a full Phase 1 deck, generated in AutoPM's real output format for a fictional product.
P2P camera-gear rental marketplace — 10 slides: market, competition, personas, unit economics, MoSCoW, roadmap, RICE, and a CONDITIONAL GO verdict with the downgrade rule applied.
Open the deck → REAL RUN · AUTOPM ON AUTOPMThe actual strategy deck this pipeline produced about itself — validation-gated market verdict, five personas, the monetization bridge, and the decision to build the cockpit.
Open the deck →strategy-presentation.html — themed pitch deck
pdd-<product>-v1.0.0.md — Notion-ready PDD
*-output.md — every robot's full analysis, on your disk
The demo ends in CONDITIONAL GO, not a rubber-stamp GO — thin evidence caps the verdict and blocks Phase 2. That gate is the product working as designed.
“The thinking is already there. I need people to see it without asking them to browse a directory tree.”
“I don't need another place to store docs. I need to know whether the thinking behind the docs is any good.”
“I can get AI to write a PRD. I need help knowing whether it is the right PRD.”
Great first-pass text. But no gates, no freshness, no artifact lineage — the thinking evaporates with the conversation.
Pages exist, but nothing tells you whether the thinking behind them is current, complete, or trusted.
Enterprise-grade artifact management — that assumes the strategic thinking already happened somewhere.
Forces the hard questions in order, scores its own confidence, and leaves an auditable file trail — locally, for free.
No signup. No API keys — the model already inside your MCP client does the reasoning. Node 20+ is the only requirement.
AutoPM is MIT-licensed and runs entirely on your machine.
git clone https://github.com/fluidumber/AutoPM.git cd AutoPM npm install
Works with any MCP-compatible client. Pick yours:
// claude_desktop_config.json { "mcpServers": { "autopm": { "command": "node", "args": ["/absolute/path/to/AutoPM/src/mcp-server.js"] } } }
Restart your client and ask it to use the interview tool. The Interview robot locks in your product idea, then the pipeline takes over — every output saved as markdown you own.