Agents Index

AI PM Lab

Online

Learn how AI products work: lessons, model cost comparisons, real experiments, PM guides.

Visit publisherConnectJSON

What it can do: 18 tools

  • search_lessons read-onlyFind AI PM Lab lessons on a topic (e.g. RAG, evals, agents, prompt injection, cost). Returns the best matches with their key idea and link.
  • get_lesson read-onlyA lesson in full: the product decision it informs, its key idea and concepts, things to try with what to notice in each (from recorded runs), what a PM takes away and questions to ask engineers, with links to the lesson,
  • list_challenges read-onlyThe challenges (games scored from real recorded runs, with leaderboards) and what each asks you to do.
  • define_term read-onlyA plain-language definition of an AI product concept (tokens, temperature, RAG, embeddings, LLM-as-judge, prompt injection…), with the lessons that teach it.
  • count_tokens read-onlyCount the tokens in a text (an estimate with OpenAI's cl100k tokenizer; other model families differ slightly).
  • estimate_cost read-onlyWhat a model call costs per request, per day and per month at a given volume, from AI Gateway's live prices. Model ids look like 'openai/gpt-4.1-mini' or 'anthropic/claude-sonnet-4.5'.
  • compare_models read-onlyCompare several models side by side at a given volume: cost per request and per month, prices, context window, output limit, release date and knowledge cutoff, from AI Gateway's live catalog. Pass ids like 'openai/gpt-4.
  • list_experiments read-onlyThe real runs recorded on one of AI PM Lab's 3D pages or lessons, each described by its setup (e.g. which defences or settings were on). Replay one to see what happened.
  • replay_experiment read-onlyWhat happened in one recorded real run (e.g. whether a prompt injection leaked data with given defences, or how many answers were made up without a facts sheet): the setup, each step, the result and the model's reply, wi
  • quiz_me read-onlyA round from AI PM Lab's challenges, built from real recorded runs: Call It (predict what a model did), Spot the Failure (ship or flag a real output) or Which Wins? (pick the better of two setups). Returns the question w
  • review_ai_spec read-onlyCheck an AI feature spec or PRD against what AI PM Lab teaches: approach, model and cost, prompt, grounding, output contract, tools, security, human oversight, evals, monitoring, fallbacks. Gaps link to lessons. Returns
  • prep_planning_meeting read-onlyThe questions a PM should ask engineers about a planned AI feature, with why each matters and what a good answer sounds like. Returns instructions to follow with the user's text.
  • design_eval_suite read-onlyBuild an evaluation suite for a planned AI feature with AI PM Lab's method: test cases (typical, edge, out of scope, attacks), graders with a judge rubric, pass bars, and a JSON test set. Returns instructions to follow w
  • write_acceptance_criteria read-onlyAcceptance criteria for an AI feature or user story that can actually be tested: Given/When/Then with measurable pass bars on a test set, must-pass safety criteria, latency and cost budgets, and example test cases, ready
  • price_ai_feature read-onlyWork out an AI feature's unit economics and pricing: cost per request and per user (light, typical, heavy), levers like caching and routing, pricing options with margins, guardrails, and the assumptions to validate. Retu
  • plan_ai_launch read-onlyA phased roadmap from where an AI feature is today to launch and its first month live: frame, prototype and model, evals, hardening, pilot, launch, monitoring. Each phase has exit criteria and the tests and checks for th
  • review_launch_readiness read-onlyA go/no-go review of an AI feature's launch plan: evals, grounding, attacks, approvals, cost, latency, monitoring, rollout and support, each marked ready, at risk or missing, with blockers and a launch-day watch list. Re
  • review_ai_incident read-onlyA blameless post-incident review for an AI feature: where it failed (input, retrieval, prompt, model, tools, output checks), why evals and monitoring missed it, actions, and the new eval cases that would catch it next ti

Connect it

Claude Code
claude mcp add --transport http ai-pm-lab https://aipmlab.io/api/mcp
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://aipmlab.io/api/mcp
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "ai-pm-lab": {
      "url": "https://aipmlab.io/api/mcp"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "servers": {
    "ai-pm-lab": {
      "type": "http",
      "url": "https://aipmlab.io/api/mcp"
    }
  }
}

Questions

What does AI PM Lab do?

Learn how AI products work: lessons, model cost comparisons, real experiments, PM guides. It exposes 18 tools to AI assistants.

What tools does AI PM Lab provide?

18 tools, including search_lessons, get_lesson, list_challenges, define_term, count_tokens, estimate_cost, compare_models, list_experiments, replay_experiment, quiz_me, review_ai_spec, prep_planning_meeting….

How do I connect AI PM Lab to Claude, ChatGPT or Cursor?

Add the remote MCP endpoint https://aipmlab.io/api/mcp as a custom connector or MCP server. Copy-paste setup is on this page.

Does AI PM Lab require an account or API key?

No sign-in was needed to list its tools. Individual tools may still need an account or API key.

Is AI PM Lab online?

As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.

Who publishes AI PM Lab?

aipmlab.io. The official MCP Registry verified that the publisher controls this domain before accepting the listing.

Similar in E-commerce & Shopping