AI PM Lab

io.aipmlabPublished by aipmlab.ioOfficial publisherv1.2.0Updated Oct 24, 2026

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

VerifiedStreamable HTTPWeb executableProductivity & WorkflowKnowledge & MemoryAI & ML

Overview

AI-generated overview

AI PM Lab gives an assistant lessons, model cost comparisons, recorded AI experiments and PM review guides for building and shipping AI products.

What you can do
Search and read lessons on AI product topics, with key ideas, concepts and links to tours and challenges; look up plain-language definitions of AI concepts and count tokens in a text; estimate per-request, daily and monthly model costs and compare models on price, context window and limits; list and replay recorded real runs, including prompt-injection and hallucination experiments; run quiz rounds built from recorded runs; review specs, planning questions, eval suites, acceptance criteria, pricing, launch plans, launch readiness and incidents using the site's method.
When to use it
Useful for product managers and teams planning, costing, evaluating or launching an AI feature who want structured guidance and evidence from recorded runs. Also handy for learning AI product concepts and comparing model costs before committing to an approach.
Requirements
Remote endpoint at aipmlab.io over streamable HTTP; no authentication, environment variables or headers are declared. Cost and model comparison tools rely on AI Gateway's live catalog and prices, so network access to the service is needed.
Before you install
Several tools (spec review, planning prep, eval design, acceptance criteria, pricing, launch planning and readiness, incident review) return instructions to follow with the user's text, so feature specs and incident details are passed to the service. Cost figures come from live third-party prices and token counts are estimates from one tokenizer, so verify before relying on them.

Installation

In SourceWeft

  1. Open AI PM Lab in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.aipmlab%2Fai-pm-lab/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "ai-pm-lab": {
      "type": "http",
      "url": "https://aipmlab.io/api/mcp"
    }
  }
}

Tools

18

search_lessons

Search AI PM Lab lessons

Find 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.

Parametersqueryrequired

get_lesson

Get an AI PM Lab lesson

A 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, its 3D tour and its challenge.

Parametersslugrequired

list_challenges

List AI PM Lab challenges

The challenges (games scored from real recorded runs, with leaderboards) and what each asks you to do.

Takes no parameters.

define_term

Define an AI concept

A plain-language definition of an AI product concept (tokens, temperature, RAG, embeddings, LLM-as-judge, prompt injection…), with the lessons that teach it.

Parameterstermrequired

count_tokens

Count tokens

Count the tokens in a text (an estimate with OpenAI's cl100k tokenizer; other model families differ slightly).

Parameterstextrequired

estimate_cost

Estimate model cost

What 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'.

Parametersmodelrequiredcached_shareinput_tokensrequiredoutput_tokensrequiredrequests_per_dayrequired

compare_models

Compare models

Compare 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-4.1-mini', or a provider name ('anthropic', 'openai', 'google') for its newest models, so you don't need to know which models are current.

Parametersmodelsrequiredcached_shareinput_tokensrequiredoutput_tokensrequiredrequests_per_dayrequired

list_experiments

List recorded experiments

The 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.

Parameterspagerequired

replay_experiment

Replay a recorded experiment

What 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, with a link to run it on the site.

Parametersrunrequiredpagerequired

quiz_me

Quiz me on real AI results

A 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 without its answer; call again with the round id and the user's choice to mark it, see how players on the site called it, and get the next round.

Parametersgameroundanswer

review_ai_spec

Review an AI feature spec

Check 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 instructions to follow with the user's text.

Parametersspec

prep_planning_meeting

Prepare for an AI planning meeting

The 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.

Parametersfeature

design_eval_suite

Design an eval suite

Build 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 with the user's text.

Parametersfeature

write_acceptance_criteria

Write acceptance criteria for an AI feature

Acceptance 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 to paste into a ticket. Returns instructions to follow with the user's text.

Parametersfeature

price_ai_feature

Price an AI feature

Work 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. Returns instructions to follow with the user's text.

Parametersfeature

plan_ai_launch

Plan an AI feature's road to launch

A 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 this feature, backed by findings from AI PM Lab's recorded real runs (injection, grounding, evals, agent cost). Returns instructions to follow with the user's text.

Parametersfeature

review_launch_readiness

Review an AI feature's launch readiness

A 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. Returns instructions to follow with the user's text.

Parametersplan

review_ai_incident

Write up an AI incident

A 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 time. Returns instructions to follow with the user's text.

Parametersincident

Version history

3
  1. v1.2.0LatestOct 12, 2026
  2. v1.1.0Oct 11, 2026
  3. v1.0.1Oct 10, 2026

Score

83% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.