AI PM Lab
Server Details
Learn how AI products work: lessons, model cost comparisons, real experiments, PM guides.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 18 tools
The set is mostly cleanly partitioned: cost/price tools (estimate_cost, compare_models, price_ai_feature) differ by scope (single call, side-by-side catalog compare, full unit economics), and the review_* and planning tools each target a distinct artifact (spec, incident, launch plan, roadmap, meeting prep, eval suite, acceptance criteria). The weakest boundaries are between list_challenges/quiz_me and list_experiments/replay_experiment, where a browsing tool and an interactive tool cover adjacent ground, but the descriptions spell out the difference clearly enough for correct selection.
Every name is snake_case verb_noun (or verb_object, e.g. quiz_me, count_tokens), with a predictable verb set: list_*, get_*, search_*, review_*, design_*, write_*, plan_*. No camelCase or mixed-convention outliers, so an agent can infer the pattern for tools it hasn't seen.
18 tools is on the heavy side but each maps to a real, non-redundant job across two connected surfaces (live catalog/cost utilities and PM learning + artifact generation). Nothing looks like filler, though the review_* / planning family could be consolidated slightly without losing capability.
The surface covers the apparent domain well: model discovery and cost math, tokenization, term definitions, lesson search/read, challenge listing, experiment listing/replay, quiz play, and the full PM lifecycle from spec review through launch readiness and incident review. Minor gaps exist around direct model-to-lesson linking beyond gaps in reviews and the lack of a plain lesson browse (search must be used even with no topic), but neither is a dead end.
Available Tools
18 toolscompare_modelsCompare modelsARead-onlyIdempotentInspect
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.
Inputs: models (required), input_tokens (required), output_tokens (required), requests_per_day (required), +1 more. Returns: models, unknown, live_catalog, requests_per_day
count_tokensCount tokensARead-onlyIdempotentInspect
Count the tokens in a text (an estimate with OpenAI's cl100k tokenizer; other model families differ slightly).
Inputs: text (required). Returns: tokens, tokenizer, characters
define_termDefine an AI conceptARead-onlyIdempotentInspect
A plain-language definition of an AI product concept (tokens, temperature, RAG, embeddings, LLM-as-judge, prompt injection…), with the lessons that teach it.
Inputs: term (required). Returns: text, links
design_eval_suiteDesign an eval suiteARead-onlyIdempotentInspect
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.
Inputs: feature. Returns: text, links
estimate_costEstimate model costARead-onlyIdempotentInspect
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'.
Inputs: model (required), input_tokens (required), output_tokens (required), requests_per_day (required), +1 more. Returns: model, per_day, per_month, input_share, +4 more
get_lessonGet an AI PM Lab lessonBRead-onlyIdempotentInspect
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.
Inputs: slug (required). Returns: text, links
list_challengesList AI PM Lab challengesARead-onlyIdempotentInspect
The challenges (games scored from real recorded runs, with leaderboards) and what each asks you to do.
Inputs: no named parameters. Returns: text, links
list_experimentsList recorded experimentsARead-onlyIdempotentInspect
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.
Inputs: page (required). Returns: text, links
plan_ai_launchPlan an AI feature's road to launchARead-onlyIdempotentInspect
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.
Inputs: feature. Returns: text, links
prep_planning_meetingPrepare for an AI planning meetingBRead-onlyIdempotentInspect
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.
Inputs: feature. Returns: text, links
price_ai_featurePrice an AI featureARead-onlyIdempotentInspect
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.
Inputs: feature. Returns: text, links
quiz_meQuiz me on real AI resultsARead-onlyInspect
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.
Inputs: game, round, answer. Returns: text, links
replay_experimentReplay a recorded experimentBRead-onlyIdempotentInspect
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.
Inputs: run (required), page (required). Returns: text, links
review_ai_incidentWrite up an AI incidentARead-onlyIdempotentInspect
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.
Inputs: incident. Returns: text, links
review_ai_specReview an AI feature specARead-onlyIdempotentInspect
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.
Inputs: spec. Returns: text, links
review_launch_readinessReview an AI feature's launch readinessARead-onlyIdempotentInspect
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.
Inputs: plan. Returns: text, links
search_lessonsSearch AI PM Lab lessonsARead-onlyIdempotentInspect
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.
Inputs: query (required). Returns: text, links
write_acceptance_criteriaWrite acceptance criteria for an AI featureBRead-onlyIdempotentInspect
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.
Inputs: feature. Returns: text, links
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Demand signals, product ideas and real-ad demand tests for AI agents. Free to read.
81Live prices, rankings, licences and privacy of AI models: best model per task, costs, alternatives.
AI model releases, price changes and deprecations in one feed: chat, embedding, speech, video.
Independent weekly on AI in B2B revenue teams: articles, frameworks, skills, playbooks, datasets.
Related MCP Servers
- AlicenseAqualityDmaintenanceGive your AI assistant real-time LLM/VLM knowledge. Pricing, benchmarks, and recommendations — updated every hour, not every training cycle.490 npm2MIT
- AlicenseNot gradedqualityDmaintenanceCompare AI inference pricing across 9 providers in real time. Routing recommendations, spend tracking, and budget alerts for AI agents.MIT

Modelglassofficial
AlicenseNot gradedqualityBmaintenanceLive, sourced pricing and benchmark data across image, language, video, and audio AI models, seven tools for comparison, competitor lookups, and cost-aware routing. Also powers the free Modelglass VS Code extension.1MIT
BuildBetterofficial
-licenseBqualityNot gradedmaintenanceAI for product teams. Connect all your company and customer knowledge to all of your other tools via BuildBetter's MCP.15-
Glama MCP Gateway
Add one secure layer between your agents and this server.