← Index25 entries · By Vocation
Section II · For the Product Manager

Prompts for the Product Manager

AI prompts for product managers: writing user stories, summarizing meetings, drafting status updates, and crafting product specs.

§ Overview

Product management is a translation job. You turn a fuzzy customer problem into a spec engineers can build, a roadmap leadership will fund, and a status update stakeholders will actually read. AI tools are well suited to that translation work because so much of it is restructuring information you already have into a cleaner shape.

This collection leans into the artifacts PMs produce week after week: user stories with Given-When-Then acceptance criteria, full PRDs with goals and open questions, quarterly OKRs that stay outcome-focused, and meeting notes distilled into decisions, owners, and follow-ups. There's also the analytical side — reading an A/B test for significance, planning a dashboard that avoids vanity metrics, and turning raw notes into a slide outline before a review.

The payoff isn't writing prose faster. It's getting a structured first draft so your time goes to judgment — prioritization, tradeoffs, and the open questions a model can surface but can't answer for you.

§ Field Notes

What makes a good prompt for a product manager

Good PM prompts give the model the context engineers would ask for in a kickoff: who the user is, what problem you're solving, what's explicitly out of scope, and how you'll measure success. A user-story prompt without acceptance criteria produces vague stories; feed it the edge cases and constraints and you get testable ones.

For anything analytical, supply the actual numbers and the decision you're trying to make. When you ask AI to read an A/B test, give it sample sizes and conversion rates and ask for a ship/no-ship call with the caveats spelled out — that's far more useful than a generic explanation of p-values.

§ Pro Tips

Get sharper results

  • 01When drafting a PRD, give the model your goals and known constraints, then ask it to generate the open-questions section last — those gaps are often more valuable than the parts it can confidently fill in.
  • 02For OKRs, push the model to write key results as measurable outcomes rather than shipped features, and ask it to flag any that are really just a task list in disguise.
  • 03Feed meeting notes verbatim and ask specifically for decisions, owners, and dated follow-ups as three separate lists, so nothing important gets buried in a prose summary.
  • 04Before an A/B-test prompt, include sample size and baseline rate and ask the model to state whether the result is significant and what it would NOT conclude from the data.
§ FAQ

Common questions

Will AI write a PRD I can actually ship to engineering?

It writes a strong first draft — structure, user stories, and open questions — but you still own the judgment calls. The model can't decide your priorities or know your technical constraints unless you tell it. Use it to skip the blank page, then layer in the context only you have.

How do I get acceptance criteria that QA can actually test?

Ask for Given-When-Then format and provide the real edge cases and failure states, not just the happy path. Then read each criterion and ask yourself whether a tester could mark it pass or fail without guessing. If it's ambiguous, feed that back to the model and tighten it.

Can I rely on AI to interpret my experiment results?

Use it to run the significance math and frame the decision, but sanity-check the inputs and the conclusion. Give it accurate sample sizes and rates, and be skeptical if it declares a winner from a tiny sample. It's a calculator and a second opinion, not the final call.

§ The Prompts · 25
№ 008productivity

Summarize Meeting Notes Into Action Items

Turn messy meeting notes into a clean summary with decisions, owners, and follow-ups.

For
chatgpt·claude
№ 010productivity

Write User Stories With Acceptance Criteria

Turn feature ideas into clean user stories with Given-When-Then acceptance criteria.

For
chatgpt·claude
№ 020productivity

Write a Concise Weekly Status Update

Convert messy weekly notes into a manager-ready 200-word status update.

For
chatgpt·claude
№ 040marketing

Craft a Clear Value Proposition Statement

Craft a positioning statement, feature-benefit table, and tagline for any product.

For
chatgpt·claude
№ 048business

Write a Product Requirements Document (PRD)

Generate a complete PRD with goals, requirements, user stories, and open questions.

For
chatgpt·claude
№ 049business

Write Quarterly OKRs for a Team

Generate outcome-focused quarterly OKRs with confidence scores and risk notes.

For
chatgpt·claude
№ 054business

Facilitate a Sprint Retrospective

Plan a full sprint retrospective with agenda, prompts, and action-item templates.

For
chatgpt·claude
№ 059design

Generate a UI Screen Mockup in Midjourney

Generate a stylized mobile app UI mockup for inspiration and client presentations.

For
midjourney
№ 060productivity

Build a Structured Daily Plan From Your To-Do List

Turn a task list into a time-blocked daily schedule with deep work sessions and an MIT.

For
chatgpt·claude
№ 065data

Plan a Data Dashboard Layout and Metrics

Plan a full dashboard with curated KPIs, chart types, layout, and vanity-metric warnings.

For
chatgpt·claude·gemini
№ 067data

Analyze an A/B Test for Statistical Significance

Statistically analyze an A/B test result with significance testing and a ship/no-ship recommendation.

For
claude·chatgpt
№ 068data

Choose the Right Chart Type for Your Data

Get a chart type recommendation with rationale, alternatives, and common pitfalls for your data.

For
chatgpt·claude·gemini
№ 084career

Write a Self-Review for Your Performance Review

Turn your wins into a polished, metrics-backed self-review with an explicit ask.

For
chatgpt·claude
№ 111productivity

Reschedule a Conflict Without Looking Disorganized

Draft a low-drama reschedule request with three concrete alternatives.

For
chatgpt·claude
№ 114productivity

Turn Raw Notes Into a Slide Deck Outline

Convert raw notes into a complete slide deck outline with titles, core messages, and transitions.

For
chatgpt·claude
№ 197business

Draft OKRs That Cascade From Company Goal to Team

Drafts outcome-based OKRs that ladder up to the company goal and weeds out tasks masquerading as key results.

For
chatgpt·claude
№ 199business

Market Analysis With TAM Logic, Segments, and Whitespace

Builds a transparent bottom-up market sizing with buyer segments, alternatives, and underserved whitespace.

For
chatgpt·claude
№ 200business

Summarize a Sprint Retro Into Themes and Owned Actions

Clusters messy retro notes into themes with root causes and a table of owned, dated actions.

For
chatgpt·claude
№ 201business

Vendor and Tool Comparison With a Weighted Scorecard

Screens tools against must-haves then ranks survivors on a weighted scorecard with a clear pick.

For
chatgpt·claude
№ 202business

Business Case for a Project With ROI and Payback

Frames a project as an investment with quantified benefits, a transparent ROI and payback calculation.

For
chatgpt·claude
№ 223data

Choose the Right Chart Type for Your Data

Recommends the best and runner-up chart type for your message, variables, and audience with encoding guidance.

For
chatgpt·claude
№ 224data

Interpret an A/B Test Result Without Overclaiming

Interprets A/B test numbers honestly, flags validity risks, and gives a ship or keep-running recommendation.

For
chatgpt·claude
№ 225data

Write a Precise, Unambiguous Metric Definition

Produces a precise metric definition with formula, grain, inclusion rules, and resolved edge cases.

For
chatgpt·claude
№ 227data

Write a Dashboard Spec Before You Build It

Drafts a build-ready dashboard spec with KPIs, layout, filters, drill-downs, and out-of-scope guardrails.

For
chatgpt·claude
№ 228data

Explain a Statistical Concept to Non-Technical Stakeholders

Translates a statistical concept into a plain-language explanation tied to a real decision for non-technical stakeholders.

For
chatgpt·claude