ThinkWithPrompt by SynotticThinkWithPrompt

Stress-test my PRD before the review meeting

A critical read of your PRD that finds weak reasoning, missing sections, and the questions reviewers will ask.

Product & UX DesignFew-ShotStandardProductMeetingsAnalyzeFill-in Template

The prompt

Critique my PRD before I take it to review. PRD: [PASTE] Reviewers: [e.g. engineering lead, design lead, VP Product, legal] Decision I need from the review: [e.g. approval to start build, scope sign-off] Review it as a skeptical reviewer would. Check: - Problem: is it evidenced, specific, and clearly worth solving now? Is the solution creeping into the problem statement? - Users: are target users and non-target users defined? - Goals: is there a measurable outcome, and could the team ship everything and still miss it? - Scope: are non-goals explicit? Is scope sized to the goal? - Requirements: are they testable, prioritized, and free of ambiguous words? - Alternatives: were other approaches considered and why were they rejected? - Risks: technical, legal, privacy, security, accessibility, operational, and dependencies on other teams. - Launch: rollout, measurement, and support plan. - Consistency: contradictions between sections. Return: 1. Top 3 issues that would block approval, with a suggested fix for each. 2. Line-level comments in a table: Section | Issue | Suggested rewrite. 3. The 8 questions each reviewer is most likely to ask, with what the PRD should say to answer them. 4. A readiness rating: ready / ready with fixes / not ready. Do not rewrite the whole PRD or add requirements I did not intend; suggest and flag.

Highlighted [brackets] are blanks to replace with your own details.

Fill in the blanks and use this promptMore Product & UX Design prompts

What to fill in

  • PASTE
  • e.g. engineering lead, design lead, VP Product, legal
  • e.g. approval to start build, scope sign-off

How this prompt is built

This prompt follows the Few-Shot structure (Few-shot prompting). A few-shot prompt includes one or more worked examples of the input and the output you want, so the model can copy the pattern instead of guessing it.

Related prompts

Find more prompts like this