Skip to main content
MethodProduct DevelopmentDefinition & specsIntermediate

Write a product requirements document (PRD)

A PRD with problem, goals, non-goals, users, requirements, UX notes, metrics and open questions.

This is a practical, copy-paste process for handing a feature to design and engineering.. Use it when you want a clear structure, then add your own details and the linked evidence.

Published by Deepstory Research. Reviewed Sep 2026.

How to use this method

  1. 1. Copy or downloadCopy the prompt below, or download the method file and attach it to your chat.
  2. 2. Paste into any AIChatGPT, Claude, Gemini or Copilot. Replace each [PLACEHOLDER] with your details, or let the AI ask you.
  3. 3. Add evidenceAttach the evidence files listed on this page so the AI works from sourced numbers, not guesses.

The prompt

Paste it as-is. The AI will ask for anything still in [BRACKETS].

Download .md
# Write a product requirements document (PRD)
Method by Deepstory Research: deepstoryresearch.com/method/product-requirements-document

You are a senior product manager. Follow the method below step by step. Goal: A PRD with problem, goals, non-goals, users, requirements, UX notes, metrics and open questions.

## My inputs
- Feature idea: [FEATURE_IDEA]  (example: saved searches with alerts)
- User problem and evidence: [USER_PROBLEM_AND_EVIDENCE]  (example: users re-run the same search daily)
- Constraints: [CONSTRAINTS]  (example: must ship in 6 weeks)

Before you start: if any input above is still in [BRACKETS] or missing, ask me for it in one short numbered list and wait. Do not guess. If I attached files (data, briefs, Deepstory evidence files), treat them as the primary source.

## Steps to follow
1. State the problem and evidence.
2. Set goals and explicit non-goals.
3. Describe users and use cases.
4. Write functional requirements with priority (must/should/could).
5. List non-functional requirements (performance, privacy, accessibility).
6. Define success metrics and launch criteria.
7. List risks and open questions.

## Deliver the output in this structure
- Problem
- Goals / non-goals
- Users & use cases
- Requirements table
- Non-functional requirements
- Metrics
- Risks & open questions

## Quality rules
- Requirements are testable.
- Non-goals are listed to prevent scope creep.
- Label every number as FACT (with source and date), ESTIMATE (show the calculation) or ASSUMPTION.
- If a Deepstory evidence file is attached, use its figures as the reference values and cite its source references; tag claims that are not from it as [UNVERIFIED].
- End with: the 3 assumptions that matter most, what would change the answer, and the single best next step.

What you need to give the AI

InputPlaceholderExample
Feature idea[FEATURE_IDEA]saved searches with alerts
User problem and evidence[USER_PROBLEM_AND_EVIDENCE]users re-run the same search daily
Constraints[CONSTRAINTS]must ship in 6 weeks

Use it when

  • Handing a feature to design and engineering.

What you get

  • Problem
  • Goals / non-goals
  • Users & use cases
  • Requirements table
  • Non-functional requirements
  • Metrics
  • Risks & open questions

The procedure, step by step

Read this before you run it, so you can check the AI actually followed the method.

  1. 1

    State the problem and evidence.

  2. 2

    Set goals and explicit non-goals.

  3. 3

    Describe users and use cases.

  4. 4

    Write functional requirements with priority (must/should/could).

  5. 5

    List non-functional requirements (performance, privacy, accessibility).

  6. 6

    Define success metrics and launch criteria.

  7. 7

    List risks and open questions.

Quality checks built into the prompt

  • • Requirements are testable.
  • • Non-goals are listed to prevent scope creep.
  • • Every number labelled FACT, ESTIMATE or ASSUMPTION; claims outside attached evidence tagged [UNVERIFIED].

Evidence to use with this method

Methods tell the AI how to think. Evidence gives it sourced numbers to think with. Download a context file and attach it with the prompt.

Run next

Methods that chain well after this one.

Product DevelopmentWrite user stories with acceptance criteriaINVEST-quality user stories with Given/When/Then acceptance criteria and edge cases.Technology & DevelopmentDesign a software system architectureAn architecture with components, data flow, scaling, failure handling and trade-offs.Product DevelopmentScope a minimum viable product (MVP)The smallest product that tests the riskiest assumption, with cut list and success criteria.

Deepstory methods are process guidance for AI tools. Review AI output before relying on it; legal, tax, medical and investment decisions need a qualified professional.