Write user stories with acceptance criteria
INVEST-quality user stories with Given/When/Then acceptance criteria and edge cases.
This is a practical, copy-paste process for breaking a prd into sprint-ready work.. 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. Copy or downloadCopy the prompt below, or download the method file and attach it to your chat.
- 2. Paste into any AIChatGPT, Claude, Gemini or Copilot. Replace each [PLACEHOLDER] with your details, or let the AI ask you.
- 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].
# Write user stories with acceptance criteria Method by Deepstory Research: deepstoryresearch.com/method/user-stories-acceptance-criteria You are an agile product owner. Follow the method below step by step. Goal: INVEST-quality user stories with Given/When/Then acceptance criteria and edge cases. ## My inputs - Feature or PRD: [FEATURE_OR_PRD] (example: paste) - User roles: [USER_ROLES] (example: admin, member, guest) 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. Split the feature into thin vertical stories. 2. Write each as "As a…, I want…, so that…". 3. Add Given/When/Then criteria including edge and error cases. 4. Estimate relative size and flag dependencies. ## Deliver the output in this structure - Story list - Acceptance criteria - Edge cases - Dependencies ## Quality rules - Each story delivers user value on its own. - 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
| Input | Placeholder | Example |
|---|---|---|
| Feature or PRD | [FEATURE_OR_PRD] | paste |
| User roles | [USER_ROLES] | admin, member, guest |
Use it when
- Breaking a PRD into sprint-ready work.
What you get
- Story list
- Acceptance criteria
- Edge cases
- Dependencies
The procedure, step by step
Read this before you run it, so you can check the AI actually followed the method.
Split the feature into thin vertical stories.
Write each as "As a…, I want…, so that…".
Add Given/When/Then criteria including edge and error cases.
Estimate relative size and flag dependencies.
Quality checks built into the prompt
- • Each story delivers user value on its own.
- • 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.
E-Commerce Share of US Retail
Online sales as a share of total US retail, and the growth gap that keeps pushing that share up.
Six-Economy Macro Baseline
A common-country, common-period baseline for real growth, inflation, modeled unemployment and trade exposure across the United States, China, India, Germany, the United Kingdom and Japan.
Run next
Methods that chain well after this one.
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.