PromptSharp › Prompt Library › Product Management › Acceptance criteria writer: turn a user story into testable given-when-then cases

PRDs & SpecsFREE

Acceptance criteria writer: turn a user story into testable given-when-then cases

Engineering keeps asking what done means for a story. Write acceptance criteria that QA can test and nobody can misread.

The prompt — copy and run it

You are a product manager writing acceptance criteria for a user story. I will paste the story, the context, and any designs described in text.

Produce:

A) STORY CHECK — the story restated as who, what, and why; flag if the why is missing or the scope is really several stories.

B) ACCEPTANCE CRITERIA — given-when-then cases covering the main path, alternative paths, validation errors, empty states, permissions, and what happens on failure. Number each case.

C) OUT OF SCOPE — behaviors someone might assume are included but are not, stated explicitly.

D) OPEN QUESTIONS — anything the criteria depend on that I have not defined, each with who should answer it.

E) TEST NOTES — the cases most likely to break and the data needed to test them.

Inputs: [PASTE USER STORY] · [CONTEXT + RELATED FEATURES] · [DESIGN DESCRIPTION OR SCREEN NOTES] · [PLATFORMS + USER ROLES]

Rules: Do not invent requirements, limits, or behaviors I did not state — anything assumed goes in open questions. Write behavior, not implementation. Verify the criteria with engineering and design before the story enters a sprint. Keep confidential customer data and roadmap details out of consumer AI tools beyond what I pasted.
Got what you needed? Get a sharp, copy-paste prompt like this in your inbox most weekday mornings — start PromptSharp Daily, free →

How to use this prompt

  1. Copy the full prompt above with the Copy button.
  2. Fill in your inputs. Replace each bracketed placeholder with your specifics: [PASTE USER STORY][CONTEXT + RELATED FEATURES][DESIGN DESCRIPTION OR SCREEN NOTES][PLATFORMS + USER ROLES]
  3. Paste into ChatGPT, Claude, or Gemini and run. Read the reality guardrail below before you act on the output.

Why this prompt works

Ambiguous stories are where rework begins: engineering builds one reading, QA tests another, and the PM meant a third. Given-when-then cases that cover errors, empty states, and permissions make the definition of done testable, and an explicit out-of-scope list prevents silent expansion. Open questions put the unknowns in front of the right owner before the sprint starts.

Get a prompt like this in your inbox

The PromptSharp Product Brief ships one desk-ready prompt every weekday — free on the web today. The Product Management email edition is part of Pro: Vertical Pro is $14.99/mo, with a 14-day free trial, cancel anytime. Product Management Pro is open now: your emails start the next weekday after you subscribe, with full Pro issues within days. The Product Management prompt stays free on the web every weekday, and PromptSharp Daily (free) emails one prompt each weekday.

Email edition with Pro → Read a sample issue

Want the full PromptSharp Product Brief, not just the free prompt? Vertical Pro is the full Pro benefit set for ONE vertical. See what Pro includes.

Start your 14-day free trial →

Card required. Free for 14 days, then $14.99/month — renews automatically until you cancel. Cancel anytime before day 14 and you won’t be charged. One free trial per card. Manage or cancel anytime.

Reality guardrail: this prompt makes the model reason from data you paste — it does not source or verify facts for you. Check every claim, keep confidential data out of consumer AI tools, and follow your employer's AI-use policy.

Frequently asked

When should I use this prompt?

Engineering keeps asking what done means for a story. Write acceptance criteria that QA can test and nobody can misread.

Why does this prompt work?

Ambiguous stories are where rework begins: engineering builds one reading, QA tests another, and the PM meant a third. Given-when-then cases that cover errors, empty states, and permissions make the definition of done testable, and an explicit out-of-scope list prevents silent expansion. Open questions put the unknowns in front of the right owner before the sprint starts.

What mistake does this prompt help you avoid?

Stories with an implied definition of done: numbered given-when-then cases include errors, empty states, and permissions, with out-of-scope stated.

Related Product Management prompts

Product Management

Interview synthesis: turn user calls into jobs-to-be-done, not feature requests

You ran a batch of user interviews and got a wishlist. Translate it into the underlying jobs and unmet needs worth building for.…

Product Management

Decision memo: one page that gets an aligned yes (or a fast no)

You need a cross-functional decision and the meeting keeps slipping. Write the memo that gets it decided async — or makes the meet…

Product Management

Experiment readout: from raw results to ship / iterate / kill

The A/B test ended. Write the readout that survives the skeptic in the room — validity checks, segment cuts, and a labeled-confide…

Product Management

PRD skeleton with the edge cases the eng team will actually find

You have a validated problem and a solution sketch. Draft the PRD skeleton — with the edge cases and non-goals that prevent the we…

Product Management

Interview debrief: from transcripts to opportunities, not feature requests

Five user interviews this week. Extract opportunities — not feature requests — while keeping quote-level receipts.…

Product Management

Churned-user postmortem: exit verbatims + usage timelines to a ranked churn-driver table

A cohort churned last quarter and the room already 'knows why' (price, a competitor, onboarding). Turn the exit surveys and the ac…

Product Management

Roadmap trade-off memo: what we are not doing this quarter, and why

The roadmap is set and five teams asked for things that did not make it. Write the memo that explains the trade-offs so the no is …

All Product Management free prompts

The PromptSharp Product Brief page — five full free prompts plus today's issue.

PromptSharp Daily — free

The cross-vertical sampler: one sharp, copy-paste prompt most weekday mornings, plus a Sunday roundup, rotating across the roster. Two things in one brief: you get better at AI and prompting, and you see the sharpest prompts from across the network. If a day's issue misses our quality bar, we hold it instead of padding your inbox.

Double-opt-in. Unsubscribe anytime. No spam, ever.

Better together
Make prompts remember you: Brainfile

Even a sharp prompt starts from zero unless your AI knows you. Brainfile is persistent context — your work, voice, and priorities loaded into every session. Brainfile is the memory; PromptSharp is the playbook. Together they compound — the same prompt gets sharper because it runs on YOUR context.

Set up your brainfile →

Want both? The All-Access + Brainfile annual bundle covers the pair.

PromptSharp prompts are drafted with AI assistance and human-reviewed. They structure how a model reasons over data you provide — they do not source or verify facts for you, and you own every output. Nothing here is financial, legal, tax, or investment advice. Never paste confidential, client, or material non-public information into consumer AI tools; follow your employer's AI-use policy. © 2026 PromptSharp.