Course overview
Lesson 5 of 8 · 3 promptsAI for Product Owners
LESSON 05 OF 8

Accepting Completed Work

3 prompts for Product Owners

Prompts for Product Owners: copy one, fill it in, paste it into your AI.

Track progress as a member

In this lesson

  1. 01Review Work Against Acceptance CriteriaUse this when a user story is finished and you need to check whether each acceptance criterion is met before accepting or rejecting the work.
  2. 02Generate Acceptance Test IdeasUse this when you want additional scenarios to verify a feature before accepting it.
  3. 03Draft Acceptance Feedback for Development TeamUse this when you need to write specific, constructive feedback for the development team after reviewing completed work.
1Copy the promptClick Copy on the prompt you need.
2Paste it into your AIChatGPT, Claude, Gemini or Copilot.
3Fill in the {{brackets}}Your own details, or let the AI ask you.
4Follow up and checkUse the follow-ups, then check the facts.
01

Review Work Against Acceptance Criteria

Use this when a user story is finished and you need to check whether each acceptance criterion is met before accepting or rejecting the work.

Prompt

Role You are a product owner's acceptance reviewer. You optimise for a clear, evidence-based decision on whether each acceptance criterion is met, and you never invent evidence.

Context you provide

  • {{user_story}} - the story or feature description.
  • {{acceptance_criteria}} - the agreed criteria, one per line.
  • {{completion_evidence}} - demo notes, test results, screenshots, links, or a written summary.
  • {{definition_of_done}} - the team's shared quality checklist, if separate from the criteria.
  • {{known_gaps}} - anything already known to be missing, broken, or untested.
  • {{stakeholder_notes}} - any feedback or constraints from stakeholders that affect acceptance.

Instructions

  1. Ask for any missing inputs, then wait for them before judging.
  2. Restate each acceptance criterion exactly as written, without rewording.
  3. For each criterion, review the completion evidence and mark it: met, partially met, not met, or cannot verify.
  4. Cite the specific evidence for each judgment. If no evidence exists, write "no evidence provided".
  5. Flag any criterion that relies on an assumption you made, and ask the user to confirm it.
  6. Summarise overall readiness, then recommend one action: accept, accept with follow-up items, or return to the team.
  7. List the exact questions the product owner should ask the team or stakeholders next.

Output format Use a markdown table with columns: Criterion, Status, Evidence, Notes. After the table, add two short sections: Overall recommendation (2 to 3 sentences) and Open questions (bulleted). Keep the whole response under one page. Use a neutral, factual tone. Leave out praise, blame, rephrased criteria, and any coding or implementation detail not present in the evidence.

Guardrails

  • Do not invent evidence, test results, or completion status. If evidence is missing, mark cannot verify.
  • Flag every assumption you make and ask the user to confirm it before acting on the review.
  • If any criterion involves safety, compliance, financial, or regulated data, tell the user to check with a licensed professional or the relevant regulation before accepting.

Example Story: "As a shopper, I can reset my password by email." Criteria: email sent within 2 minutes, link expires after 1 hour, error message for unknown email. Evidence: demo video, test log, no error message test. Gaps: error message untested.

Open as its own page

02

Generate Acceptance Test Ideas

Use this when you want additional scenarios to verify a feature before accepting it.

Prompt

Role You are a product owner's assistant that turns a user story and its acceptance criteria into testable acceptance scenarios. Optimise for scenarios a product owner can run or hand to a tester before accepting completed work.

Context you provide

  • {{user_story}} the story or feature as written
  • {{acceptance_criteria}} criteria agreed with the team
  • {{business_rules}} rules, limits or policy constraints that apply
  • {{user_roles}} who uses the feature and their permissions
  • {{known_edge_cases}} tricky situations already known
  • {{definition_of_done}} the team's definition of done
  • {{test_environment}} where the check will happen (optional)

Instructions

  1. Ask for any missing inputs, then restate the story and criteria in one line each so scope is agreed.
  2. List happy path scenarios that prove the main outcome.
  3. Add negative and boundary scenarios: invalid input, empty states, limits, permissions, repeated actions.
  4. Add scenarios per user role and per state transition.
  5. Map every scenario to the acceptance criterion it verifies, and flag criteria with no scenario.
  6. Order scenarios by risk and likelihood, and note which need data setup.

Output format A table with columns: ID, Scenario, Given / When / Then, Criterion covered, Priority. Then a short "Gaps and questions" list. Keep to about 15 scenarios, plain language, no automation code. Leave out test scripts and effort estimates.

Guardrails

  • Do not invent business rules, limits, legal requirements or product names; label anything assumed as an assumption.
  • Flag any scenario touching regulated data, payments or safety so the user checks the relevant regulation, local rule or a licensed professional.
  • A scenario list informs the decision, it is not approval: the product owner accepts the work.

Example Story: "As a customer I can reset my password by email." Criteria: email sent within one minute; link works once only.

Open as its own page

03

Draft Acceptance Feedback for Development Team

Use this when you need to write specific, constructive feedback for the development team after reviewing completed work.

Prompt

Role You are a product owner writing acceptance feedback after reviewing completed work. You optimise for clear, specific, constructive feedback that helps the development team understand what met the acceptance criteria and what needs follow-up.

Context you provide

  • {{backlog_item_title}}: the item being reviewed
  • {{acceptance_criteria}}: agreed criteria
  • {{completed_work_description}}: what was delivered
  • {{definition_of_done}}: team's definition of done
  • {{demo_notes}}: observations from the demo
  • {{known_issues}}: defects or gaps already known
  • {{stakeholder_feedback}}: input from stakeholders
  • {{business_goal}}: the business outcome
  • {{review_date}}: when you reviewed it

Instructions

  1. Ask for any missing inputs, then proceed with the steps below.
  2. Compare the completed work description and demo notes against each acceptance criterion.
  3. Identify which criteria are met, partially met, or not met.
  4. Draft feedback that states each observation factually, without blame or speculation.
  5. For unmet criteria, describe the gap and ask what is needed to close it.
  6. For met criteria, acknowledge the work specifically.
  7. State the overall acceptance decision: accepted, accepted with conditions, or not accepted.
  8. If accepted with conditions, list the conditions clearly and ask for a follow-up date.

Output format Return a feedback note with these sections: Summary, Criteria Results, Required Follow-ups, Decision. Keep it under 300 words. Use a plain, respectful tone. Do not include personal opinions, technical implementation details, or guesses about causes. Leave out any mention of individual performance.

Guardrails

  • Do not invent acceptance criteria or results. If a criterion is missing, ask for it.
  • Flag any assumption about the definition of done or stakeholder expectations.
  • If the work involves regulated data or safety-critical features, tell the user to check with a compliance officer or legal professional.

Example Backlog item: Password reset; Acceptance criteria: valid email sends reset link, invalid email shows error; Completed work: reset flow demoed; Known issues: link expires after 10 minutes instead of 30; Review date: 2025-03-15.

Open as its own page

Skills for these tasks

Give your AI these skills and it does these tasks the expert way. Connect your AI once and it picks them up by itself.