Paul Lister
In my experience, user stories are the working unit of agile teams - and bad stories cause bad sprints. Good stories take time to write well, which is why I see teams chronically underinvest in them. AI changes the math for me: a high-quality user story now takes 5-10 minutes instead of 30-45 minutes, and the team can iterate fast.
AI User Story Generator: Prompts, Templates & Examples
In this guide I share the prompts, templates, and review patterns I’ve found make AI user story generation reliable, plus the failure modes I’ve watched catch teams off-guard. Use it as the working manual I wish I’d had earlier.
The Anatomy of a Great User Story
A great user story has:
- A user: who needs this.
- A goal: what they want to accomplish.
- A reason: why it matters.
- Acceptance criteria: how we know it is done.
- Dependencies: what else must be in place.
- A reasonable size: small enough to ship in one sprint.
Skip any of these and the story underperforms.
The AI Story Generation Workflow
A working workflow:
- PM/PO drafts a one-line problem statement.
- AI generates a draft story with AC.
- Human reviews against INVEST and context.
- Team refines in sprint planning.
- Final story in PM tool.
End-to-end: 10-15 minutes per story instead of 30-45.
The Prompts You Need
Prompt 1: Generate a story from a problem statement
“You are a senior product owner. Below is a problem statement. Generate a user story in the format: ‘As a [user] I want [goal] so that [reason]’. Include 6-10 acceptance criteria covering happy path, edge cases, error states, and DoD. Output as markdown.”
Prompt 2: Refine an existing story
“Take this story and improve it: [paste]. Score it against INVEST. For any criterion failed, propose a specific fix.”
Prompt 3: Generate acceptance criteria only
“Take this story: [paste]. Generate 8-12 acceptance criteria. Use Given/When/Then format. Cover happy path, edge cases, error states, observability, and DoD.”
Prompt 4: Split a story
“This story is too big: [paste]. Suggest 3 ways to split it that each deliver independent customer value. For each split, name the new stories and what gets deferred.”
Prompt 5: Convert a feature description to stories
“Below is a feature description from a roadmap. Decompose it into 5-10 user stories. For each: title, narrative, AC. Order by suggested priority.”
INVEST-Aligned Output
INVEST = Independent, Negotiable, Valuable, Estimable, Small, Testable.
A useful audit prompt:
“Run INVEST checks on this story: [paste]. For each criterion, state pass or fail and why. Propose specific changes for any failed criterion.”
Output is a 6-line audit. Address the failures and re-run.
Generating Acceptance Criteria
AI-generated AC tends toward generic. Improve with these techniques:
- Specify the format: “Use Given/When/Then” or “Use checklist format”.
- Demand coverage: “Include error states, edge cases, observability”.
- Demand specificity: “Each AC must reference a specific user behaviour or system state”.
- Demand testability: “Each AC must be objectively testable”.
A working AC generation prompt:
“Generate 8-12 acceptance criteria for this story: [paste]. Use Given/When/Then. Each AC must be objectively testable, reference a specific user behaviour or system state, and avoid vague language. Cover happy path, 3 edge cases, 2 error states, observability hooks, and DoD.”
Splitting Stories That Are Too Big
Common splitting patterns AI applies well:
- SPIDR: Spike, Path, Interface, Data, Rules.
- Workflow steps: each step a story.
- Business rules: each rule a story.
- Happy path / edge cases: ship happy path first.
- Configurations: one config first.
A useful prompt:
“This story is too big: [paste]. Apply 3 different splitting strategies. For each, output the resulting stories. Recommend the best split for delivering customer value fastest.”
Generating Stories From Discovery Notes
A higher-leverage workflow: generate stories directly from user research.
“Below are 8 user interview transcripts. Identify pain points worth solving. For the top 5 pain points, generate user stories with AC. Include a count of how many users mentioned each pain.”
This converts research into actionable backlog in minutes. Pairs especially well with continuous discovery practices.
The Review Checklist
Before any AI-generated story enters the backlog:
- Does the story have a real user, not a generic “user”?
- Is the goal specific to a behaviour, not vague?
- Is the reason (“so that”) concrete?
- Do the AC cover error states and edge cases?
- Is the size reasonable for one sprint?
- Are dependencies named?
- Is it testable?
A 60-second review pass per story prevents bad stories from entering planning.
Common Failures and Fixes
- AI invents users. Always specify the real user from your discovery.
- AC drift to generic. Demand specificity in the prompt.
- Stories that look good but lack scope clarity. Add “What is explicitly out of scope?” as a section.
- AI assumes UI conventions you do not have. Provide your design system context.
- Over-specified AC. Trim to the essential. Engineers can add their own internal criteria.
- Identical-sounding stories. AI templated outputs. Edit for voice.
- Missed business context. AI can’t know your strategic priorities. Inject them in the prompt.
Templates You Can Copy
Story template:
As a [specific user] I want to [specific goal] So that [concrete benefit]
Acceptance criteria: - Given X, When Y, Then Z - (more)
Out of scope: - …
Dependencies: - …
Refinement template:
Story title Narrative (As a… I want… So that…) Background context AC Design link Dependencies DoD additions specific to this story
Story Generation by Domain
Consumer software: focus on user emotions and journey moments. AC includes UX states.
B2B SaaS: focus on workflow integration and admin / end-user separation. AC includes role-based behaviour.
Mobile: AC includes platform-specific (iOS/Android) considerations, offline state, push notifications.
Hardware: AC includes physical states, calibration, error recovery.
Internal tools: simpler narratives, focus on process compliance and audit logging.
Marketing/ops: stories about tasks rather than user experiences. AC includes deliverables and approval flows.
Building a Shared Prompt Library
For teams to benefit:
- Save prompts in shared Notion or Confluence.
- Tag each prompt with use case.
- Note expected output format.
- Include examples of strong prompt outputs.
- Update quarterly as models change.
A team-wide prompt library is one of the highest-leverage investments a scrum master or PO can make.
Quality Metrics for AI-Generated Stories
Track:
- Refinement edits per story: declining is good (prompts improving).
- In-sprint scope changes: declining is good (stories were sized correctly).
- Stories carried over: declining is good (better estimation).
- Engineer satisfaction with stories: pulse survey, should rise.
- PO review time per story: should drop after prompt library matures.
If quality drops, the issue is usually prompt drift, not AI itself.
Questions people ask
Published