What is a user story?

Explained

A user story is a small, valuable piece of functionality described from the point of view of the person who will use it. It is often written as 'As a [type of user], I want [something] so that [benefit]', and completed with acceptance criteria that say how to know it is done. Stories link personas to outcomes and are used to order and plan a team's backlog. In spec-driven AI work they also anchor evaluation: each story should map to measurable acceptance criteria and be traceable to the prompts, tools and telemetry that implement it.

Parts of a good user story

• Who: the user or role, specific enough to picture.
• What: the capability they need, described as behaviour, not as a screen or a technical task.
• Why: the benefit, which helps decide priority and the simplest solution.
• Acceptance criteria: concrete conditions, often in Given-When-Then form, that confirm the story is done.
• A conversation: the card is a reminder to talk; details are agreed between the team and the people who know the need.

INVEST and story size

A common checklist for judging a story is INVEST: independent, negotiable, valuable, estimable, small and testable. A story that fails one of these is usually reworded or split.

Stories that are too big to deliver in one iteration are called epics and are broken down into smaller stories. Each resulting story should still deliver something of value on its own, rather than being a technical layer that only works once the others are done.

User stories in AI projects

AI features are harder to specify because their output varies. A useful story states not only what the user wants but how a good answer is recognised: the cases it must handle, what it must never do and when it should hand over to a person.

Those acceptance criteria become evaluation cases. Tracing each story to the prompts, tools, data and metrics behind it means you can show, after every change, which stories still pass and which have regressed.

Frequently asked questions

Further reading

• AI-Native Application Development: A C-Suite Guide
• Enterprise AI Transformation: A Strategic Roadmap for Competitive Advantage

Related terms

• Evaluation The process of measuring how well an AI model or application performs: accuracy, relevance, safety, bias, cost and other criteria.
• Spec-Driven AI Using product and system specifications, such as requirements, API contracts and guardrails, as the source that steers AI models, agents and evaluations.
• Acceptance Criteria Testable conditions that define when a feature or a model's output is complete and correct, so that 'done' can be checked rather than argued.
• AI Bill of Materials A machine-readable inventory of everything an AI system is built from: models, datasets, dependencies, licences and their lineage.
• AI Governance The policies, processes and controls an organisation uses to make sure its AI is safe, lawful, ethical and worth what it costs.
• AI Native Systems, products and processes designed from the start with AI as a core part, rather than with AI added afterwards.