Skip to main content
A coding agent with the Momentic MCP server and the momentic-spec skill turns a user story into a .test.yaml file before anyone writes product code. The agent reads the story, maps the acceptance criteria to steps and assertions, and writes the file into your repository. Once the feature is usable in your app, the agent proposes a run and executes it after you confirm. The test is plain YAML, so you edit it in a pull request like any other file.

​
Setup

Install the MCP server and the skills with the CLI. Both commands are described in Building with AI:
The agent needs a MOMENTIC_API_KEY in its environment and a reachable app to test: a local dev server, a preview deploy, or staging.

​
In your coding agent

Inside Claude Code, Cursor, Codex, or another agent with the Momentic MCP server and skills installed, paste the story after the skill name:
The agent writes one test per acceptance criterion that changes what the user sees, or one test that covers the story when the criteria form a single journey. For the story above it produces a file like this:
apply-promo-code.test.yaml
The second entry uses fill so the field’s value is replaced instead of appended to. See type. The agent does not run the test right away. Momentic runs are end-to-end checks against the real UI, so the skill waits for a durable checkpoint: the promo code feature is implemented and a user can exercise it in the app. At that point the agent names the test it proposes to run, asks you to confirm, and runs it once you agree. If you run it before the feature exists, the assertions fail.

​
Edit the generated test

The file lives in your repository, so review it in the same pull request as the feature:
  • Rename the id to something your team recognizes, then keep it stable. See File format.
  • Replace a natural-language step with a preset step when the action is exact. click: Apply gives the runtime one action to perform, where “click the apply button” leaves the path to an AI action. Steps lists the preset steps.
  • Tighten each assert to the contract in the story. “The order total is lower” is a weaker check than “The order total is $89.10” when the story fixes the discount.
  • Move shared setup such as log-in into a module so every test generated from a story reuses it.
Run the edited file locally before you push:

​
What to expect

  • The agent covers the acceptance criteria you give it. A story with no criteria produces a test that asserts only the happy path.
  • Steps that name UI elements the app does not have yet still run: the AI action step finds the element by description once it exists. Preset steps such as click also target by description.
  • When the UI changes later, locator auto-healing re-resolves a stale target during the run, and failure recovery can clear an obstruction and retry. See AI test maintenance.
For tests scoped to a code change instead of a story, see Generate tests from a pull request diff.