AI Genie

AI test case generation, grounded in your requirements.

Pick a requirement and the categories you want. AI Genie writes structured test cases for it, you review them or let them run, and every case stays linked to the requirement it checks.

"Test the checkout flow"

becomes 3 test cases

1Add item to cart
2Apply coupon code
3Confirm payment

runs them in Chrome

Add item to cart
Apply coupon code
Confirm payment

3/3 passed

How it works

From requirement to test cases.

  1. 01

    Give Project Brain your requirements

    Upload specs, PRDs, user stories or Jira issues once. testdart extracts the requirements from them.

  2. 02

    Pick requirements and categories

    Choose the requirements to cover and the categories you want: positive, negative, boundary and integration.

  3. 03

    Steer it if you want

    Add an optional instruction to focus the generation, such as a flow or an edge case you care about.

  4. 04

    Review or run

    In copilot mode your team reviews the cases and chooses which run. In autonomous mode testdart runs and verifies them on its own.

What you get

Test cases you can actually run.

Four categories

Positive, negative, boundary and integration cases, so a requirement is covered beyond its happy path.

Grounded in your spec

Every case is generated from a requirement Project Brain extracted, and stays linked to it.

No scripts to maintain

Cases turn directly into executable browser tests. There is no script or framework for your team to write.

Runs in a real browser

Tests run in a real, headed Chrome browser, with steps and screenshots for every run.

How it works

Watch one requirement become a tested release.

The whole loop in under a minute: AI Genie writes and runs the tests, Project Brain grounds them in your spec, requirements show what is covered, reports show what broke. Sample project, representative UI.

Try it on your own spec

A real browser

Tests run headed in Chrome, so you can watch every click the agent makes.

Traced to requirements

Every test case links to the requirement it proves, and every failure to the one it breaks.

Your call on autonomy

Review cases before they run in copilot mode, or let autonomous mode go end to end.

FAQ

Common questions.

Requirements that Project Brain extracts from your specs, PRDs, user stories or Jira issues.

1 requirement → test cases → a run → a report

Your next release, tested before it ships.

Point testdart at one requirement you care about. You'll have test cases, a real-browser run and a report in a single sitting.