productagents
QA written in English. Run in a real browser.
Describe a test in numbered steps. A browser agent runs it in Chrome on every push, records a replay you can watch live, and refuses to guess when it cannot verify.
- 1Open the checkout page as a returning customer
- 2Add “Annual plan” to the cart
- 3Pay with the saved card
- 4/verify the order confirmation shows a receipt number
- 5/extract receipt = the receipt number
- 6Save state as paid-customer
how you use it
Agentic QA, in order.
01
Write the test the way you would explain it
Numbered steps in plain words, with a frontmatter for the platform and the state it starts from. Verify and extract are steps too; values you extract become variables for later steps, and a state you save can start the next test. The same file is understood by the editor, the worker and the repository.
02
A browser agent runs it, in Chrome, on every push
Six cooperating agents drive a real browser over its debugging protocol: one plans, one acts, one asserts, one judges the interface, one extracts, one plays the persona. Nineteen actions, including throttling the network and the CPU to see what a customer on a bad connection sees. No selectors to maintain: a redesign does not break the test, a broken flow does.
03
Evidence, streamed live
A session replay, the console and the network log stream while the run happens; a late joiner catches up, then follows live. When a step cannot be verified, the run says so with a reason instead of faking a pass. The probe engine handles plain HTTP checks without a model or a browser.
04
The agent’s loop: the push that came from an agent gets the same run
A coding agent’s push triggers the same QA run as a person’s. The run, its replay and its verdict sit in the hub on the branch, where the reviewer of the agent’s change request sees them before approving. Runs also start by hand or on a schedule; a project can pause new runs without cancelling queued ones. On iOS simulators and Android devices the worker installs a verified build and launches it.
not built yet: agentic steps on iOS and Android; today those platforms install and launch · automatic scheduling for test groups
The full reference lives in the docs.
works with
Open a branch and try it.
Boots in seconds. Your team joins with a link.