Xedant Test Agent — Product Launch

Today Xedant Test Agent launches — interface checking that learns once. You open a page in Chrome, take a snapshot and explain in words what is wrong, and the AI turns the remark into a rule: a small check that then runs right in the browser.

A rule works fast, costs nothing and finds the same problem on every similar page. So the longer the product runs, the less AI is left in it and the cheaper the checks become: rules and recorded actions assemble into tests, the tests run on a schedule, and every build is seen as a picture next to the approved baseline.

Key capabilities

Screens in one click: a snapshot of the visible area, the address, the title and the page structure are saved at once

Comments in plain words right on the page — no machine-style wording

One comment becomes a check for a whole class of problems, not for a single page

A check is plain JavaScript that runs in the browser without calling the model: fast and free

Tests assemble from rules and recorded actions, and run on demand or on a schedule

A built-in runner inside the container executes tests with no separate Chrome

Every step leaves a screenshot as evidence, and identical errors merge into a single issue

Builds are compared with the approved baseline: a layout shift, a colour or a missing block is visible in the picture

The verdict on every difference is always a human’s — the AI only suggests. Everything runs on your own server. Details and documentation are on the product page: Xedant Test Agent.