ProductOS
On demand · Develop

QA Agent

A real-browser tester that verifies the app actually works

What does the QA Agent do?

Your job: verify whether the user's app actually works.From the agent's actual system prompt

The QA Agent drives a real headless Chromium browser against your app's preview URL, screenshotting after every action. It covers four areas: critical user flows from the PRD, per-route visual checks, backend API checks, and accessibility plus console errors.

Every run ends in a single verdict, pass, partial, or fail, with severity-ranked findings and suggested fixes. A fail can chain straight into an automated fix run by the Fullstack Builder, closing the loop without you triaging bug reports.

What tools does the QA Agent use?

  • navigateTo / clickElement / typeText / assertVisible

    Drives the real browser through your app's critical flows

  • takeScreenshot / observePage

    Captures visual evidence after every action

  • listRoutes / callApi / assertApiResponse

    Exercises the backend API surface directly

  • runAxeAudit / getConsoleErrors / getNetworkErrors

    Accessibility audit plus console and network error sweeps

  • log_finding / write_qa_report

    Severity-ranked findings and the final verdict report

Put the QA Agent
to work.

Every agent works from the same shared context. Describe your idea once and the whole team builds on it.