Define browser success as explicit URL, title, text, selector and value assertions.
PROJECT / 06 · Agent tooling / browser verification
BrowserProof
BrowserProof is a small verification layer for AI browser agents and Playwright workflows that turns “done” into an observable, testable browser state.
browser state / verified
PASS
CAPABILITIESWhat it does,
What it does,
without the theatre.
01URL and title assertions02Text and selector verification03Input-value checks04Playwright execution05Final screenshot capture06SHA-256 evidence hash07JSON and HTML reports08CI-ready exit codes
Autonomous browser runs can confidently report success while the wrong page is open, a save never happened, or the attached screenshot does not prove the requested outcome. Execution and verification need to be separate concerns.
HOW I BUILT AROUND IT01 02 03 04
Capture the final rendered state instead of trusting an agent-generated summary.
Hash screenshot evidence so the report carries a stable artifact fingerprint.
Return a machine-readable pass/fail result that can gate CI or a larger autonomous workflow.
ARCHITECTURE
What the system is meant to preserve.
- 01Proof after execution
- 02Observable state over agent confidence
- 03Portable artifacts over opaque logs
- 04Fail loudly when the browser does not match the claim
Is BrowserProof another browser agent?+
No. It is deliberately downstream of the agent. The agent or Playwright flow acts; BrowserProof verifies the resulting browser state and emits evidence.
What can it verify?+
URL and title conditions, required text, visible selectors and input values, then JSON and HTML proof reports.
Can it gate CI?+
Yes. Failed assertions produce a failed proof and a non-zero process exit code.