Skip to content
Projects06 / 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.

StackTypeScript · PlaywrightStatusPublic · v0.2.1Year2026LicenseMIT
Repository
Concept artwork for BrowserProof
BROWSERPROOF / conceptual system artwork
01THE PROBLEM

Why this needed to exist.

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.

02THE APPROACH

How I built around it.

  1. 01Define browser success as explicit URL, title, text, selector and value assertions.
  2. 02Capture the final rendered state instead of trusting an agent-generated summary.
  3. 03Hash screenshot evidence so the report carries a stable artifact fingerprint.
  4. 04Return a machine-readable pass/fail result that can gate CI or a larger autonomous workflow.
03WHAT SHIPPED

Capabilities

  • URL and title assertions
  • Text and selector verification
  • Input-value checks
  • Playwright execution
  • Final screenshot capture
  • SHA-256 evidence hash
  • JSON and HTML reports
  • CI-ready exit codes
04SYSTEM

Architecture

Runtime
TypeScript · Node.js
Browser
Playwright / Chromium
Verification
Explicit state assertions
Evidence
Screenshot + SHA-256
Output
JSON · HTML · exit code
License
MIT
05 / PRINCIPLES

What the system is meant to preserve.

  • Proof after execution
  • Observable state over agent confidence
  • Portable artifacts over opaque logs
  • Fail loudly when the browser does not match the claim
06FAQ

Useful answers.

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 BrowserProof verify?

The current runner can verify URL and title conditions, required text, visible selectors and input values, then emit JSON and HTML proof reports.

Can it run in CI?

Yes. Failed assertions produce a failed proof and a non-zero process exit code, so it can gate a CI job or a larger automation.

NEXT BUILD / 07

RunLedger

Tamper-evident local execution ledger for AI agents: hash-chained tool calls, decisions, retries, results and verifiable HTML reports.

Keep exploring
Concept artwork for RunLedger