Proof Docs
Autonomous product QA

Introduction

Proof learns the customer outcomes your product must protect, exercises them in a real browser, and turns successful AI exploration into deterministic Playwright coverage.

What Proof does

Proof starts from a business task, not a selector list. It observes the page, chooses browser actions from the current state, verifies the resulting customer outcome independently, and compiles the verified semantic trace into a Playwright test that runs without AI.

When that deterministic test later fails, Proof retries the original business intent. If the outcome still works, it can prepare a validated test repair. If the outcome no longer works, it reports a regression with the run history and captured evidence.

Ways to use Proof

Slack
Ask Proof to complete a customer task from Slack.

Every entry point creates the same durable run and returns the same business outcome.

Command line
Configure and run Proof from a terminal.

Every entry point creates the same durable run and returns the same business outcome.

GitHub pull requests
Automatically test affected business flows.

Every entry point creates the same durable run and returns the same business outcome.

Production monitoring
Run deterministic suites continuously without AI.

Every entry point creates the same durable run and returns the same business outcome.

The mental model

  1. Business flow: a customer outcome worth protecting, such as completing checkout.
  2. Scenario: one happy path or edge case with explicit success evidence.
  3. Exploration: an AI agent reasons through the scenario in a browser.
  4. Semantic trace: the verified, selector-independent record of what worked.
  5. Compiled test: a versioned Playwright test replayed without model calls.
  6. Adjudication: a fresh semantic attempt that decides whether a failed test is stale or the product is broken.