Your app works. Until someone double-clicks.
GenClass finds what breaks in your web app, can hotfix it live, and hands the real fix to your AI. One command sets it up.
npx genclass
- Duplicate submitPOST /api/orders · /checkout41
- Stale responseGET /api/search · /search17
- Failing requestGET /api/inventory · /products/:id9
- Fixed by GenClassstale writes dropped, repeats merged52
Measured results
- 0
- bugs introduced in 3,510 runs
- 0.13%
- false interventions in guard
- 75%
- duplicate submits caught
- 7.5%
- fixable cases guard acts on
Real browsers, on held-out apps it never trained on. Every number, with its method
What GenClass does
- 01
Review every pull request
The GitHub App reads what the runtime saw while your Playwright tests ran, and comments with each race. It never reads your source code.
- 02
Catch it in production
A stale response, a double submit, an endpoint that keeps failing: nothing crashes, so error monitors see nothing. GenClass reports each one with its evidence.
- 03
Fix it with your agent
Over MCP, your agent gets what happened in order, reruns it with the responses reordered, and writes a test that fails on the bug.
- 04
See it on the dashboard
What broke, on which page, and how often. Open the sample dashboard
US$50 a developer. 3 days free.
US dollars, per developer, billed monthly through Stripe. Cancel any time.
The runtime, its model and the MCP server are open source (Apache-2.0) and free.
npx genclass
Questions
Will GenClass break my app?
The default mode only observes. GenClass introduced no bugs in 3,510 test runs across 7 frameworks, and ?genclass=off turns it off on a page.
Will my visitors see GenClass?
No. It draws nothing on your pages. What it finds goes to the browser console, your dashboard and your terminal.
Does it need an account or an API key?
The runtime needs neither: one import, and the model runs on the device. npx genclass signs you in and starts Pro's 3 free days, so your app gets a dashboard.
Can my coding agent use it?
Yes. @genclass/mcp shows your agent what happened in order, replays the bug and writes a test for it.