Product Checks After Every Merge
When a PR lands, an agent opens the product, checks that the affected flows still work, and reports what it found.
Tests Pass, and the Product Still Breaks
Unit and integration tests cover what someone thought to test. A merged change can still break a page, a flow, or a link that no test touches, and the team finds out from a user. Checking the product by hand after every merge doesn't scale.
An Agent Uses the Product the Way a Person Would
Start an agent from an event after a merge or deployment. Ask it to explore the affected flows with Felan's managed browser, run the relevant tests, and classify failures as product, test, environment, or expected-change issues. Review its report and supporting evidence.
- Sign-in and checkout flows
- Settings page loads
- Invoice download returns 404
Common Questions
What triggers a check?
Configure GitHub pull-request or push events, GitLab merge-request events, or Vercel deployment events. GitLab webhook setup requires Felan support; Vercel webhooks require manual setup. You can also use a schedule or a manual request.
Does it need our existing tests?
No. Felan can explore the application with its managed browser and write test scenarios. It can also extend and run your repository's Playwright tests using your existing conventions.
Where do the findings go?
Results remain available in the session and go to the team's default communication channel when configured. Ask for reproduction steps and test results. With a supported issue tracker connected, the agent can prepare findings for that tracker.
Which models can it use?
Any major provider, plus local and private models. Bring your own keys or subscription, and there's no markup on tokens.
Related: Quality assurance docs, Failed build triage.
Keep Your Attention for the Hard Problems
Start with one repo and one recurring task.