Hacker News Reader

Would love to hear more about using Claude to determine which E2E tests to run. What context are you giving it?

Is it like, "this looks like a billing feature, let me run any tests that seem relevant"?

I feed the `git diff` of the branch (excluding large files like package-lock) and a list of the E2E files. Claude reads and compares the E2E tests against the modified content.

The good thing about Claude Code is that it uses tool calls to explore the files to check which E2E tests can validate the changes.

How well does this work for massive codebases and thousands of e2e tests?

Reply on news.ycombinator.com