Agent loop catalog

Run your test suite, fix the smallest root cause on failure, and repeat until every test passes.

Deploy to staging, run browser smoke tests on critical paths, fix failures, and repeat until every path is green.

Run Playwright or Cypress end-to-end tests with annotated failure screenshots, fix root causes, and loop until the suite is green.

Capture UI screenshots, diff against baselines, fix visual drift, and repeat until pixel diffs are within tolerance.

Run the test suite N times on an interval, capture intermittent failures, isolate flakes, and open a fix PR.