Tusk is triggered when a PR/MR (draft or otherwise) is created or a new commit is pushed to the PR/MR’s branch. It shows up as a non-blocking check, akin to automated code review but with the added benefit of scaling your testing infra.

  1. Software engineer creates a draft PR/MR with their code changes.
  2. On PR/MR creation, Tusk takes 8-15 mins to generate, run, and iterate on its unit tests (latency varies depending on PR/MR size and complexity).
  3. Engineer clicks on Tusk’s PR/MR comment and reviews the test generation output in the Tusk web app.
  4. Engineer selects which unit tests they want to commit and clicks Incorporate tests in the Tusk web app.
    • If there are failing tests, engineer checks out the branch and fixes the bug in their code causing the failing test. Tusk labels failing tests with a [Tusk] FAILING TEST comment in the test file for easy reference.
    • Note: Once Tusk’s tests are incorporated, the agent no longer re-runs test generation to avoid excessive looping.
  5. Engineer marks the PR as ready for review.
  6. Go through your typical PR review workflow before approving and merging the PR/MR.