What is AI code review?

AI code review uses an AI model or agent to examine code changes, usually in a pull request, and flag bugs, security issues and style problems before or alongside human reviewers.

AI code review applies a model to a pull request to look for likely bugs, missing tests, security risks and inconsistencies with the code base. It is fast and tireless, which makes it a good first pass before a human reviewer spends time on the change.

Using it well

  • Treat AI review as an extra reviewer, not a replacement for human approval.
  • Give it the team's standards so its comments match how you work.
  • Review agent-written code with the same, or stricter, rules as human-written code.

Updated