Coding with AI tools

Stage 4 · Lesson 7 of 7

AI review as a second pass

Reading and reviewing AI code

After your own review, a separate AI review in a fresh context can catch edge cases, because it is not attached to the code it just wrote. In , /review reviews the current or a for bugs and /security-review checks the for vulnerabilities.

In Cursor, /agent-review reviews local changes and reviews pull requests, following rules in BUGBOT.md files. On GitHub, you can request Copilot as a reviewer on a pull request; its comments are plain comments by default, so they do not count as an approval. Treat the findings as suggestions to verify, not orders.

Common trapchasing every AI review comment: a reviewer asked to find problems always finds some, so fix what affects correctness and skip the rest.

A question to check yourself, an AI practice session and 1 cheat sheet entry come when you add the roadmap to your account. Add it

Resources for this stage

Start with

  • GuideFree
    Google Engineering Practices

    Google · Intermediate

    Google's free code review guide: what reviewers look for and how to write review comments

Practise

  • After solving an exercise, read several community solutions and review them against your checklist

Keep handy

Also worth your time

Mark this stage as not done?