Coding with AI tools

Stage 4 · Lesson 2 of 7

A review checklist for AI code

Reading and reviewing AI code

AI mistakes repeat, so a short, fixed checklist catches most of them: does it do what I asked and nothing else; does every function, flag and package exist; are errors, empty input, nulls and limits handled; are there secrets, disabled checks or new uses of eval; do the tests check behaviour and would they fail if the code broke; were any tests deleted or loosened; is any new real and needed; could I explain every line?

Keep it next to your editor and run it on every change, even small ones, because tiredness is when bad changes slip through. Add to it whenever a mistake gets past you.

Common trapreviewing from memory and checking only whatever you happened to think of that day.

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?