AI confidently writes code that's completely wrong

1. Check the problem

Confidently wrong code almost always hides one edge case the model never considered. Ask how it would verify the code works, and what happens if the input is empty, null, or huge.

2. Use the prompt

Before I accept this code, answer two things. One: how would you verify it actually works, what specific inputs or test cases would prove it? Two: what happens if [the key input] is empty, null, very large, or malformed? Walk each case and fix any that break.

3. Verify the fix

Review the proposed diff, run the relevant checks and exercise the original failing flow before merging.