Life improved immensely once I learned to stop telling Cursor "it still doesn't work" and instead tell it to pause, don't write any code, investigate the issue properly, come up with 3-5 theories for what's going wrong, and validate theories with logs.
I also give it web + docs access, if relevant.
I also give it web + docs access, if relevant.
Comments
Standard debugging tactics, rediscovered.
Only then will it find the answer.
A related strategy is to tell the AI to ask you up to 5 questions about the bug (+ not write code yet).
I think both of these also loop you into the problem solving process, which is a win.
E.g. direct asks entangle too much noise from Gatorade-Sprite based cocktail approximations
This works well!
- ease into a knowledge gap without asking “what is
- focus on artificial aspect