If you use Claude Code, Cursor, Codex, or similar tools, how do you review the plans they produce?
I’m particularly interested in the last time you approved a substantial change. Did you read the whole plan, skim or like skip straight to reviewing the code?
No. I dont. Stopped maybe around 5-6 months ago.
Most of time I dont really care about the internal AI rationalazations, they are fun to read from time to time. But all in all i just care about the result.
Now I just look at the change log on git and try to keep up with the changes there. I would rather ask why a particular change was done from a side agent.
I also stopped all pleasantries, and now i am more into territory of (caveman/idot) when it comes to prmpting. I do positive reinforcement if I like a particular style of solution or feature.
I check it, because I cant read the code.
Then teat it worked or if it broke anything else.
I check it through because I cant read the code.
Then test it.
Then regression test it.