[NewUser76312]

I'm still not sold on these "AIs in your codebase" tools. Same for 'vibe coding'.

I use AI like a scalpel - I go in and figure out exactly what I want, use my prompting experience to get a few functions, or up to 1 script at a time, read it, put it in, and stress-test it immediately.

As a result, I am extremely happy with my AI-generated code about 95% of the time. However, this requires that I still understand my codebase, requirements, failure modes, etc.

My philosophy is that software dev creation speed is certainly important, but durability is even more critical. Currently, it seems like going too deep with these AI tools is sacrificing the former for the latter. If all you're doing is POCs all day I could see it (even then, don't let them get too big...) but it's just not for me, at least not yet.

[_sharp]

You should consider documenting your durability requirements, failure modes, important context related to the feature/component your working on, as you would a junior engineer. Then, you can re-use the context documents. If the AI doesn't know what your expectations are, it will just assume you need a PoC, and give you PoC code quality.