Why do you want to understand the agent generated code though? That would make you the bottleneck. Shouldn’t you just concentrate on checking for optimal outcomes, exhaustively trying to find/prompt edge cases and profiling performance?
If your work has little liability then you can afford to not care beyond “does it work”.
If you have to worry about quality and ensuring you don’t get sued, you make sure the process works.
If it has to maintainable, you you need the mental model to be present in someone’s head.
You are not a serious person if you recommend that.
Check back in a couple years and I’m sure they’ll be there but today’s frontier models 100% absolutely are not ready to fully own a nontrivial production codebase with no human involvement.
I'm a happy little bottleneck, what's wrong with that? How do you even know how to ask it to build stuff for you if you don't understand what foundations are you building on?
Writing commit message (aka. what has changed) gives me a sense of control that I know what's happening and I can confidently build the next thing.