I've never been able to one-shot a feature with an agent. It's much easier to "learn my way around the codebase" by watching the AI search the codebase and seeing its motivation/mental model.
Going AFK is a terrible idea anyways because I have to intervene when it's making bad architectural decisions. Otherwise it starts randomly deleting stuff or changing the expected results of test cases so they'll pass.
Of course, LLMs might get there eventually. But until then I think it will create a bigger divide between seniors and juniors than it traditionally has been.