I’m not so sure. I had a recent experience where Kiro was convinced there was a defect in the testing library when I asked it to refactor some existing project code.

However this conclusion made no sense as we had similar scenarios across our project that worked flawlessly. After intervening I determined the root cause was a combination of an async issue with the production code and some incorrect mocking that was covering up the async issue.

It never occurred to the AI agent to do some simple cross examination before essentially throwing in the towel?

I think uncle bob meant you are not going to type the code anymore, not that you stop coding.

I would argue your example is exactly the reason why you need to supervise AI