I've found this to be the case as well. My typical workflow is:

1. Have the ai come up with an implementation plan based on my requirements

2. Iterate on the implementation plan / tweak as needed, and write it to a markdown file

3. Have it implement the above plan based on the markdown file.

On projects where we split up the task into well defined, smaller tickets, this works pretty well. For larger stuff that is less well defined, I do feel like it's less efficient, but to be fair, I am also less efficient when building this stuff myself. For both humans and robots, smaller, well defined tickets are better for both development and code review.

Yeah, this exactly. And if the AI wanders in confusion during #3, it means the plan isn’t well-defined enough.