With my current project (a game project), I full-vibed as hard as I could to test out the concept, as well as get some of the data files in place and write a tool for managing the data. This went great, and I have made technology choices for AI-coding and have gained enough skill with AI-coding that I can get prettttty far this way. But it does produce a ball-of-mud pattern and a lot of cruft that will cause it to hit a brick wall.

Then I copied the tool and data to a new directory and fully started over, with a more concrete description of the product I wanted in place and a better view of what components I would want, and began with a plan to implement one small component at a time, each with its own test screen, reviewing every change and not allowing any slop through (including any features that look fine from a code standpoint but are not needed for the product).

So far I'm quite happy with this.