The only two instances where I didn't manage to achieve satisfactory outcome with AI were when I overspecced ahead of time. The things I left out of the spec were implemented in the most undesired manner possible.
The best mode of work for me was gradually sculpting the prototype into a product by providing feedback and moving to version 2 (from scratch but often with v1 accessible as inspiration) if I felt like it's becoming overbloated.
The best mode of work for me was gradually sculpting the prototype into a product by providing feedback and moving to version 2 (from scratch but often with v1 accessible as inspiration) if I felt like it's becoming overbloated.