Every tool I've tinkered with that hints at one-shotting (or one-shot and then refine) ends up with a messy app that might be 60-70% of what you're looking for but since the foundation is not solid, you're never going to get the extra 30-40% of your initial prompt, let the multiples of work needed to bolt of future functionality.

Compare that to the approach you're using (which is what I'm also doing), and you're able have have AI stay much closer to what you're looking for, be less prone to damaging hallucinations, and also guide it to a foundation that's stable. The downside is that it's a lot more work. You might multiply your productivity by some single digit.

To me, that 2nd approach is much more reasonable than trying to 100x your productivity but actually end up getting less done because you end up stuck in a rabbit hole you don't know you're in and you'll never refine your way out of it.

I got stuck in that rabbit hole you mention. Ended up ditching AI and just picked up a no/low-code web app builder cause I don’t handle large project contexts in my own head well enough to chunk design into tasks that AI can handle. But the builder I use can separate the backend from the front end which allows for a custom front end template source code to be consumed by an ai agent if you want. I’m hoping I can manage this context better but I still have to design and deploy a module to consume user submitted photos and process with an ai model for instant quote generation