This sort of "spec-driven development" was the USP behind AWS Kiro: https://kiro.dev/docs/specs/

> And of course you have to go read the code because I have found it that AI misses polishes

Since you mentioned using other agents, do you get mileage out of code reviews with another agent polishing the unpolished bits? My colleagues swear by it, though I personally remain skeptical about its value without a human reviewer.

> Then I ask another AI

May be synthesis-antithesis-thesis works better in applied computer science... https://en.wikipedia.org/wiki/Dialectic#Criticisms