This definitely seems like a potentially powerful approach. The said, maybe I'm missing something obvious, but is the LLM generating both the tests and the implementation? If that's the case, then it seems like there could be issues caused by the generated tests not matching what's specified in the initial prompt. Manually writing highly focused unit tests doesn't seem like the best way to work with this, but being able to manually write some sort of high-level, machine-checkable specs might be useful.