While interesting, the fact that it doesn't output code is worrisome. This because the function is no longer idempotent, each call to the AI can yield a different result.
Sketch is similar, but can do code generation (with `.sketch.howto`): https://github.com/approximatelabs/sketch
> This because the function is no longer idempotent, each call to the AI can yield a different result.
Also, it makes it harder to verify correctness, and may make processing larger datasets (or repeatedly processing similar datasets) more expensive.