I used it (well, a skill based on the same idea) to optimise a prompt that does data extraction from UGC.

However there isn't really a "correct" answer that's easy to define in code (I could manually label a training set, but wanted to avoid that) so I had the LLM just analyse the results itself and decide if they are better or not. It wrote deterministic rules for a few things, but overall it just reviewed the results of each round and decided if the are better or not.

Reviewing the before and after results, I would say yes, it's a big improvement in quality. It also optimised the prompt size to reduce input tokens by 25% and switched to a smaller/cheaper model.