I've been kicking around an idea and want to read up before I build it.
The idea: you type a rough, half-formed prompt, an LLM works out what you actually mean, and then rewrites it into a specific, optimized prompt tuned for each target model (Claude, GPT, Gemini, etc.).
The Core Insight: The same instruction lands differently on different models. I don't want a single generic "cleaned-up" prompt—I want one explicitly tailored per model.
What I'm Looking For
Before I start building, I'd love to find prior work. Specifically, I'm looking for:
