Anyone know prior research on rewriting a rough prompt per model?

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.).

What I'm Looking For

Before I start building, I'd love to find prior work. Specifically, I'm looking for:

• Automatic prompt optimization or prompt rewriting techniques.


• Research on adapting a prompt to a specific target model's quirks and strengths rather than producing a generically better prompt.

Is this already well-studied and I'm just searching the wrong terms?

If you've run across papers, GitHub repositories, or blog posts tackling model-specific prompt adaptation, please drop them in the comments below! What keywords should I actually be searching for?