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. ).
Source: [Dev.to](https://dev.to/mathew_woo/anyone-know-prior-research-on-rewriting-a-rough-prompt-per-model-n9f)