Use LLMs to generate, refine, and optimize prompts — automating the prompt engineering process itself.
Five passes over the same idea, each from a different angle. Do them in order, or jump to whichever you need.
Meta-prompting is using an LLM to write and improve prompts for another LLM (or itself). Techniques include automatic prompt optimization (APO), prompt breeding, DSPy-style compiled prompts, and iterative refinement loops. This is how production systems evolve their prompts beyond what a human would manually write.
