autoresearch Beyond ML — Optimizing Prompts, Code Performance, and Landing Pages Overnight

autoresearch Beyond ML — Optimizing Prompts, Code Performance, and Landing Pages Overnight

In Parts 1-3, we applied the autoresearch pattern to ML tasks: LLM pretraining, text classification, image classification, and RAG pipelines. But the ratchet loop — modify, run, evaluate, keep or discard — doesn't care what you're optimizing.

In this post, we apply autoresearch to three non-ML problems that developers and marketers deal with every day:

1. System prompt optimization — automatically improve an LLM prompt's accuracy
2. Code performance optimization — make your build faster, your bundle smaller