autoresearch Beyond ML — Optimizing Prompts, Code Performance, and Landing Pages Overnight
Apply the autoresearch pattern to non-ML problems. Working code for system prompt optimization, code performance optimization, and landing page copy optimization.
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:
- System prompt optimization — automatically improve an LLM prompt's accuracy
- Code performance optimization — make your build faster, your bundle smaller
Related Posts
CLAUDE.md Templates for Five Project Types — Copy, Paste, and the Rules That Actually Change Agent Behavior
Five CLAUDE.md/AGENTS.md templates — Next.js, Python ML, monorepo, data pipeline, research notebook — plus which lines agents actually obey and how to use a rules file to govern side effects.
Mobile Claude Code: three approaches, and what actually works
Three ways to reach Claude Code from your phone — tmux + SSH, /remote-control, and server-based agents. The real fix isn't "mobile support" but decoupling compute from your device.
Inside Google COSMO — The New Architecture of On-Device AI Agents
Deep-dive into COSMO, Google's next-gen AI assistant accidentally leaked before I/O 2026. Full breakdown of the 3-mode architecture: Gemini Nano + PI server + Hybrid routing.