... prompt optimizer) to code, agent architectures, scheduling policies, and more. Two key ideas: (1) diagnostic feedback (stack traces, rendered images, profiler output) is a first-class API concept the LLM proposer reads to make targeted fixes, and (2) Pareto-efficient search across metrics preserves specialized strengths instead of averaging them away. Results across 8 domains: learned agent skills pushing Claude Code to near-perfect accuracy simultaneously making it 47% faster, cloud scheduling algorithms cutting costs 40%, an evolved ...