Agents Building Agents: Reflective Optimization Loops

Learn how AI agents can build and optimize other AI agents through reflective optimization, improving prompts, evaluations, architecture, and model selection for enhanced system development.

Overview

I’ll show how an AI agent can build and optimize another AI agent, using reflective optimization to find issues, optimize evals, iterate on architecture, find the optimal prompt/model, and more.

We’ve built a system with multiple levels of reflective optimization for agent development.

GEPA: reflective prompt optimization
Synthetic eval generation: going from a 1-off bug to an proper eval you can use in reflective optimization
Expanding reflective optimization beyond prompts: model selection, tool use, subagents – reflective optimization can drive all levels of agent optimization.

Links

Tech stack