Make your coding agent actually work for you

AI coding agents ship daily. So do models, MCP servers, skills, and extensions you bolt on because someone on X said they're amazing. But every tool you add changes how your agent behaves - and most people have no idea if it's helping or hurting.

In this session, we'll cut through the hype and show you a simple, repeatable way to evaluate what's actually working in your setup. You'll walk out knowing how to measure impact, drop the dead weight, and tune your agent to the way you work. No benchmarks, no ML degree - just a better agent.