AI Agent Evals: The 4 Layers Most Teams Skip
Most teams evaluate AI agents by vibes. Here are the four layers of evals you actually need to ship agents with confidence.
I walk through the eval stack I use on real agent projects — from unit-level prompt checks up through end-to-end trajectory scoring — and explain where each layer catches different classes of failure. If you’re building agents for production and wondering why regressions keep slipping through, this is the framework to borrow.
Building an AI agent?
I help teams design and ship agentic systems — from architecture to production.
See how I can help
I Added ACP to My Mastra Agent So It Can Work in Repos
ACP is the layer that lets my Mastra agent hand real repo work to Claude Code instead of stopping at advice.
Stop Giving Your Agent Every Tool
Large tool catalogs break agent context. Tool search fixes that by letting agents discover and load only what they need.
Stop Letting AI Agents Run the Whole Workflow
One inbox agent should not classify, research, score, route, and draft replies in one loose loop.
Harness Engineering: 4 Levers to Diagnose Any AI Agent
Most agent failures aren't model failures. They're harness failures. Here's the 4-lever framework I use to diagnose what broke.
Get new videos and posts by email
Weekly videos on AI engineering, plus deeper dives in the newsletter.
Occasional emails, no fluff.