Free Lesson
Don't Tweak Prompts. Engineer Agents.
Part of Building Production AI Systems
30 min
Oct 9, 2025 7:00 PM
Virtual (Zoom)
In this video
What you'll learn
Master the Core Eval Loop
Go from staring at a wall of tokens to systematically finding and fixing bugs with a repeatable 5-step process.
Define Actionable Milestones
Break down long, chaotic agent traces into clear, gradable checkpoints to instantly see where things go wrong.
Build Failure Funnels
Use aggregate data to pinpoint the biggest leaks in your agent’s performance and focus your efforts for maximum impact.
Create a Trusted Scoreboard
Ship every new version with confidence by tracking task success, regressions, and costs in one holistic view.
Why this topic matters
Debugging a multi-step agent can feel like navigating a fog. You’re staring at endless traces, unsure if your latest change did anything at all. A magical new model won’t save you. What you need is a systematic process to observe, diagnose, and improve. This lesson provides a proven framework to cut through chaos and help you confidently measure, debug, and refine even your most complex agents.
You'll learn from

Hugo Bowne-Anderson
Podcaster, Educator, DS & ML expert

Skylar Payne
AI made easy. AI executive for startups. Ex-Google. Ex-LinkedIn.
