Free Lesson
Evals Your Whole Team Can Run, Not Just the Experts
Part of AI Product Engineering
45 min
Jul 9, 2026 3:00 PM
Virtual (Zoom)
In this video
What you'll learn
Codify your eval process into a reusable skill
How Lucas packaged judge prompts, judge validation, and a human review interface into skills his teammates run on their own, so the process stopped living in one person's head.
Get non-experts running evals, no ML background needed
How Nova Escola's pedagogy team and other PMs started running real evals inside an AI coding agent, and what made the workflow approachable enough to hand off.
Know what to automate and what stays human
Where Lucas leaned on skills versus where expert judgment had to stay in the loop, like error analysis and labeling, and how to make that call on your own product.
Why this topic matters
Most teams have one person who really gets evals, and everything bottlenecks on them. Lucas took Hamel's open-source eval skills and turned them into something his whole team could run. His team uses evals to optimize the WhatsApp assistant Nova Escola ships to teachers across Brazil. We'll show you exactly how, so you can do it on your own product.
You'll learn from
Hamel Husain
ML Engineer with 20+ years of experience
Lucas Machado Rocha
AI Product Manager at Nova Escola