AI Evaluations Crash Course | Hamel Husain

Watch now (57 mins) | Hamel shows how to use Claude Code and Codex to find real AI failures, build useful evals, and improve your workflows.

AI Evaluations Crash Course | Hamel Husain

TL;DR

  • Upgrade to unlock live workshops and full access to behindthecraft.com.
  • Gain access to AI courses, skills, tool credits, and workshops.
  • Start with real AI failures, not generic scores.
  • A recording and key takeaways from a recent live workshop are available.
  • Paid subscribers can find all workshop recordings.