CMU Publishes Free AI Agents Course on YouTube
Carnegie Mellon University is offering free YouTube lectures on AI agents, covering Claude Code, Codex, tools, context compression, evals, and reinforcement learning.
Carnegie Mellon University (CMU) is publishing a free AI agents course on YouTube. The lectures are taught by Graham Neubig, one of the creators of OpenHands, and Daniel Fried.
The course is especially useful because its content closely matches the tools developers use today. It covers topics encountered when working with Claude Code and Codex: tools, skills, context compression, and coding agents.
The practical assignments are interesting too. In the first assignment, a coding agent fixes bugs in a chess application, after which a second agent plays chess in the newly fixed app.
Later assignments focus on evaluating agent quality (evals) and training agents with reinforcement learning (RL). All three assignments are available on GitHub.
Why it matters
AnalysisIt connects AI-agent theory with real coding-agent workflows and provides open hands-on tasks for building, evaluating, and training agents.
Discuss in community
Share your questions and insights with developers