We're creating a new course on AI Agents at CMU this Fall!
- Source
- x.com
- Date
We're creating a new course on AI Agents at CMU this Fall! We’re aiming to give students hands-on experience: from building agentic harnesses and evals to training with RL. Check out our course site for the full schedule: https://t.co/DW9J20fpZD https://t.co/wKn89YDx60
Context
The Fall 2026 AI Agents course at Carnegie Mellon University aims to teach students how to build systems that act across multiple steps. Instructor Daniel Fried connects practical work on harnesses, evaluations and reinforcement learning in the announcement, describing a progression from building the software around a model to testing and improving its behavior.
The course overview makes the target concrete: agents call tools, navigate interfaces and write code while working toward a task. Its emphasis is on implementing those systems and studying their training, safety and interaction with people. The syllabus aims it at graduate students who already have experience training neural language models.
- AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Checking sign-in…
Loading comments…