Inside the Agent: Demystifying LLM Agents in Practice
This hands-on workshop will help researchers build a stronger intuition for what is happening under the hood of modern LLM-powered agents. We'll begin with developing a practical mental model for how large language models work as next-token predictors, and use this model to understand the API endpoints and requests that agents use.
Participants will explore concepts like the agentic loop, how tools are exposed, how skills work, and discuss practical considerations around security and caching.
To develop experience with these concepts, we will write simple agents in Python, so some programming experience is useful.
Live Workshop
Session #1 for Summer 2026
Date: Friday, July 10, 2026
Time: 1:00 PM — 3:00 PM (2 hours)
Location: Zoom