AI Workshop
Episode 3 of 10Upcoming
How an agent actually works
The «think → call a tool → read the result» loop, the context window, and why an agent suddenly «forgets».
The link arrives by email an hour before the stream
Sign up — a day before we'll send a reminder with the episode plan, and an hour before the start the stream link. The player appears on this page 15 minutes before the start.
What we'll show
- The agent loop step by step on a live task: reasoning, tool call, result, next step
- The agent's tools: reading and editing files, the terminal, search, MCP
- The context window: what goes in, how it fills up, what happens on compaction
- Why a long session degrades and when to start a fresh one
- Reading the agent's log to see where it took a wrong turn
What you take away
A working model of the agent loop — so you predict its behaviour instead of being surprised by it.
Cheat sheet: the agent loop and context
- An agent is a model in a loop: reasoning → tool → result → reasoning again
- Everything the agent «knows» about the project is what's in context: files, command output, CLAUDE.md, your messages
- Long command output eats context: ask the agent to filter (grep, head), not print everything
- One session, one task; a new task means a new session or /clear
- If the agent «forgot» an agreement, it isn't in context — move it into CLAUDE.md
- Read the log: at which step did the agent decide wrong, and what information was missing
Harness in this episode
The harness is what surrounds the loop: what the agent sees going in and what checks the result coming out.
The full harness episodeWhat to have ready
- The setup from episode one
- A project with more than a couple of files