Skip to content

Day 1 — Foundations of Agent AI with the Claude Agent SDK

Goals for the day

  • Build a shared mental model of what an Agent AI is and isn’t
  • Get everyone’s environment up and running with the Claude Agent SDK
  • Ship a first working agent that uses tools, has memory, and runs in a loop

Agenda

TimeSessionFormat
09:30 – 10:00Welcome, intros, environment checkRound-the-room
10:00 – 11:00What is an agent? Agent vs assistant vs workflowLecture + discussion
11:00 – 11:15Break
11:15 – 12:30Claude Agent SDK — anatomy of an agent (loop, tools, memory)Lecture + live demo
12:30 – 13:30Lunch
13:30 – 15:00Lab 1 — your first agent: tool use + multi-turnHands-on
15:00 – 15:15Break
15:15 – 16:30The tool surface — built-in tools, custom tools, MCP overviewLecture + demo
16:30 – 17:00Day 1 retro, Day 2 previewRound-the-room

What participants will leave with

  • A running local agent that uses at least one custom tool
  • A clear mental model of the agent loop (model → tool → observation → model)
  • An opinion on when not to use an agent (the most underrated lesson)

Materials

  • Slide deck: link TBD
  • Lab 1 starter repo: link TBD
  • See References for SDK docs

Attendees

  • NBS: TBD
  • MetaWeave: TBD

Decisions

  • Captured live during the session.

Action items

  • Owner — action — due