Week 3 (Friday): Agents - from pipeline to system that decides
6 lessons · Back to full syllabus
What you keep
What an agent really is, how to build the loop by hand, and how to orchestrate one reliably.
You ship
Your assistant turned into an agent that plans and uses tools.
Lessons
Live
The agent loop, by hand with the raw SDK
Think, pick a tool, call it, observe, decide again - no framework mystification.
Live
Orchestration with LangGraph
Nodes, edges, shared state - durable execution and human-in-the-loop checkpoints.
Live
Tools and MCP
MCP is how modern agents get tools - connect to servers instead of hand-wiring every integration.
Live
Multi-agent and A2A
Several specialists when roles are genuinely separable - most problems do not need multiple agents.
Live
Prompt injection, where guardrails get dangerous
Malicious instructions in retrieved content can hijack tool-using agents.
Assignment
Turn your capstone into an agent
LangGraph agent with at least one real tool - trace each step of the decision loop.
Lessons in this module