Session 3: Agents - from pipeline to system that decides

11 lessons · Back to full syllabus

What you keep

What an agent really is, how to build the loop by hand, and how to ship one on Google ADK (with LangGraph as an accepted alternative for explicit graph control).

You ship

Your assistant turned into an agent that plans and uses tools, plus a Streamlit UI that demos the loop.

Recommended reading (async)

Multi-agent foundations - watch & read (async)

Before or after the live Session 3 deck, these videos and docs give you production multi-agent patterns and the Claude Agent SDK as a programmable harness - complementary to ADK / LangGraph hands-on work in the lessons below.

Videos

The Multi-Agent Architecture That Actually Ships

Luke Alvoeiro (Factory) at AI Engineer - orchestrators, workers, validators, and validation contracts that hold up in production.

Multi Agent Systems Explained: How AI Agents & LLMs Work Together

IBM Technology - plain-English intro to multi-agent cooperation, structures, and how LLMs + tools fit together.

Live session resources

Lessons

Live

The agent loop, by hand with the raw SDK

Think, pick a tool, call it, observe, decide again - no framework mystification.

Read lesson
Live

Orchestration with LangGraph

Nodes, edges, shared state - durable execution and human-in-the-loop checkpoints.

Read lesson
Live

Tools and MCP

MCP is how modern agents get tools - connect to servers instead of hand-wiring every integration.

Read lesson
Live

Multi-agent and A2A

Several specialists when roles are genuinely separable - most problems do not need multiple agents.

Read lesson
Live

Prompt injection, where guardrails get dangerous

Malicious instructions in retrieved content can hijack tool-using agents.

Read lesson
Deep dive

Build your own MCP server

Tools, resources, and prompts, then a real Python FastMCP server you can wire into Claude Code today.

Read lesson
Deep dive

Build your own A2A integration

Agent Card, skills, and tasks - a minimal A2A server and the client call that reaches it.

Read lesson
Deep dive

LangGraph in depth

Reducers, Command routing, subgraphs, checkpointers, time travel - what the live session does not have time for.

Read lesson
Deep dive

Agent security mitigations

Least privilege, human-in-the-loop, structural separation of instructions from content, sandboxing, and an audit trail.

Read lesson
Async

Session 3 assignment support: Turn your capstone into an agent

Step-by-step: pick the job, build a Google ADK agent with one real tool and a Streamlit UI, prove Think → Act → Observe, then optional stretch (LangGraph accepted as alt).

Read lesson
Assignment

Turn your capstone into an agent

Google ADK agent with at least one real tool and a Streamlit UI - trace each step of the decision loop. LangGraph accepted as alternative. Stretch: HITL, MCP, A2A.

Read lesson