AI Agents — From Basics to Multi-Agent Systems

What is an AI Agent?

Understand the key difference between a chatbot and an agent, and learn the four components every agent is built from.

The Agent Loop — ReAct

Follow a complete agent trace through the ReAct pattern and understand how stopping conditions prevent agents from running forever.

Tools and Function Calling

Define tools with the Anthropic API, build the minimal agent loop from scratch, and apply the four principles that make tools reliable.

Single-Agent Patterns

Build three single-agent patterns using LangGraph and learn when each one is appropriate.

Memory — What Agents Remember

The four types of agent memory and how to choose the right one for your use case.

Multi-Agent Systems

Why multiple specialised agents outperform one generalist, and how to build the three core multi-agent patterns with LangGraph.

Agent Frameworks

LangGraph, CrewAI, AutoGen, Agno, Swarm, and Smolagents — strengths, trade-offs, and a working code example for each.

Observability with Langfuse

Set up Langfuse, wire it to a LangGraph agent in one line, and learn exactly what to track in every agent run.

Human-in-the-Loop

Classify actions by risk, implement LangGraph's interrupt pattern, and build a trust level system that pauses before any irreversible action.

Hands-on Project: Multi-Agent Research Pipeline

Build a complete Researcher → Writer → Publisher pipeline with Langfuse observability and a human approval gate before anything is published.