Skip to content
hands-on lab

M4: Working with Multiple Agents

Difficulty: Intermediate
Duration: Up to 1 hour and 30 minutes
Students: 13
Start lab
On average, students complete this lab in25m
Get guided in a real environmentPractice with a step-by-step scenario in a real, provisioned environment.
Learn and validateUse validations to check your solutions every step of the way.
See resultsTrack your knowledge and monitor your progress.
About
Author

Description

In this lab, you'll learn how to build a simple multi-agent system using LangGraph’s Swarm library.

You will create two AI agents with different roles who can hand off tasks to each other dynamically — without using any tools. This is perfect for showcasing agent collaboration, decision-making, and handoff logic using just prompts and messages.

By the end of this notebook, you’ll understand how to:

  • Create agents using create_react_agent

  • Connect them in a swarm using create_swarm

  • Enable dynamic handoffs between agents

  • Run a conversation where agents decide who should respond next

Learning objectives

Upon completion of this lab, you will be able to:

  • Create an agent
  • Connect multiple agents together in a swarm
  • Enable dynamic handoffs between agents

Intended audience

  • AI Engineers

Prerequisites

Completion of previous modules is highly recommended before attempting this lab.

Covered topics

Artificial Intelligence
Hands-on Lab UUID

Lab steps

0 of 1 steps completed.Use arrow keys to navigate between steps. Press Enter to go to a step if available.
  1. Starting the Notebooks

Lab Rules