Build intelligent Multi-Agent applications with AutoGen 0.7

Name: Build intelligent Multi-Agent applications with AutoGen 0.7
Rating: 4.3 (276 reviews)

Master AutoGen 0.6 to Build Scalable, Intelligent Multi-Agent AI Applications for Real-World Tasks

Created byAmit Kumar Thakur

Last updated 9/2025

English

English [Auto],Korean [Auto],

What you'll learn

Understand Multi-Agent Systems – Learn the fundamentals of multi-agent architectures, their advantages, and real-world applications in AI-driven workflows.
Hands-on with AutoGen – Gain practical experience in using AutoGen 0.4 and 0.5 to build and customize intelligent multi-agent applications for problem-solving
Agent Collaboration & Communication – Explore how multiple AI agents interact, share knowledge, and coordinate tasks efficiently using structured protocols
Building Scalable AI Applications – Develop AI solutions for real-world scenarios, such as customer support

Course content

9 sections • 44 lectures • 2h 56m total length

Introduction1:09
Understand what is this course about.
Python installation2:12
Download and setup Visual Studio Code3:42
Download Code Link0:01
Download code and create virtual environment5:50
Download the autogen code from GitHub, extract and rename it, then open visual studio code, create and activate a virtual environment, and install dependencies from requirements.txt.

What are LLM models?1:29
Explore large language models and their interactive use with chatgpt. Learn to connect ai agents to llm services via openai api, azure openai, and olma for llama.
How to decide which LLM model to use?5:54
Create OpenAI Api Key2:52
Run your first code with OpenAI Key5:50
Code explanation of OpenAI client usage with AutoGen4:14
OpenAI Pricing and Tokenization details0:09
Use any Open Source LLM model with AutoGen3:49

What are messages?3:01
Autogen messages enable seamless communication between agents. They include agent-to-agent and internal events types, support text and multimodal content, and show how to define and send messages to coordinate actions.
Demonstrating TextMessage in Action: Sending Messages to AI Agents2:31
The lecture shows defining a text message from the Autogen messages module, setting the user as source, and sending it to an assistant agent powered by a GPT-4 mini LLM.
AutoGen AgentChat: Understanding Agents3:12
Discover the AutoGen 0.6 agent chat framework, importing agents like base chat, assistant, code executor, society of mind, and user proxy, and using methods like own messages and on reset.
Understanding Tool Calling, reflect_on_tool_use, and HandOff4:15
Assistant Agent Explained: Code, Execution, and Deep Dive6:23
Understanding on_messages and run Function: Properties & Usage Explained3:23
Exploring reflect_on_tool_use & Function Calling with code4:58
Examine two ways to use a function as a tool: function calls and the function tool class from Autogen core tools, including reflect on tool use.
UserProxyAgent: Capturing and Managing User Input3:24
Combining Text and Images in Multi-Modal AI Systems3:21
Streaming Agent Messages & Tokens: Real-Time Insights3:19

AI Agent Teams Explained: Definition & Use Cases2:08
Exploring Available Group Chat Teams in AutoGen1:17
Running a Team in Round Robin Fashion6:35
Run a round robin group chat with two agents sharing context and taking turns; draft creates the blog post and the enhancement optimizes for readability and seo, ending with final.
Human in the Loop: Different Ways to Take User Input5:45
Defining When and How AI Agent Teams Should Stop using Termination conditions3:54
Learn how termination conditions govern multi-agent teams, using max message termination condition and text message termination condition to stop at the right moment and prevent output issues.
LLM-Based Agent Selection with SelectorGroupChat2:30
SelectorGroupChat in Action: How It Works8:32
Running Selector Group Chat Code & Custom Selector Function in Action6:53

Project Overview3:48
Project architecture and Frontend code walkthrough for Multi-Agent AI Chatbot6:25
Fast API code walkthrough for Multi-Agent AI Chatbot7:24
Explore how to set up a FastAPI backed multi-agent chatbot by building a lightweight uvicorn server, exposing a chat endpoint, and routing queries through a backend function.
Database and tools code walkthrough for Multi-Agent AI Chatbot5:23
Explore backend architecture in teams.py that configures an agent team, defines product and order databases, and deploys tools for product inquiry, order placement, order status, and complaint registration.
All agents definition code walkthrough for Multi-Agent AI Chatbot3:33
Running code and testing Multi-Agent AI Chatbot portal2:58

Requirements

Python Basics

Description

Microsoft has re-architected the AutoGen framework in version 0.4, and this course is entirely based on the updated version.

The future of AI is multi-agent collaboration, where intelligent agents work together to solve complex tasks efficiently. This course is designed to help you master the AutoGen framework (v 0.4+), a powerful tool for building and orchestrating AI agents that interact, reason, and collaborate. Whether you're an AI enthusiast, a developer, or a researcher, this course will equip you with the skills to build and deploy scalable multi-agent applications.

What You Will Learn

Fundamentals of Multi-Agent Systems – Understand the core components of AI agents, their use cases, and how they enhance AI-driven workflows.
Setting Up Your Development Environment – Learn how to install Python, set up VS Code, create virtual environments, and install necessary dependencies.
Deep Dive into AutoGen – Explore AutoGen’s architecture, libraries, and capabilities, including working with OpenAI and open-source LLaMA models.
Key AutoGen Concepts – Master agent messaging, user proxy agents, assistant agents, streaming responses, and multi-modal AI integration.
Team-Based AI Agent Collaboration – Learn how to organize AI agents into teams, define termination conditions, and implement SelectorGroupChat for LLM-based agent selection.
Advanced Multi-Agent Concepts – Explore state management in AI workflows and dive into Magentic-One, a generalist multi-agent system for web and file-based tasks.
Hands-On Projects – Implement real-world AI agent applications, including:
- Project 1: Develop a Streamlit-based AI Agent App, understand and optimize code with agent
- Project 2: Build a Multi-Agent AI Chatbot for Customer Support that interacts with users of ecommerce portal and processes queries dynamically.

Who Should Take This Course?

AI & ML practitioners looking to build intelligent AI agents
Developers interested in AutoGen, AutoGen AgentChat and AI automation
Researchers exploring multi-agent collaboration
Anyone eager to develop AI-powered applications

By the end of this course, you will have hands-on experience building and optimizing AI-driven multi-agent systems using AutoGen, setting you up to develop next-gen AI solutions.

Who this course is for:

This course is designed for AI enthusiasts, GenAI practitioners, software developers, and machine learning practitioners who want to build intelligent multi-agent applications using AutoGen.

Build intelligent Multi-Agent applications with AutoGen 0.7

What you'll learn

Explore related topics

Course content

Introduction5 lectures • 13min

Introduction to Multi-Agent Systems and Autogen3 lectures • 12min

LLM Models7 lectures • 24min

Important AutoGen Concepts10 lectures • 38min

Project 1 - Streamlit App with AI Agent: Code Walkthrough & Optimization2 lectures • 9min

Teams: Organizing Agents for Collaborative Tasks8 lectures • 38min

Project 2: Multi-Agent AI Chatbot for Customer Support6 lectures • 30min

Advanced Concepts in Multi-Agent Systems2 lectures • 13min

Thank you and further actions1 lecture • 1min

Requirements

Description

Who this course is for: