AgenticFrameworks

AI Agentic Design Patterns with AutoGen

by DeepLearning.AI × Microsoft

IntermediateCourseFree~2 hours

Build conversational multi-agent systems and learn the core agentic design patterns with Microsoft's AutoGen.

Start LearningReviewed July 3, 2026

Overview

Co-created with Microsoft's AutoGen team, this course teaches the recurring design patterns behind capable agents: reflection (agents critiquing their own output), tool use, planning, and multi-agent conversation. You build examples like a coding assistant and a customer-onboarding system where multiple agents converse to solve a task, learning when each pattern pays off.

At a Glance

Topic
Agentic
Level
Intermediate
Format
Course
Cost
Free
Duration
~2 hours
Provider
DeepLearning.AI × Microsoft
Hands-on
Yes — code/exercises
Certificate
None

What You’ll Learn

  • Reflection: agents that critique and improve their own work
  • Multi-agent conversation patterns
  • Planning and tool-use patterns
  • Building a collaborative coding assistant

Highlights

  • Built with Microsoft's AutoGen team
  • Pattern-focused and framework-concrete

Who It’s For

Best For

  • Developers exploring multi-agent conversation designs

Prerequisites

  • Intermediate Python

FAQ

What is AI Agentic Design Patterns with AutoGen?

A hands-on tour of agentic design patterns — reflection, tool use, planning, and multi-agent conversation — implemented in AutoGen.

Is AI Agentic Design Patterns with AutoGen free?

AI Agentic Design Patterns with AutoGen is free to access.

What level is AI Agentic Design Patterns with AutoGen for?

AI Agentic Design Patterns with AutoGen is aimed at a intermediate audience. Recommended background: Intermediate Python.

How long does AI Agentic Design Patterns with AutoGen take?

Expect roughly ~2 hours. Most learners work through it at their own pace.

What will I learn from AI Agentic Design Patterns with AutoGen?

You'll learn: Reflection: agents that critique and improve their own work; Multi-agent conversation patterns; Planning and tool-use patterns; Building a collaborative coding assistant.

Topics

AutoGenagentic patternsmulti-agentreflection