Slide 1

Slide 1 text

Building Agentic LLM Workflows with AutoGen Daron Yöndem Tech Lead for Application Innovation Microsoft http://daron.me @daronyondem

Slide 2

Slide 2 text

Welcome! • Why Agentic Systems Matter? • AutoGen: An Open Source Multi Agent Framework that can operate agents autonomously or collaborate with humans. • AG2 – Fork of AutoGen 0.2 • Microsoft AutoGen 0.4

Slide 3

Slide 3 text

Foundations of Agentic LLM Workflows • Autonomy • Collaboration • Adaptability

Slide 4

Slide 4 text

AutoGen Architecture • A unified conversation framework for multi-agent interactions • Assistant Agents + User Proxy Agents • As simple as it sounds.

Slide 5

Slide 5 text

Categories of Design Patterns for Agents • Reflection • Tool Use • Planning • Multi-agent collaboration

Slide 6

Slide 6 text

Reflection

Slide 7

Slide 7 text

Tool Use

Slide 8

Slide 8 text

Planning

Slide 9

Slide 9 text

Multi-Agent Collaboration

Slide 10

Slide 10 text

Single-Agent Task DEMO

Slide 11

Slide 11 text

From Single to Multi-Agent • Easy Agent Orchestration • State and Memory • Tool Integration • Error Handling & Control

Slide 12

Slide 12 text

Multi-Agent Problem Solving / Research Assistant DEMO

Slide 13

Slide 13 text

Advanced AutoGen Workflows • Extending Agent Abilities (Skills/Tools) • Incorporating Multiple Models • Custom Prompts & Behaviors • Memory and Context

Slide 14

Slide 14 text

Complex Multi-Agent Orchestration DEMO

Slide 15

Slide 15 text

Real-World Applications • Customer Support • Automation & Scripting • Knowledge Assistants

Slide 16

Slide 16 text

Challenges and Limitations • Complexity • Cost and Performance • Reliability

Slide 17

Slide 17 text

Further Learning AutoGen Discord - https://aka.ms/autogen-discord Magentic One • MultimodalWebSurfer, FileSurfer, and MagenticOneCoderAgent - https://aka.ms/magentic-one Code Samples used in this session • https://drn.fyi/codesamples

Slide 18

Slide 18 text

Thanks http://daron.me | @daronyondem Grab slides on http://decks.daron.me/