Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Building Agentic LLM Workflows with AutoGen
Search
Daron Yondem
February 24, 2025
Programming
0
8
Building Agentic LLM Workflows with AutoGen
This is the deck I have presented at Intel AI Dev Summit 2025.
Daron Yondem
February 24, 2025
Tweet
Share
More Decks by Daron Yondem
See All by Daron Yondem
Solo to Scale,Building a People-First Engineering Culture
daronyondem
0
22
AI Prototyping to Productionwith Promptflow
daronyondem
0
55
Retrieval Augmented Generation
daronyondem
0
240
Azure OpenAI
daronyondem
0
210
FaaS for Everyone, Everywhere
daronyondem
0
150
Skyrocketing Developer Velocity
daronyondem
0
92
What’s in Azure for Your Mobile Projects?
daronyondem
0
72
Azure Applied AI and AutoML
daronyondem
0
90
Serverless + APIM
daronyondem
0
92
Other Decks in Programming
See All in Programming
お前もAI鬼にならないか?👹Bolt & Cursor & Supabase & Vercelで人間をやめるぞ、ジョジョー!👺
taishiyade
7
4.1k
負債になりにくいCSSをデザイナとつくるには?
fsubal
10
2.5k
責務と認知負荷を整える! 抽象レベルを意識した関心の分離
yahiru
8
1.2k
DRFを少しずつ オニオンアーキテクチャに寄せていく DjangoCongress JP 2025
nealle
2
180
クリーンアーキテクチャから見る依存の向きの大切さ
shimabox
4
880
Djangoにおける複数ユーザー種別認証の設計アプローチ@DjangoCongress JP 2025
delhi09
PRO
4
380
ファインディLT_ポケモン対戦の定量的分析
fufufukakaka
0
840
ソフトウェアエンジニアの成長
masuda220
PRO
12
2k
バッチを作らなきゃとなったときに考えること
irof
1
410
Amazon S3 TablesとAmazon S3 Metadataを触ってみた / 20250201-jawsug-tochigi-s3tables-s3metadata
kasacchiful
0
180
DROBEの生成AI活用事例 with AWS
ippey
0
140
Djangoアプリケーション 運用のリアル 〜問題発生から可視化、最適化への道〜 #pyconshizu
kashewnuts
1
250
Featured
See All Featured
Site-Speed That Sticks
csswizardry
4
390
Bootstrapping a Software Product
garrettdimon
PRO
306
110k
Designing for humans not robots
tammielis
250
25k
It's Worth the Effort
3n
184
28k
Helping Users Find Their Own Way: Creating Modern Search Experiences
danielanewman
29
2.4k
Keith and Marios Guide to Fast Websites
keithpitt
411
22k
Distributed Sagas: A Protocol for Coordinating Microservices
caitiem20
330
21k
CSS Pre-Processors: Stylus, Less & Sass
bermonpainter
356
29k
4 Signs Your Business is Dying
shpigford
182
22k
[RailsConf 2023] Rails as a piece of cake
palkan
53
5.3k
CoffeeScript is Beautiful & I Never Want to Write Plain JavaScript Again
sstephenson
160
15k
Music & Morning Musume
bryan
46
6.4k
Transcript
Building Agentic LLM Workflows with AutoGen Daron Yöndem Tech Lead
for Application Innovation Microsoft http://daron.me @daronyondem
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
Foundations of Agentic LLM Workflows • Autonomy • Collaboration •
Adaptability
AutoGen Architecture • A unified conversation framework for multi-agent interactions
• Assistant Agents + User Proxy Agents • As simple as it sounds.
Categories of Design Patterns for Agents • Reflection • Tool
Use • Planning • Multi-agent collaboration
Reflection
Tool Use
Planning
Multi-Agent Collaboration
Single-Agent Task DEMO
From Single to Multi-Agent • Easy Agent Orchestration • State
and Memory • Tool Integration • Error Handling & Control
Multi-Agent Problem Solving / Research Assistant DEMO
Advanced AutoGen Workflows • Extending Agent Abilities (Skills/Tools) • Incorporating
Multiple Models • Custom Prompts & Behaviors • Memory and Context
Complex Multi-Agent Orchestration DEMO
Real-World Applications • Customer Support • Automation & Scripting •
Knowledge Assistants
Challenges and Limitations • Complexity • Cost and Performance •
Reliability
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
Thanks http://daron.me | @daronyondem Grab slides on http://decks.daron.me/