Skip navigation
New Agentic AI short course! AI Agentic Design Patterns with AutoGen, taught by Microsoft Research's…
0:00 / 5:14

New Agentic AI short course! AI Agentic Design Patterns with AutoGen, taught by Microsoft Research's…

Andrew Ng

@AndrewYNg1.9M followers

Visit on X
1,465 likesDownloadOriginal post

218,895 views

New Agentic AI short course! AI Agentic Design Patterns with AutoGen, taught by Microsoft Research's Chi Wang and Penn State's Qingyun Wu (Hiring), shows you how to use AutoGen to implement agentic design patterns like multi-agent collaboration, sequential and nested chat, reflection, tool use, and planning. Learn how to build and combine multiple specialized agents – such as researchers, planners, coders, writers, and critics – that interact to execute complex workflows, like generating detailed financial reports, that would otherwise have taken extensive manual effort. This course illustrates key agentic design principles with many fun demonstrations. For example, you'll build a conversational chess game using two player agents, each of which can use a tool to validate moves and update the board state, while engaging in lively banter about the game! I've enjoyed using AutoGen, and think you will too. Sign up to get started here:

10 Comments

Comments from the original post on X (Twitter)

  • Qingyun Wu's profile picture

    @qingyun_wu

    @MSFTResearch @Chi_Wang_ @penn_state Thank you all for your interest and compliments in this course. Learn more about the AutoGen project here :) and follow the latest updates from the AutoGen OSS community from @autogen_ai

    6 likes

  • Ignacio.-'s profile picture

    @nacho_java

    @MSFTResearch @Chi_Wang_ @penn_state @qingyun_wu impressive what you are doing

    3 likes

  • Key's profile picture

    @KeyFactoryNYC

    @MSFTResearch @Chi_Wang_ @penn_state @qingyun_wu Exciting course! I'm looking forward to learning how AutoGen enables multi-agent collaboration and nested chats. The real-world applications seem promising.

    2 likes

  • NinjaTech AI's profile picture

    @NinjaTechAI

    @MSFTResearch @Chi_Wang_ @penn_state @qingyun_wu What an exciting opportunity for one to enhance their AI skills!

    1 like

  • Tritonix's profile picture

    @Tritonix7

    @MSFTResearch @Chi_Wang_ @penn_state @qingyun_wu What are some of the key agentic design patterns demonstrated in the "New Agentic AI" short course, and how can they be applied to create complex workflows using AutoGen?

    1 like

  • GodZilla's profile picture

    @Jezmond81

    @MSFTResearch @Chi_Wang_ @penn_state @qingyun_wu Oooh I will add this to my list. It just keeps getting bigger. Currently on week 2 of the Advanced Algorithms in your Machine Learning specialisation.

    1 like

  • Vincent Valentine (CEO of UnOpen.ai)'s profile picture

    @BitValentine

    @MSFTResearch @Chi_Wang_ @penn_state @qingyun_wu @AndrewYNg Fascinating concept. How might agentic AI enhance multitasking and decision-making processes?

    1 like

  • AI Zona's profile picture

    @ai_zona

    @MSFTResearch @Chi_Wang_ @penn_state @qingyun_wu AutoGen is not very token efficient, maybe Microsoft has a vested interest to maximize number of tokens used. Agency Swarm and CrewAI seem to be superior products.

    1 like

  • Pablo Marino's profile picture

    @pablomarino_com

    @MSFTResearch @Chi_Wang_ @penn_state @qingyun_wu @DeepLearningAI used to have great content, but now their courses are marketing videos about some product, I don't recommend them. @AndrewYNg newsletter the batch is the best newsletter in the AI field and I do recommend it.

  • OmarOmar's profile picture

    @OmarSaydThat

    @MSFTResearch @Chi_Wang_ @penn_state @qingyun_wu Hey Andrew.. You/Your team sent/spammed this mail after 7th oct attack.. Can you ask your team to send this email again without even changing the context.. I repeat WITHOUT EVEN CHANGING THE CONTEXT!