Getting Started with AutoGen
Published by O'Reilly Media, Inc.
How to build LLM-based AI agents using Microsoft’s AutoGen
Course outcomes
- Learn the basics of working with LLM-based agents
- Gain proficiency in working with AutoGen to build agents that perform tasks like browsing websites, writing research reports, and much more
- Gain the ability to build apps powered by AutoGen LLM agents
Course description
Join expert Lucas Soares to gain the fundamental skills for working with AutoGen, Microsoft’s modern LLM-based agent framework. You’ll explore the foundations of AI agent systems and progressively work through practical use cases, covering all the fundamental functionalities of AutoGen to build agents that can perform complex tasks such as web browsing, research, learning assistance, productivity-related tasks, and much more. By the end of the course, you’ll have acquired the practical skills to create an AutoGen-based agent that can automate the creation of a research report and write, execute, and integrate code into a personal or enterprise system.
What you’ll learn and how you can apply it
- Gain a foundational understanding of AI agent systems
- Build simple LLM-based AI agents that can browse the web and perform research tasks
- Build complex search workflows powered by Autogen Agents
This live event is for you because...
- You’re a software or machine learning engineer, data scientist, software developer (AI engineer) who wants to learn how LLM-based agents work and how to build them using the current best frameworks.
Prerequisites
- Familiarity with Python programming
- Some knowledge of large language models
- A simple working understanding of NLP
Recommended preparation:
- Read chapters 1, 6, and 7 in Natural Language Processing with Transformers (book)
Recommended follow-up:
- Read Language Models in Plain English (report)
- Explore NLP Using Transformers Architectures (video)
Schedule
The time frames are only estimates and may vary according to how the class is progressing.
Agent systems and current frameworks
- Presentation: Agents overview; general framework for building agents
- Demonstration: Building a web browsing agent
- Hands-on exercise: Build a web browsing agent
- Break
AutoGen core concepts and workflow
- Presentation: Building agents with AutoGen; building agents with AutoGen and OpenAI function calling
- Hands-on exercises: Build a simple search agent with AutoGen; build a basic personal assistant agent with AutoGen and OpenAI function calling
- Q&A
- Break
AutoGen agents case studies
- Presentation: AutoGen agent desktop tasks
- Hands-on exercises: Build a researcher agent with AutoGen; build a learning assistant agent with AutoGen
- Q&A
Your Instructor
Lucas Soares
Lucas Soares is an AI engineer who worked as a research assistant at the Champalimaud Neuroscience Institute where he finished his masters working on an application of generative adversarial networks to predict mouse behavior. He switched his focus to industry and worked as a machine learning engineer for K1 Digital and Biometrid, developing computer vision and NLP based applications and gaining experience working with Pytorch. More recently over the last 2 years he has developed expertise working with LLM models, developing applications for his current employer Otovo as well as developing courses for OReilly Media and periodically making technical content about AI for Medium and Youtube.