Chi is founder of AG2 (formerly known as AutoGen), the open-source AgentOS to support agentic AI, and its parent open-source project FLAML, a fast library for AutoML & tuning. He has received multiple awards such as best paper of ICLR’24 LLM Agents Workshop, Open100, and SIGKDD Data Science/Data Mining PhD Dissertation Award. Chi runs the AG2 community with 20K+ members. He has 15+ years of research experience in Computer Science and work experience in Google DeepMind, Microsoft Research and Meta.
In this hands-on technical workshop, you'll master the fundamentals of building production-grade AI agent applications with AG2 (formerly AutoGen), a lending open-source AI Agent framework that is adopted by millions of users and downloaded over 700k times per month.
You'll explore essential AI agent design patterns and discover how to customize agents for specific domains using reference implementations from the AG2 team. You'll also learn production deployment strategies using FastAgency and build complete agent solutions for real business scenarios.
Through guided exercises, you'll develop AI agent systems that can tackle real-world applications like customer support, marketing research, and data analysis. By the end of the day, you'll have the knowledge to build specialized, scalable agent applications that deliver reliable results in production environments.
What You’ll Learn
- Fundamentals of AI Agents: Understand the core concepts and architecture of agent-based AI systems
- AG2/AutoGen Framework: Master the key components and capabilities of AG2 framework
- AI Agentic Design Patterns: Key AI Agent design patterns
- Customized Agent Creation: Build specialized agents for specific tasks and domains. Learn from reference agents built by the AG2 team.
- Integration Strategies: Connect your agent systems with external tools and APIs, and MCPs
- Development: Build specialized agents for specific tasks and domains
- Practical Applications: Apply agent technology to real-world use cases
- Best Practices: Optimize agent performance and reliability in production environments
Prerequisites
- Basic Python programming knowledge
- Familiarity with LLMs
- GitHub account for accessing workshop materials
- Local development environment with Python 3.9+
Technical Requirements
- Python 3.9 or higher
- Git
- Code editor of choice
- Virtual environment management (venv, conda, etc.)
Discover how multi-agent systems are revolutionizing AI performance beyond single-model limitations. Built on insights from AG2, Gemini Deep Think, Grok Heavy, and "Myth of Reasoning", MassGen orchestrates diverse AI agents (Claude, Gemini, GPT, Grok) to collaborate in real-time, mimicking human "study group" dynamics.
This session will showcase the architecture that enables cross-model/agent synergy, parallel processing, and iterative refinement through live demonstrations including creative writing consensus, travel planning intelligence sharing, and complex problem-solving. Learn how agents naturally converge on superior solutions through collaborative reasoning rather than isolated thinking. We'll demonstrate the open-source framework, share real case studies, and explore the future of recursive agent bootstrapping. Join us to see how the next evolution of AI isn't about bigger models, it's about smarter collaboration.
Managing and scaling ML workloads have never been a bigger challenge in the past. Data scientists are looking for collaboration, building, training, and re-iterating thousands of AI experiments. On the flip side ML engineers are looking for distributed training, artifact management, and automated deployment for high performance
Read MoreManaging and scaling ML workloads have never been a bigger challenge in the past. Data scientists are looking for collaboration, building, training, and re-iterating thousands of AI experiments. On the flip side ML engineers are looking for distributed training, artifact management, and automated deployment for high performance
Read More