Abstract: Session Objective: 1. Use practical implementations to demonstrate AI agents in action; 2. Illustrate cutting-edge AI agent applications that seamlessly integrate multiple agents powered by models from OpenAI, Anthropic, Gemini, and open-weight providers, and a diverse range of tools; 3. Explain how to contribute to the thriving AI agent ecosystem.
Learning Outcomes: 1. Understand the agent-oriented programming concepts; 2. Able to construct effective multi-agent systems to solve complex tasks. 3. Reach production-readiness 10x faster.
Target Industry: 1. Industries that require deep research, such as finance, healthcare, science & engineering. 2. Industries involving customer support, such as e-commerce, education, social media; 3. Industries involving heavy software design & development, such as gaming, web, data engineering.
Session Outline:
Research/Analysis/Science use cases: Deep Research Agent, SciAgents, Financial Analysis
Customer-oriented use cases: Travel Planner, Order Management, Realtime ToDo Assistant, Social Media Management, Youth Helper.
Software-oriented use cases: Game Design Agents, Web Agent, Software Testing Agent
Background Knowledge:
Learn basic and advanced agentic design patterns in AG2: 1. Customized GroupChat; 2. Code execution; 3. Deep Research Agent; 4. Swarm; 5. Tool using; 6. Async chats; 7. Dynamic instructions; 8. Realtime Agent; 9. GraphRAG; 10. Structured Output
Bio: Chi is the 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.

Chi Wang, PhD
Title
Founder of AutoGen (Now AG2) | Senior Staff Research Scientist | Google DeepMind


