Mastering Real-World Agentic AI Applications with AG2 (AutoGen)
23 August 2025 | 09:30AM - 05:30PM
About the workshop
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
- API keys for language models (OpenAI, Anthropic, etc.)
- Code editor of choice
- Virtual environment management (venv, conda, etc.)
Modules
Kick things off with an overview of what AI agents are and why they matter. Understand the agent paradigm, its evolution, and its value in modern applications.
Learn how to install, set up, and run your first AG2-based agent. Get hands-on exposure to the AG2 interface and starter agent templates.
Dive into the AG2 framework’s architecture, from agent definitions to message routing. Explore the role of core components like GroupChat, ToolCall, and UserProxyAgent.
Discover reusable agent design strategies for tasks like tool orchestration and memory. Learn how to implement patterns for robustness, coordination, and decision-making.
Create agents tailored to domain-specific workflows and user needs. Use AG2’s flexible config system to define logic, tools, and behaviors.
Learn how to connect agents with APIs, databases, and services via the MCP layer. Understand plugin systems and dynamic tool usage in real-time agent tasks.
Hands-On: Integrate your agent with external data sources and tools via MCP
Package and launch your agent using FastAgency’s deployment pipeline. Explore production-ready configurations, logging, and scalability tips.
Hands-On: Prepare an agent application for production deployment
- Customer support automation
- Market research and competitive analysis
- Content generation and marketing
- Financial analysis and reporting
- Hands-On: Build a complete agent solution for a business scenario
Wrap up with proven strategies to ensure reliability, security, and maintainability. Look ahead at emerging trends and what’s next for agent ecosystems.
Open floor for questions, feedback, and discussion. Recap the day’s learnings and share resources for continued development.
