2025-11-09 –, Tutorial Track 1
Over the past few years, large language models (LLMs) have transformed the AI landscape, becoming an integral part of our daily workflows. Now, a new wave of AI innovation is emerging: AI agents. These agents go beyond static responses - they can reason, take actions, use tools, and solve multi-step problems, often with minimal human guidance. This evolution is driven by advancements like tool use and the Model Context Protocol (MCP), which enable models to interact with real-world environments. In this hands-on workshop, participants will learn how to build practical, task-oriented AI agents.
This tutorial is designed to give participants a practical understanding of AI agents in action. It will cover various frameworks and include a hands-on session with the LlamaStack framework, highlighting its built-in and MCP-compatible tools, and demonstrating how these components enable agents to interact with external systems. Attendees will also learn how to develop custom MCP tools to extend agent functionality for specific use cases. The session is ideal for developers, data scientists, and AI practitioners looking to move from foundational concepts to real-world implementation.
Outline:
- Quick Recap of Large Language Models
- Introduction to AI Agents and MCP
- Getting Started with LlamaStack
- Using built-in tools and MCP-compatible interfaces
- Hands-On: Building a Basic Agent
- Creating Custom MCP Tools
- Designing Task Workflows and Debugging
- Key Takeaways
Background Knowledge Required:
Beginner-friendly - no prior knowledge needed. Familiarity with LLMs is a plus but not necessary.
No previous knowledge expected
Aarti Jha is a Senior Data Scientist at Red Hat, where she develops AI-driven solutions to streamline internal processes and reduce operational costs. She brings over 6.5 years of experience in building and deploying data science and machine learning solutions across industry domains. She has been an active part of the PyData community and presented at PyData NYC 2024 and PyData Amsterdam 2025.