Agentic AI is quickly becoming the next evolution of application development—but building agents that are actually useful in real-world scenarios requires more than just plugging into an LLM.

In this session, we’ll explore how to use the Microsoft Agent Framework to build domain-aware, production-ready AI agents using the concept of Agent Skills. Instead of relying on generic reasoning, Agent Skills enable agents to gain structured domain expertise, making them more reliable, controllable, and enterprise-ready.

We’ll walk through:

What the Microsoft Agent Framework is and how it fits into the modern AI stack
The concept of Agent Skills and how they differ from tools and plugins
How to design and implement reusable, composable skills
Integrating agents with Azure services for real-world scenarios
Best practices for building scalable and maintainable agentic systems

By the end of this session, you’ll have a clear understanding of how to move from simple LLM-based apps to robust, domain-specific agent systems using Azure and Microsoft’s latest agent tooling.