Building intelligent applications and integrating AI into modern software is an exciting but complex task. Real-world AI solutions demand much more than Agents defined by prompts, low-code tools, or data science prototypes. Agents require robust architectures, integration flexibility, and intelligent design. In this demo-driven session, you’ll discover how to build AI agents that seamlessly integrate into any type of application, across virtually any platform or operating system. You’ll also learn how to extend agent capabilities using Function Calling with MCP and the RAG algorithm. Even if C#/.NET isn’t your primary focus, this session will help you understand the core concepts behind agents and plugins, empowering you to create your own custom Agents. You’ll also explore Azure Foundry, learn how to work with different AI models, and see how to leverage the Agent Framework and Semantic Kernel to bring intelligent solutions to life. This session is a technical presentation designed for developers, architects, and technical decision-makers.

In this demo-driven engineering session, we will explore the hidden aspects of Generative Artificial Intelligence that go far beyond prompt engineering and basics. The goal of the session is to learn how GenAI works and how to implement various use cases, such as classification, recommendation, and semantic search. We will start with core topics such as tokens, demonstrating how transformers learn associations between them. Next, we will discuss completions to explain how text generation works, providing a deeper understanding of model functionality. Additionally, we will cover embedding vectors, cosine similarity, and vector databases to explain the semantics behind models. Afterwards, you will learn how to expand and manipulate model knowledge using techniques like Retrieval Augmented Generation (RAG). Finally, we will explore different model types and tools such as OpenAI, Azure Foundry and more. This session is a technical presentation designed for anyone interested in understanding and building intelligent applications leveraging large language models.