This talk was recorded at NDC Copenhagen in Copenhagen, Denmark. #ndccopenhagen #ndcconferences #developer #softwaredeveloper    

Attend the next NDC conference near you: 
https://ndcconferences.com
https://ndccopenhagen.com/

Subscribe to our YouTube channel and learn every day:   
/        @NDC 

Follow our Social Media!

https://www.facebook.com/ndcconferences
https://twitter.com/NDC_Conferences
https://www.instagram.com/ndc_conferences/

#ai #genai #microsoft 

AI Agents have been a fast-growing pattern among AI devs but have since become more relevant and attainable to every developer!

This session aims to equip you with both the theory and the practical knowledge required for getting started with building AI Agents on Azure. We will cover the fundamentals of AI agents, their applications, and how they can work together in multi-agent systems to solve complex problems. Then, we build some AI Agents using the open-source framework Semantic Kernel and test them live.

At the end of the session, you will be able to answer these questions:
Why is agentic AI becoming a trend?
What are popular frameworks for building AI Agents?
Why have more than one agent?
How to actually get started?

This session is designed for developers and AI enthusiasts who are eager to dive into the world of intelligent agents and their collaborative capabilities. We will use code in Python but equivalent code is available for .NET and Java as well.

NDC Conferences

AI agents represent the evolution beyond simple chatbots by possessing agency—the ability to autonomously determine when and which tools to use. Building effective AI agents requires a language model, instructions, tools, and orchestration to connect these components. The session demonstrates building single agents with Semantic Kernel (Microsoft's orchestration framework available in Python, .NET, and Java), adding plugins/functions for tool calling, integrating MCP servers for browser automation, and creating multi-agent systems using group chat orchestration. Azure AI Foundry Agent Service offers cloud-hosted agent orchestration with persistent state, easy integration with Logic Apps and Microsoft Graph, and connected agent capabilities. Multi-agent patterns include concurrent, sequential, handoff, and group chat approaches, enabling agents with different motivations and tools to collaborate—mirroring human organizational structures to avoid conflicts of interest.

Building AI Agents and Multi-Agent Systems with Azure AI - Henri Schulte - NDC Copenhagen 2025