Welcome to the Agentic Age - Building Intelligent Agents with Azure AI Foundry SDK

Discover how to build autonomous AI agents that reason, plan, and execute complex tasks using Azure AI Foundry SDK. This session highlights Azure's optimized model inference capabilities and agent orchestration, demonstrating how to reduce costs and latency while accelerating development. Through live coding, learn to design effective agent architectures and coordinate multi-agent workflows. Walk away with practical techniques for deploying intelligent agents that solve real business problems at enterprise scale.

GraphRAG in Action with Microsoft Agent Framework & Microsoft Foundry

No PowerPoint, no fluff — just VS Code.

We’ll build a small knowledge graph, implement a GraphRAG workflow, and connect it to an AI agent powered by the Microsoft Agent Framework and Microsoft Foundry. You’ll see how the agent traverses a graph database, interprets relationships, and answers queries over connected data.

Expect real code, real reasoning, and a clear blueprint for building graph-native AI applications.

Foundry IQ for Developers: Agentic Retrieval Without Building Your Own RAG Pipeline

Stop hand-coding RAG plumbing for every agent.

Foundry IQ lets you encapsulate knowledge retrieval into reusable Knowledge Bases backed by Azure AI Search—handling query planning, decomposition, parallel hybrid retrieval (keyword + vector), reranking, and grounded responses with citations out of the box.

In this session, we'll build a minimal but production-real agent using the Microsoft Agent Framework that calls Foundry IQ. From there, we’ll focus on what actually matters to developers: query steering, multi-source retrieval behavior, and getting predictable, structured outputs your agents can reliably reason over and compose.

Expect a tight, code-first walkthrough and practical patterns you can reuse immediately—without reinventing yet another RAG pipeline.

Everyone talks about MCP — but how many teams can actually run it securely in production?

The Model Context Protocol (MCP) is emerging as the de-facto standard for connecting AI agents to tools, APIs, and enterprise systems — a “USB-C for AI” that promises to kill the M×N integration problem.

But production MCP isn’t about demos. It’s about authentication, client identity, and trust boundaries.

In this session, we do a code-first MCP deep dive focused on what teams actually struggle with: secure auth flows, client registration without unsafe dynamic onboarding, token scopes, and clear responsibility between MCP client, host, and server.

Using the Microsoft Agent Framework as an MCP client, we’ll show real patterns that work today — and the pitfalls you need to avoid before MCP hits production.

MCP is easy to demo — and hard to secure. This session is a code-first deep dive into MCP authentication and client design, using the Microsoft Agent Framework as a real MCP client.