Discover how to seamlessly integrate AI applications and agents into Azure AI Foundry using the Model Context Protocol (MCP). In this session, we will explore how MCP enables direct connections to existing knowledge servers and APIs, allowing actions and knowledge to be automatically added and updated within your agents. Learn how this integration simplifies the agent-building process, reduces maintenance efforts, and leverages enterprise security and governance controls such as Virtual Network integration, Data Loss Prevention policies, and multiple authentication methods.

Microsoft Copilot Studio empowers organizations to build conversational agents that streamline work—but what if your business needs domain-specific intelligence beyond the standard models? That’s where Azure AI Foundry comes in. In this session, we’ll explore how to bring your own model (BYOM) from Azure AI Foundry into Copilot Studio, enabling copilots that are fine-tuned to your enterprise data and use cases. You’ll learn how to connect custom or pre-trained models—whether for document processing, forecasting, classification, or vision tasks—directly inside Copilot Studio, and orchestrate them into intelligent workflows. We’ll also cover governance, security, and responsible AI practices to ensure these integrations scale safely across the enterprise. By the end, you’ll see how BYOM unlocks the next level of enterprise-ready copilots—smarter, domain-aware, and tailored to your business needs.

Social media automation is one of the fastest and most practical ways to experience the value of generative AI. In this hands-on session, we’ll build a secure, scalable AI agent that automates social media interactions, specifically LinkedIn, using Azure AI Foundry, Playwright, and Pydantic AI. We'll walk through the architecture of a multi-agent system, explore best practices for secure deployment using Microsoft Purview, Defender for Cloud, and Sentinel, and demonstrate how to integrate browser automation with LLM-based decision-making. Whether you're an enterprise architect or a curious developer, this session will equip you with the tools and insights to build responsible AI agents that operate safely in real-world environments.

Learn how to build an Azure AI Foundry Agent that leverages MCP. In this session we will be using the Foundry Agents Service to build a sales data analytics agent and unlock its capabilities with Model Context Protocol.

Join Jay Parikh, Microsoft EVP of Core AI, as he opens MCP DevDays with an exciting look at how the Model Context Protocol is revolutionizing AI application development. Discover why Microsoft is all-in on MCP and how it's accelerating developer productivity across VS Code, GitHub Copilot, Azure AI Foundry, and Windows. This keynote features lightning demos showcasing real-world MCP implementations. Whether you're a developer, tool builder, or AI enthusiast, this session sets the stage for two days of hands-on learning about the protocol that's defining the next generation of intelligent

MCP is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications. Just as USB-C provides a standardized way to connect your devices to various peripherals and accessories, MCP provides a standardized way to connect AI models to different data sources and tools.

Why MCP? MCP helps you build agents and complex workflows on top of LLMs. LLMs frequently need to integrate with data and tools, and MCP provides:

• A growing list of pre-built integrations that your LLM can directly plug into
• The flexibility to switch between LLM providers and vendors
• Best practices for securing your data within your infrastructure

In this talk, we will discuss how we can use MCP with Azure AI Foundry and Copilot Studio to create AI Agents.

Hands-on workshop focused on building agents with Azure AI Foundry.

Vous prévoyez ou avez déjà implémenté votre IA pour un cas d'usage précis et souhaitez éviter les dérapages tels que les hallucinations, les réponses inappropriées ou les utilisateurs malintentionnés. Nous passerons en revue les éléments à considérer ainsi que les outils de la plateforme Azure (AI Foundry, Content Safety...) pour mieux encadrer votre IA et être plus serein lors de la mise en production.

In this session, we’ll explore how Microsoft Copilot Studio’s AI-driven features streamline the creation of powerful, interactive agents, while also simplifying both the development and design processes. We’ll dive into AI Builder prompts for generative AI capabilities, generative orchestration for intuitive agent design, and generative answers for enhanced user engagement. We’ll also cover integrating Azure AI Foundry models for smarter, more sophisticated solutions.

Session will focus on: practical demonstrations, best practices, and real-world examples of combining Copilot Studio’s AI tools to simplify agent development and enhance user experiences.

What attendees will learn: Hands-on knowledge of seamlessly incorporating AI features into agents, from concept to deployment, using Copilot Studio’s unified environment.

Learn Modules: https://aka.ms/Agents-MicrosoftCopilot https://aka.ms/Studio-Documentation