In the era of intelligent agents and generative AI, data is not just an input - it is the differentiator. This session focuses on the strategic importance of data in designing, building, and deploying high-performing AI agents. Whether you're using Microsoft Copilot Studio, Azure AI services, or building custom RAG (Retrieval-Augmented Generation) pipelines, the success of your solution hinges on how well your data is curated, connected, and consumed. We’ll explore end-to-end data strategies — from identifying the right data sources to optimizing them for retrieval and grounding. We'll also discuss how semantic search, vector databases, metadata enrichment, and feedback loops contribute to relevance, accuracy, and adaptability in AI agents. Key Takeaways: -Understand the data lifecycle in AI agent development -Learn how to identify, structure, and prepare enterprise data for grounding and RAG -Explore best practices for data governance, compliance, and quality -Discover how to use vector search and semantic indexing for better contextual responses -Design feedback loops for continuous learning and improvement of AI outcomes Join us to uncover why great AI agents begin with great data - and how a solid data strategy can elevate your AI initiatives from functional to truly intelligent.

Today, data professionals are expected to do more than just manage and transform data-they need to unlock intelligence, automation, and actionable insights from it. In this session, we’ll explore how Microsoft Fabric makes data engineering simpler with powerful pipelines, and how these pipelines can feed AI-powered Data Agents. These agents don’t just analyze data—they reason over it, provide contextual insights, and surface intelligence through Power Platform apps, Copilot Studio, and AI Foundry, making insights and actions accessible to both internal and external users. Through a live, step-by-step demo, you’ll see how to: -Build a Fabric data pipeline to ingest, clean, and transform raw data -Publish curated data into a Lakehouse and semantic model for business-ready insights -Create a Data Agent that can reason over Fabric data -Connect the agent to Copilot Studio, and AI Foundry, enabling intelligence and automation to flow into apps, workflows, and external systems This session is designed for data professionals familiar with SQL and analytics platforms who want to take their skills to the next level—moving from pipelines and dashboards to intelligent, agent-driven solutions. Attendees will leave with practical knowledge and a clear roadmap to turn their data into actionable AI-powered experiences. Key Takeaways -Understand Microsoft Fabric’s role as the backbone for intelligent data solutions -Learn how to build and orchestrate scalable Fabric pipelines -Discover how to create AI-powered Data Agents that interact with enterprise data -See how to connect agents with Copilot Studio, and AI Foundry to expose intelligence externally -Gain hands-on, demo-driven insights to implement agentic data solutions in real-world projects

As organizations adopt AI to drive productivity, the future lies not in a single chatbot or Copilot—but in networks of intelligent agents working together. With Microsoft Copilot Studio’s new capability to connect agents to agents, we can now design distributed systems where specialized copilots collaborate, delegate, and orchestrate tasks seamlessly. In this session, we’ll walk through building multiple connected agents in Copilot Studio that integrate with Power Automate Flows, AI Builder prompts, and Power Apps to deliver a truly end-to-end intelligent solution. Attendees will learn how to design agent roles, establish communication flows, and embed AI-driven decision-making into their Copilots to solve complex, real-world business scenarios. Whether you’re a maker, developer, or IT leader, you’ll leave with practical insights and design patterns for scaling beyond a single Copilot—unlocking the power of collaborative AI agents across the Microsoft ecosystem. Key Takeaways - Learn how to design multi-agent architectures in Copilot Studio - See how agent-to-agent communication unlocks more complex and dynamic workflows - Understand how to integrate Power Automate Flows, AI Builder prompts, and Power Apps with your copilots - Explore real-world use cases where connected agents boost productivity and collaboration - Gain practical tips for scaling and governing multiple AI agents in enterprise environments

What This session explores how to design and implement multi-agent AI systems using MS Foundry Agent Service, where multiple specialized agents collaborate to solve complex real-world problems. The focus is on moving beyond single chatbots to role-based agents that work together with clear responsibilities. Why Many enterprise AI scenarios require coordination between capabilities such as data retrieval, reasoning, and task execution. A single agent often becomes difficult to scale and manage. Multi-agent architectures provide a structured way to divide responsibilities, improve reliability, and enable more intelligent automation. How Through a hands-on demonstration built using MS Foundry Agent Service, the session will show how agents can be designed with specific roles, connected together, and orchestrated to collaborate while maintaining context. The talk will highlight practical architecture patterns, communication flows, and key considerations for building scalable agent-based systems. For Whom This session is designed for AI engineers, developers, architects, and solution designers who want to understand how to build real-world agentic systems and implement collaborative AI agents in enterprise solutions using MS Foundry. Key Takeaways -Understand how multi-agent architectures enable specialized AI agents to collaborate instead of relying on a single monolithic agent. -Learn how to define clear roles and responsibilities for agents such as retrieval, reasoning, and task execution. -See how agent orchestration and communication patterns enable agents to work together while maintaining shared context.

Building an AI agent is easy, but managing it across development, testing, and production environments is often the real challenge. As organizations adopt agents built with Microsoft Copilot Studio, they need structured processes to deploy updates, manage configurations, and ensure stable releases. This session introduces Application Lifecycle Management (ALM) practices for Copilot Studio agents using solutions in the Microsoft Power Platform. We will explore how agents, flows, and integrations can be packaged and promoted across environments while maintaining proper governance and change control. Through a live demo, we will build an agent in a development environment and promote it to test and production, demonstrating how ALM helps teams manage agent deployments reliably at enterprise scale. Key Takeaways • Understand Application Lifecycle Management (ALM) concepts for AI agents • Learn how to structure Copilot Studio agents using solutions • Safely promote agents across Dev to Test to Production environments • Manage configuration using environment variables and connection references • Implement deployment pipelines to support enterprise change management