Join us for an insightful talk on how autonomous agents can transform how organizations handle incoming email inquiries when integrated with Dynamics 365 Customer Service and Dynamics 365 Contact Center. Discover how leveraging advanced AI technologies can introduce self-service options, streamline ticket creation, and ensure seamless human escalation when necessary. This session will cover: Self-Service Solutions: Learn how autonomous agents can empower customers to resolve their issues independently, reducing the load on human agents and improving response times. Automated Ticket Creation: Explore how AI can automatically generate and categorize tickets from incoming emails, ensuring no customer query goes unnoticed. Efficient Human Escalation: Understand the mechanisms for escalating complex issues to human agents, ensuring that customers receive the personalized attention they need when it matters most. By the end of this talk, you will understand how combining autonomous agents with Dynamics 365 Customer Service can enhance customer satisfaction, optimize operational efficiency, and drive business success.

This session explores advanced design patterns for building resilient multi-agent systems in Microsoft Copilot Studio, focusing on nested (child) agents, connected agents, Agent-to-Agent (A2A) collaboration, and MCP-enabled autonomous agents. Participants will learn how to model roles, capabilities, and boundaries across agents, implement planner/executor and supervisor/child topologies, and apply guardrails for safe scaling. Key topics include: Nested Agents: Lifecycle management, context scoping, memory sharing, and escalation strategies. Connected Agents: Designing stable contracts for plugins/connectors and managing capability registries. A2A Collaboration: Message routing, negotiation, and observability practices for reliable handoffs. MCP Integration: Leveraging Model Context Protocol for capability discovery, permissioning, and safe autonomy. Governance & Safety: Least-privilege design, auditability, and rollout strategies to minimize risk. By the end of the session, attendees will be equipped to design robust multi-agent architectures, enable scalable collaboration, integrate MCP tools, and apply testing and observability practices to improve outcomes. Audience: Solution architects, developers, and technical leads working on Copilot Studio or multi-agent systems. Level: Intermediate with advanced design patterns.

Session Overview Discover how Agent Evaluation and related tools are transforming test automation for custom agents built with Microsoft Copilot Studio. In this 45‑minute session, you’ll get a hands-on introduction to how agent evaluation streamlines development workflows, accelerates testing cycles, and improves overall agent quality. What You’ll Learn Agent Evaluation Explained A concise introduction to the purpose, concepts, and core capabilities of agent evaluation. Key Capabilities A deep dive into the features that distinguish agent evaluation as a foundation for reliable agent testing. Optimizing Development and Testing Workflows Live demonstrations showing how agent evaluation improves efficiency across development, validation, and testing stages. Real-World Use Cases Practical examples illustrating how agent evaluation delivers value in different scenarios and enterprise contexts. Takeaways By the end of the session, you’ll understand how to leverage agent evaluation to: Improve the reliability and consistency of custom agents Reduce development and testing time Confidently scale low-code agent solutions Audience & Level Target Audience: Developers, QA engineers, and technical leads working with Copilot Studio or evaluating automated agent development Level: Intermediate

Session Overview Explore proven design patterns for multi‑agent systems in Microsoft Copilot Studio, including nested (child) agents, connected agents, Agent‑to‑Agent (A2A) collaboration, and MCP‑enabled autonomous agents. In this 45‑minute workshop, you’ll learn how to design, compose, and operate resilient multi‑agent solutions. Through reference architectures, live demos, and practical guardrails, we’ll show how to scale from a single copilot to a governed, multi‑agent topology—while maintaining control, observability, and safety. What You’ll Learn * Multi‑Agent Architecture Fundamentals * How to model roles, capabilities, boundaries, and context across agents. * An overview of key architectural patterns such as planner/executor, broker/worker, and supervisor/child topologies. Takeaways By the end of the session, you’ll be able to: Design robust multi‑agent solutions with clear roles, contracts, and governance Implement nested and connected agent patterns that scale without losing control Enable A2A collaboration with traceable handoffs and measurable reliability Integrate MCP tools to systematically extend agent capabilities Apply testing and observability practices to reduce manual intervention and improve outcomes Audience & Level Target Audience: Solution architects, developers, and technical leads building agents in Copilot Studio or scaling toward multi‑agent and autonomous systems Level: Intermediate (with advanced design patterns).