Voice is the most natural interface—and now you can bring it to life with Azure AI Foundry and the Realtime API. In this session, you’ll learn what it takes to design, build, and deploy intelligent voice agents that can hold fluid, multi-turn conversations in real time. We’ll explore why real-time voice matters for customer support, virtual assistants, and interactive applications, and how Azure AI Foundry makes it possible to combine speech recognition, synthesis, and custom models into one seamless experience. Through a live demo, you’ll see how to set up a Realtime API connection, stream audio in and out, and orchestrate responses that sound natural and human-like. We’ll also share best practices for latency, accuracy, and scaling your voice agents in production. Who should attend: Developers, solution architects, and innovators who want to move beyond text-based bots and deliver next-generation AI experiences powered by voice.

As organizations embrace AI to transform the way they work, securing sensitive data and ensuring regulatory compliance are more critical than ever. In this 60-minute, demo-driven session, we’ll explore how Microsoft Defender and Microsoft Purview work together to protect your AI ecosystem — from safeguarding data in prompts and responses to managing risk and maintaining compliance across your environment. Through a series of real-world demonstrations, you’ll see how to: Discover and classify sensitive data before it’s exposed to AI tools. Enforce security and compliance policies in real time during AI interactions. Detect, investigate, and respond to AI-related risks using advanced security capabilities. Build a proactive data security posture that supports innovation without compromise. Whether you’re an IT professional, security specialist, or compliance leader, this session will give you practical insights and hands-on examples you can apply immediately to secure your organization’s AI journey.

As Copilot Studio usage expands, a Center of Excellence (CoE) is key to managing growth, maintaining governance, and driving adoption. This session shows how to design and run a CoE to standardize development, enforce security and compliance, and accelerate innovation. Learn how to define roles, set up review processes, create reusable assets, and embed best practices so copilots can scale reliably across the organization. Who should attend: Platform leads, CoE teams, enterprise architects, and governance owners. Why attend: Gain a practical framework to transform Copilot Studio from isolated projects into a secure, scalable enterprise capability.

What A demo-driven, architecture-focused session showing how to build a Copilot Studio agent that connects directly to Microsoft Dynamics 365 Business Central using the Model Context Protocol — entirely through the GUI with no custom code required. Why Business Central holds some of the most business-critical data in any organisation — yet accessing it conversationally through an AI agent has historically required complex custom development. MCP changes that fundamentally by giving Copilot Studio a standardised, secure, and configuration-driven way to talk to Business Central directly. This session bridges the gap between BC practitioners and Copilot Studio developers live, end to end, with real data and real business scenarios attendees can replicate the very next day. How - Architecture overview of how MCP bridges Copilot Studio and Business Central including the authentication flow through the built-in Power Platform connector - Live demo configuring the BC MCP connection — adding the MCP server, authenticating, and verifying live data access - Live demo building the agent across real BC business scenarios — balance enquiries, General Ledger payments, and sales quote creation against a live BC environment - Live model comparison switching the same agent between GPT and Claude — processing speed, response quality, and reasoning depth compared across identical BC scenarios - Q&A on architecture, configuration, model selection, and real-world implementation Who Business Central consultants, Copilot Studio practitioners, and solution architects working at the intersection of ERP and AI. Skill level: Intermediate to Advanced. No prerequisites required. Top 3 Key Takeaways 1. A clear understanding of how MCP connects Copilot Studio to Business Central natively — including authentication, data access patterns, and configuration steps replicable immediately in your own environment. 2. Live demonstration of a Copilot Studio agent handling real BC business scenarios — showing what production-ready ERP AI integration actually looks like beyond a toy demo. 3. Evidence-based insight into how GPT and Claude handle identical ERP tasks differently — giving you the confidence to make informed model selection decisions for your own BC agent implementations.

What A demo-driven session showing how to design and orchestrate multi-agent systems using the Microsoft Agent Framework — moving beyond single-agent solutions into coordinated agent networks that handle complex enterprise workflows reliably in production. Why Single agents have limits. Complex workflows spanning multiple systems and requiring specialised reasoning demand a different architectural approach. Most organisations attempting multi-agent architectures do it without a structured framework — resulting in brittle systems that work in demo but fail in production when agents loop, disagree, or produce outputs that cannot be audited. This session shows the right way — with honest coverage of failure modes and governance patterns most conference sessions never address. How - Architecture overview — orchestrator and specialist agents, communication protocols, handoff mechanisms, shared context management, and failure handling - Live demo of multiple agents orchestrated against a real enterprise workflow — delegation, parallel execution, context passing, and live tool invocation demonstrated end to end - Honest coverage of production failure modes — infinite loops, agent disagreement, timeout scenarios, and graceful degradation - Q&A on architecture decisions, governance, cost management, and real-world implementation challenges Who Solution architects, enterprise developers, and technical leads designing multi-agent AI systems. Solid experience with Copilot Studio, Azure AI Foundry, or the Microsoft 365 Agents SDK required. Skill level: Advanced. Top 3 Key Takeaways 1. A complete architectural understanding of multi-agent orchestration — communication patterns, handoff mechanisms, and failure handling that make multi-agent systems reliable in production. 2. First-hand experience seeing multiple specialised agents working together live on a real enterprise workflow including delegation, parallel execution, and context passing. 3. A practical governance and production readiness framework covering monitoring, auditability, and the failure points that only reveal themselves when real users interact with a live multi-agent system.