What happens when you turn the tables on your own AI? In this session, we dive into the fascinating journey of building an autonomous agent with Copilot Studio—and then trying to break it. You’ll hear the real story of how an agent designed to streamline job applications was stress-tested with prompt injections, tool misuse, and data exfiltration attempts. Discover where the agent held strong, where it failed spectacularly, and what lessons emerged for anyone building AI-driven automation. This is not theory - it’s a candid look at the vulnerabilities, defenses, and design patterns that matter when your agent moves from the lab to the real world. Why Attend? If you’re working with Copilot Studio, Power Automate, or planning to deploy autonomous agents, this session will give you practical insights into: • Common attack surfaces and how to mitigate them • Designing safe, auditable actions and flows • Grounding AI responses to enterprise data • Building resilience without sacrificing usability Join us for a story that blends innovation, security, and a little bit of hacking fun—because the best way to understand your agent is to try breaking it.

Proposal Operator demonstrates a practical multi agent orchestration pattern built entirely with native Microsoft Copilot Studio capabilities. Instead of one agent, a coordinated team handles the full RFP flow: ingesting documents, extracting metadata and requirements into a response matrix, drafting proposal sections, running validation gates for contradictions and outdated content, and delivering role aware outputs with mandatory citations. The focus is on how an orchestration layer routes work to the right specialists, enforces quality controls, and keeps the solution governed and understandable. External integrations are not required for the demo; the architecture simply remains extensible through standard patterns should additional tools be introduced later. Key Takeaways • Why multi agent orchestration is better suited for RFP and proposal work than single agent designs • How to decompose proposal automation into specialized agent roles with clear responsibilities • Practical Copilot Studio patterns for routing, validation gates, and cited outputs • How to design agent solutions that are extensible without depending on external systems • A realistic blueprint for building AI assisted proposal workflows that scale beyond demos

In automation, actions aren’t just louder—they’re smarter. This advanced session will show you how to make your Power Automate flows speak through intelligent execution. Karl-Johan Spiik will guide you through techniques that transform complex workflows into seamless, reliable automation. From iterative development and child flows to AI-powered enhancements, you’ll learn how to build flows that communicate precision and efficiency without saying a word. What You’ll Learn • Build flows iteratively for easier debugging and maintainability • Implement child flows and secure execution with ‘run only’ users • Use nested output values from lookup field actions • Configure dynamic responses before parent flow termination • Apply robust error handling and logging strategies • Use trigger actions and Terminate functions effectively • Leverage AI models like GPT for smarter data operations • Manage advanced scenarios in model-driven apps and Teams approvals Why Attend? Karl-Johan Spiik brings 19+ years of experience and a passion for turning automation into action. Join this session and learn how to make your flows Spiik louder than words - because in Power Automate, actions truly speak louder.

From Smart Answers to Trustworthy AI: Designing Governed Copilot Studio Agents Generative AI makes it easy to build agents that sound helpful. Building agents that are trusted in production is much harder. In this session, we explore how to design Copilot Studio agents that behave like enterprise products instead of experimental chatbots. Rather than focusing on prompts or model tuning, the session dives into the often ignored foundations of trustworthy AI: controlled knowledge scope, lifecycle awareness, metadata reliability, and explicit governance boundaries. Using real-world patterns built with Copilot Studio, SharePoint, and Power Automate, the session shows how users—not the AI—control what content an agent is allowed to use. You’ll see how metadata-driven source selection, curated knowledge libraries, and flow enforced rules prevent accidental oversharing and stale answers. Special attention is given to content retention and orphaned files: how flows acts when source documents expire, are deleted due to retention policies, or lose their responsible owner—and how to avoid AI answers being based on information that no longer officially exists. The session emphasizes a key mindset shift: optimizing for defensible answers instead of impressive ones. Attendees will leave with concrete design principles they can apply immediately when building production ready Copilot Studio agents that security teams, compliance officers, and business users can all trust. Key takeaways • How to design Copilot agents with an explicit, user controlled knowledge scope • How retention policies and orphaned files impact AI reliability • Why Power Automate is a critical governance boundary for enterprise AI • Patterns for building predictable, auditable, production ready Copilot Studio agents

Power Platform and Copilot agents enable rapid innovation—but without the right governance, they can introduce security risks, operational friction, and long-term technical debt. This session shows how governance can accelerate adoption instead of slowing it down. Using real-world enterprise patterns, we present an end-to-end governance model covering the full lifecycle from idea intake to production, operations, and ongoing support. Attendees will learn why documentation alone is not enough, and how operational governance helps balance business agility with enterprise IT control. The session introduces a practical governance add-on approach that complements existing ITSM tools, providing a single intake for environment requests, connector approvals, access management, and Power Platform or Copilot Studio agent issues. We also cover approval and integration models—including hybrid and tiered approvals—and explain why these matter in customer-facing discussions. Finally, we look at the Copilot Studio agent lifecycle: ownership, citizen vs. IT delivery paths, quality gates, controlled releases, and the often-overlooked challenges after go-live. Who should attend: Sales, solution architects, delivery leads, project managers, and Power Platform or Copilot Studio specialists. Key takeaway: A clear, practical way to position governance as a business enabler.