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and requirements into a response matrix, drafting proposal sections, running validation gates for contradictions and outdated content, and delivering role aware outputs with mandatory citations.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