Global AI On Tour Boston

Description

!!! Registration link: https://globalai.community/e/hkamkvke

Boston Azure AI is excited to welcome Paolo Pialorsi and Mehrnoosh Sameki for a special in-person evening of AI learning, builder stories, and community conversation. Paolo and Mehrnoosh will share practical insights from the front lines of Microsoft AI innovation, with a likely focus on topics like agents, GitHub, and Microsoft Foundry, plus the real-world patterns that help developers go from experimentation to impact.

Understanding Work IQ for Developer
As AI agents become an essential part of the modern workplace, developers are increasingly looking for ways to connect them to the knowledge, context, and tools that drive productivity across their organizations. Work IQ, a key component of the Microsoft IQ Platform, helps bridge that gap by making organizational intelligence available to agents, enabling richer and more impactful user experiences. In this session, we'll introduce the core concepts behind Work IQ and explore how developers can leverage protocols such as A2A, MCP, and REST to connect agents with their organizational intelligence.
By Paolo Pialorsi

From Intent to Enforcement: Open-Source Evaluation and Governance for AI Agents
AI agents are taking on increasingly complex tasks, but evaluation and governance are still often fragmented across disconnected tools and platform-specific controls. In this talk, we introduce two open-source tools that connect testing to runtime enforcement. ASSERT turns natural-language expectations about what an agent should and should not do into executable, scenario-specific evaluations. ACS (Agent Control Specification) carries those expectations into production as portable policies that can be enforced across key points in an agent’s execution. Together, they create a continuous governance loop: define intended behavior → test it → identify failures → turn findings into controls → enforce them at runtime → evaluate again. The result is a practical approach to governing agents across models, frameworks, and deployment environments without locking developers into a single platform.
by Mehrnoosh Sameki