Building a great agent is half the battle; operating at scale is where programs succeed. This session goes deep on the controls, patterns, and telemetry that make Copilot Studio agents production‑ready.
We’ll unpack tenant and environment controls in the Power Platform admin center, how DLP for Microsoft 365 Copilot and sensitivity labels shape what agents can access or return, and how IT can manage agents centrally via Integrated Apps.
Then we’ll cover ALM environments, pipelines, versioning, and analytics, plus when to involve Application Insights for richer traces.
- Learning Objective 1: Implement enterprise controls: enforce tenant/environment policies, apply DLP for Copilot, and honor sensitivity labels so agents cannot leak or over‑retrieve data
- Learning Objective 2: Operationalize agent lifecycle (ALM): structure environments and pipelines, monitor with analytics/audit logs, and know when to add Application Insights
- Learning Objective 3: Design for scale and interoperability: use multi‑agent orchestration and BYOM/BYOKnowledge patterns to connect Studio agents
Terms: All rights reserved by the speaker, AI Agent & Copilot Summit NA, and Dynamic Communities and cannot be reproduced or distributed without express written consent by the speaker and Dynamic Communities.
Speakers
Johnny Lopez, Technical Director, Principal Copilot Solutions Engineer in MW + Copilot, Microsoft

