Technology

Microsoft 365 Copilot Agent's Playbook: A 4-Part Livestream Series

Microsoft is launching a four-part livestream series on Microsoft 365 Copilot declarative agents, running August 18 through September 8 at 9 AM PT. The sessions cover building, grounding, extending, and evaluating agents.

Microsoft is launching The Microsoft 365 Copilot Agent's Playbook, a four-part livestream series running August 18 through September 8 at 9 AM PT. The series is designed for developers, makers, architects, and technical decision-makers who want to learn how Microsoft 365 Copilot declarative agents are built, grounded, extended, and evaluated. Each session includes presentations, demos, and live Q&A from Microsoft engineers, with a focus on agents that use skills, reason over context, connect to tools, and improve over time through evaluation.

What the series covers

Microsoft is launching The Microsoft 365 Copilot Agent's Playbook, a four-part livestream series running from August 18 through September 8 at 9:00 AM to 10:00 AM PT. The series is designed for developers, makers, architects, and technical decision-makers who want to understand how modern Microsoft 365 Copilot declarative agents are built, extended, grounded, and evaluated.

Each session includes a focused presentation, demos, and live Q&A so attendees can learn directly from the teams behind the platform. Engineers and product makers from Microsoft walk through real-world patterns, live demos, and practical techniques.

Why declarative agents, why now

Declarative agents are quickly becoming one of the most exciting ways to extend Microsoft 365 Copilot and bring organizational knowledge, workflows, and tools directly into the flow of work. The capability surface is growing, and the practical guidance is thin on the ground. The series exists to close that gap. The sessions are aimed at people who are just getting started with Microsoft 365 Copilot extensibility and at people who are already building declarative agents and want to go deeper.

What you'll build toward

By the end of the series, attendees will have a clearer playbook for building agents that are useful, grounded in the right context, extensible with skills and tool connections, and measurable through evaluation. The series covers how to design agents that do more than respond to prompts. The agents built through the series use skills, reason over relevant context, connect to tools, and improve over time through evaluation.

Who should attend

Developers, makers, architects, and technical decision-makers who want to learn how to design agents that use skills, reason over context, connect to tools, and improve through evaluation. To get the most out of the livestreams, Microsoft recommends reviewing the basics of Microsoft 365 Copilot extensibility and declarative agents before the first session, including the materials in Copilot Developer Camp.

The lineup

The full session schedule is on the Microsoft 365 Copilot blog, with each session focused on a specific part of the declarative agent development journey. All sessions run from 9:00 AM to 10:00 AM PT. The first session is on August 18, and the series runs through September 8. The future of AI agents is practical, contextual, and extensible, and the series is positioned as the practical path from "what can agents do?" to "how do I build and improve one?"