Harness the power of AI: Extend Copilot and beyond
summary
Shows how to extend Microsoft Copilot with real plugins that work today from existing Teams message extensions or from any API documented with an OpenAPI spec; demos create and update tasks via Adaptive Cards, Copilot auto-selects the right plugin, and the Teams Toolkit scaffolds a plugin in seconds. Introduces the Teams AI library (planner, prompt manager, moderator, action handlers) wired to models like text-davinci-003, includes planning for multi-step actions, and partners (Decisions, Aisera, Lucid) shipping working demos.
AI-written summary · about
chapters (10)
- 0:00Introduction to AI in Teams
- 1:24Understanding Copilot Plugins
- 5:07How Copilot Plugins Function
- 6:54Building Plugins from APIs
- 10:53Plugin Best Practices
- 14:12The Teams AI Library
- 17:16Technical Deep Dive on AI
- 24:23Building a Bot Demonstration
- 32:59Partner Use Cases and Examples
- 39:18Wrap up and Developer Resources
related talks
45mReach 320M+ users in flow of work building your own copilot for Teams
12mThe mechanics of building and extending Microsoft Copilot
51mExtend your Copilot with plugins using Copilot Studio
36mCustom copilot Teams Integration in Government applications
45mDeveloper’s Guide to Customizing Copilot
36mWhat's new with Copilot Studio
23mEnabling ISVs to transform industries in the age of copilots
23mKEYNOTE: From Copilot to Flight Captain