Develop AI agents with Semantic Kernel
summary
Demonstration of Microsoft Semantic Kernel shows concrete patterns: install the NuGet, create a Kernel, attach Azure/OpenAI models, and register plugins as hands that run real C# or YAML prompts. The talk uses function calling so the model picks and invokes APIs, with a live demo reading Swedish Radio episodes, writing an episodes.txt file, and booking meeting rooms from a calendar. Planners and personas orchestrate flows and small agent teams (developer + organizer) iteratively produce and validate a 100‑word proposal.
AI-written summary · about
chapters (15)
- 0:00Introduction
- 4:18Microsoft CoPilot
- 5:21What is a CoPilot
- 7:21Semantic Kernel API
- 9:49Semantic Kernel Overview
- 11:42Code Snippets
- 19:28Plugins Planners Personas
- 21:44Plugin Examples
- 25:10Planners
- 31:54HandlebarPlanner
- 37:44Importing plugins
- 44:34Demo
- 52:26Active Booking
- 54:03Agent Approach
- 56:19Example
related talks
01h 00mBuilding your own AI Agent using Semantic Kernel
53mUnleash the power of AI: Automate tasks with OpenAI and Semantic Kernel
33mHow to enhance your own AI services using Semantic Kernel
26mSemantic Kernel: Teaching AI to Not Just Repeat, But Complete!
46mBuilding AI solutions with Semantic Kernel
01h 12mBuilding Scalable GenAI Apps Using Semantic Kernel and .NET Aspire
39mAI app 101: Starting from scratch with Semantic Kernel
36mBuilding AI Agents in .NET with Azure AI Foundry