AI app 101: Starting from scratch with Semantic Kernel
summary
Starts from a brand‑new .NET project and shows how Semantic Kernel wires an AI model into a C# app: create a kernel, add OpenAI chat completions, register plugins and let the model call functions via function calling. Demonstrates a streaming chatbot, a datetime helper and a light‑control plugin that actually changes bulb color, and an event‑triggered to‑do automation. Notes practical limits (APIs accept ~256 functions; sweet spot is ~6–12) and the end‑to‑end function calls succeed.
AI-written summary · about
chapters (10)
- 0:00Semantic Kernel intro
- 2:10Core concepts
- 5:46Function calling
- 13:32Setting up a Semantic Kernel project
- 18:05Basic chatbot
- 21:20Adding plugins
- 26:39Plugin management
- 29:05Real-world plugins
- 33:43Beyond manual AI
- 36:55AI automation future & Q&A
related talks
01h 02mDevelop AI agents with Semantic Kernel
46mInfusing your .NET Apps with AI: Practical Tools and Techniques
26mSemantic Kernel: Teaching AI to Not Just Repeat, But Complete!
01h 00mBuilding your own AI Agent using Semantic Kernel
46mBuilding AI solutions with Semantic Kernel
58mEasily Add GenAI to .NET Apps using Microsoft.Extensions.AI
01h 10mPractical Applications of Generative AI: How to Sprinkle a Little AI in Your App
47mAI Orchestration with Semantic Kernel