How to enhance your own AI services using Semantic Kernel
summary
Shows how Semantic Kernel wires OpenAI / Azure OpenAI / Hugging Face models into an app via a Kernel builder, uses plugins via JSON+prompt files to generate a joke (example: T‑rex dentist punchline), and registers C# functions to control lights so the Kernel does auto planning and function calling to switch a table lamp on. Demonstrates text embeddings and a memory store (examples return a relevance score — one answer reports 83%), and adds a Bing connector for up‑to‑date web lookups (demoed but web query failed live).
AI-written summary · about
chapters (9)
- 0:00Introduction and speaker background
- 1:26AI Assistants vs AI Agents
- 5:29Setting up Semantic Kernel
- 10:27Creating plugins for Semantic Kernel
- 17:41Planning and function calling
- 20:35Using memory with Semantic Kernel
- 25:31Connectors and third-party services
- 29:16Summary and resources
- 31:23Q&A session
related talks
01h 02mDevelop AI agents with Semantic Kernel
26mSemantic Kernel: Teaching AI to Not Just Repeat, But Complete!
46mBuilding AI solutions with Semantic Kernel
59mOrchestrate your AI with Semantic Kernel
01h 12mBuilding Scalable GenAI Apps Using Semantic Kernel and .NET Aspire
47mAI Orchestration with Semantic Kernel
01h 00mBuilding your own AI Agent using Semantic Kernel
46mInfusing your .NET Apps with AI: Practical Tools and Techniques