Building AI solutions with Semantic Kernel
summary
Semantic Kernel is an open source framework that composes LLM prompts, vector-backed state, and connectors to build copilots; the team demos a runnable co-pilot app that ingests a manual via Azure Cognitive Search, stores embeddings in Qdrant/Pinecone or Cosmos, runs C# or Python plugins, and deploys to Azure in minutes. The planner component auto-generates command pipelines, the VS Code tooling tests prompts, and the demo works though hallucination and safety checks remain. Semantic Kernel 1,400 connectors planner
AI-written summary · about
chapters (18)
- 0:00Introduction
- 0:35Meet the speakers
- 2:02The age of AI consumption
- 2:50Evolution of development
- 5:03Foundations of AI apps
- 7:35Controlling AI flow
- 9:33Connectors and plugins
- 11:30Semantic Kernel demos
- 14:15Building a chat copilot
- 17:38DevOps copilot demo
- 20:03Reference app details
- 23:02VS Code tooling
- 26:23Daytona Beach analogy
- 29:12The power of open systems
- 31:25Collaborative UX
- 32:25Fusion of syntax and semantics
- 34:45Engineering challenges
- 40:26Conclusion
related talks
01h 02mDevelop AI agents with Semantic Kernel
01h 00mBuilding your own AI Agent using Semantic Kernel
33mHow to enhance your own AI services using Semantic Kernel
26mSemantic Kernel: Teaching AI to Not Just Repeat, But Complete!
59mOrchestrate your AI with Semantic Kernel
47mAI Orchestration with Semantic Kernel
53mUnleash the power of AI: Automate tasks with OpenAI and Semantic Kernel
01h 12mBuilding Scalable GenAI Apps Using Semantic Kernel and .NET Aspire