Semantic Kernel is aimed at teams with an existing codebase rather than a blank notebook. It treats the model as one more service you inject, with plugins, planners and memory that fit the way enterprise .NET and Python apps are already structured.
Reach for it when
- You are adding AI to an existing .NET or Python application
- You want plugins and dependency injection rather than scripts
- You are already on Azure
Look elsewhere when
- You want the shortest path to a prototype
- You are not in the Microsoft ecosystem
What the lessons will cover
- 01Install and setup
- 02Kernel and services
- 03Plugins and functions
- 04Prompt templates
- 05Planners
- 06Memory and embeddings
- 07Filters
- 08A production integration
Others in vendor sdk
Google ADK
OpenAI Agents SDKOpenAI's own agent loop, with handoffs and guardrails.
Claude Agent SDKClaude Code as a library you can run yourself.
Vercel AI SDKThe TypeScript way to build streaming AI apps.Common questions
Is Semantic Kernel free to use?
Semantic Kernel is open source and free to run yourself. You still pay whichever model provider you point it at, and this tutorial is free with no signup.
Do I need to know Python to use Semantic Kernel?
Basic Python is enough. Functions, dictionaries and imports cover most of what Semantic Kernel asks of you.
When should I not use Semantic Kernel?
You want the shortest path to a prototype. You are not in the Microsoft ecosystem.
Lessons for Semantic Kernel are being written. Meanwhile the LangGraph tutorial covers the same ground: state, tools, loops, memory and human approval. Most of it carries straight over.
Start the LangGraph tutorial →