Tutorials Agentic AI with .NET Tutorial
Introduction to Semantic Kernel
Introduction to Semantic Kernel: free step-by-step lesson with examples, common mistakes, and interview tips — part of Agentic AI with .NET Tutorial on Toolliyo Academy.
On this page
Agentic AI with .NET Tutorial · Lesson 11 of 120
Semantic Kernel
Foundations & SK → Tools & RAG → Product & Ops → Projects
Foundations & SK · 1 — Agent basics · ~6 min · Semantic Kernel
What is this?
Semantic Kernel (SK) is a .NET SDK that connects chat models, prompts, and plugins (tools). You build a Kernel, register services, then invoke prompts or functions.
Why should you care?
For AgentVerse on .NET, SK is a practical way to keep prompts and tools organized instead of scattered HttpClient calls.
See it live — copy this example
Use .NET 8+. Run Semantic Kernel samples in a console or Web API. Keep API keys in user secrets or environment variables — never in source.
// dotnet add package Microsoft.SemanticKernel
using Microsoft.SemanticKernel;
var builder = Kernel.CreateBuilder();
// next lessons: add chat completion + plugins
var kernel = builder.Build();
Console.WriteLine($"Plugins: {kernel.Plugins.Count}");
What happened?
- CreateBuilder configures the kernel.
- Build() creates the runtime object.
- Plugins hold your tools.
Practice next
- Create a console app.
- Add Microsoft.SemanticKernel.
- Build an empty kernel and print plugin count.
- Add logging to the builder.
- Create a second project for Web API later.
Remember
SK = kernel + prompts + plugins. Start empty, then add chat + tools. Keep config outside code.
SK as the spine
All AgentVerse skills register as plugins on one kernel per request.
Outcome: Clear place to attach tools.
Interview prep for this lesson
Practice these questions aloud after reading—each links to a full structured answer.
Sign in to ask a question or upvote helpful answers.
No questions yet — be the first to ask!