Why should you care?

Portfolio proof beats slides — one working endpoint shows you understand agents.

See it live — copy this example

Run CLI steps in a terminal. Run C# samples in a .NET 8 console or Web API project with Ollama running on localhost:11434.

// LocalAIDesk Capstone — capstone slice
app.MapPost("/api/project/run", async (ProjectRequest req, AiChatService ai) =>
{
    var prompt = $"Project=LocalAIDesk Capstone. User goal: {req.Goal}. Reply in 5 short steps.";
    return Results.Ok(new { plan = await ai.CompleteAsync(prompt) });
});

What happened?

• A POST endpoint builds a strict prompt and returns a plan/summary from the local model.
• Follow the steps below — typing the code yourself is the fastest way to learn.

Practice next

1. Read the example and rewrite it in your own repo.
2. Run it against local Ollama (or finish the Ollama module first).
3. Change one prompt constraint and compare output.
4. Tighten the prompt to 3 bullets max.
5. Log duration of the model call.

Remember

You can explain your local AI app Capstone simply. You have a runnable local sketch. You know one risk to watch.

LocalAIDesk Capstone in LocalAIDesk

Your team applies localaidesk capstone while building a private agent desk.

Outcome: A concrete next step exists in code or checklist form.