Building Intelligent .NET Applications: From AI Features to Agentic System

dotnet explains how to add practical AI capabilities to .NET apps using Microsoft.Extensions.AI, starting with features like summarization, classification, and semantic search across cloud and local models, then extending the same foundations into agentic systems with the Microsoft Agent Framework.

Overview

Building intelligent .NET apps with incremental AI features

The session focuses on a practical path for introducing AI into modern .NET applications using Microsoft.Extensions.AI and .NET's unified AI abstractions.

It covers how to:

• Integrate large language models (LLMs) into .NET applications.
• Add AI-backed application features beyond a chatbot, including:
  • Summarization
  • Classification
  • Semantic search
• Work with both:
  • Cloud-hosted models
  • Local models
• Apply patterns that keep the solution maintainable and production-ready, with minimal friction when adding AI to existing applications.

Quality, governance, and enterprise readiness

The session also addresses how to ensure quality and governance when integrating AI into enterprise applications, with an emphasis on building in a way that can be managed and operated responsibly.

From AI features to agentic architectures

After establishing the foundations for AI features, the session introduces agentic development and shows how the Microsoft Agent Framework can be used to build more autonomous systems where applications can:

• Reason about tasks
• Plan steps
• Take action via tools and workflows

Links

• Blog: https://aka.ms/dotnet/blog
• Twitter: https://aka.ms/dotnet/twitter
• TikTok: https://aka.ms/dotnet/tiktok
• Mastodon: https://aka.ms/dotnet/mastodon
• LinkedIn: https://aka.ms/dotnet/linkedin
• Facebook: https://aka.ms/dotnet/facebook
• Docs: https://learn.microsoft.com/dotnet
• Forums: https://aka.ms/dotnet/forums
• Q&A: https://aka.ms/dotnet-qa
• Microsoft Learn: https://aka.ms/learndotnet