Infusing your .NET Apps with AI: Practical Tools and Techniques
summary
Demo shows how to add LLM features into existing .NET apps using Semantic Kernel to wire OpenAI, Mistral, Google Gemini and local models into console, ASP.NET and Blazor code with DI. It demonstrates automatic function calls (AI requests invoke C# plugins), a live eShop assistant, and one real product shipped to production (AI Tax Assist) while telemetry uses OpenTelemetry and Aspire and AZD to trace tokens, prompts, deploy to Azure and observe model calls end‑to‑end. Tests evaluate relevance via prompt‑based plugins.
AI-written summary · about
chapters (5)
- 0:00Introduction and overview
- 2:58Building AI apps with .NET
- 19:29Observability and testing AI
- 29:14Real-world production lessons
- 36:40Resources and Q&A
related talks
01h 10mPractical Applications of Generative AI: How to Sprinkle a Little AI in Your App
44mAI Building Blocks for .NET: Add intelligence to your C# Apps
55mDive into the Future: .NET and AI!
59mHow to add genuinely useful AI to your webapp (not just chatbots)
01h 08mFrom Model Integration to Agents: Building Intelligent .NET Applications
58mEasily Add GenAI to .NET Apps using Microsoft.Extensions.AI
01h 10mPractical Applications of Generative AI: How to Sprinkle a Little AI in Your App
33mHow to enhance your own AI services using Semantic Kernel