This talk was recorded at NDC London in London, England. #ndclondon  #ndcconferences #developer #softwaredeveloper    

Attend the next NDC conference near you: 
https://ndcconferences.com
https://ndclondon.com/

Subscribe to our YouTube channel and learn every day:   
/        @NDC 

Follow our Social Media!

https://www.facebook.com/ndcconferences
https://twitter.com/NDC_Conferences
https://www.instagram.com/ndc_conferences/

#ai #dotnet #api #azure¨

There are multiple ways to add AI to a .NET application. Depending on the problem you’re solving, you may choose anything from direct model integration to higher-level abstractions and frameworks.

In this session, we’ll explore the different options available to .NET developers when building AI-enabled applications. We’ll start with direct model access using APIs and SDKs, move on to using managed services such as Azure AI Services, and then look at higher-level composition approaches using libraries like Semantic Kernel.

Finally, we’ll look at agent-based frameworks and how they build on these foundations to make it easy to add agents to your applications.

This session is aimed at understanding the trade-offs between these options and when each one makes sense in a real-world application. All examples are demonstrated using a Blazor application, but the concepts apply to any .NET platform.

You’ll leave with a clear overview of the AI integration options available in .NET, along with practical guidance to choose the right level of abstraction for your application.

NDC Conferences

A conference talk walkthrough covering multiple approaches to integrating AI into .NET applications. Starts with direct OpenAI API usage via the OpenAI .NET SDK, covering chat completions, streaming responses, conversation history, function calling, and image generation. Moves to Azure AI Services for text analytics tasks like sentiment analysis, language detection, and translation. Then covers Semantic Kernel as an abstraction layer that decouples code from specific model SDKs and simplifies plugin/tool registration. Concludes with an introduction to the Microsoft Agent Framework, the successor to Semantic Kernel merged with AutoGen, designed for building multi-agent systems. Practical demos use a Blazor-based pie shop application throughout.

From Model Integration to Agents: Building Intelligent .NET Applications - Gill Cleeren