This talk was recorded at NDC Copenhagen in Copenhagen, Denmark. #ndccopenhagen #ndcconferences #developer #softwaredeveloper    

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

#dotnet #ai #cloud #genai 

Microsoft.Extensions.AI is an exciting new library that makes it easier than ever to integrate AI models into our .NET apps! By providing an abstraction that integrates with any AI service, we can easily leverage any AI model in our code, easily write unit tests, and easily upgrade to a newer model, all with just one line of code!

In this session, we'll introduce Microsoft.Extensions.AI and dive deep into its abstractions like IChatClient. We'll also highlight its integration with Microsoft's Semantic Kernel as its foundational layer.

Then, we'll jump into the code where we'll build our own custom chat client together! We'll quickly write code to use various models from OpenAI, and then we'll use that same code to jump to other providers like Amazon Bedrock and Ollama.

Join me as we learn about the best way for adding AI to any .NET app!

NDC Conferences

Microsoft.Extensions.AI is a service-agnostic library that simplifies adding generative AI to .NET applications. The library provides a unified interface (IChatClient) that works across different AI providers (Azure OpenAI, AWS Bedrock, Ollama), making it easy to switch providers without rewriting code. Key features include chat history management, system prompts for model behavior customization, function invocation that allows AI models to call your application methods, and built-in evaluation tools for testing AI responses. The library includes quality evaluators (equivalence, relevance, completeness) and safety evaluators (violence, sexual content, code vulnerabilities) that use Microsoft-trained models to assess AI outputs locally. Implementation requires minimal code: initialize a chat client, optionally configure chat options with tools/functions, and use streaming or standard response methods.

Easily Add GenAI to .NET Apps using Microsoft.Extensions.AI - Brandon Minnick - NDC Copenhagen 2025