Curious about a real-world implementation of AI in .NET looks like? Have your dipped your toes in the deep AI waters but need some ideas on how to let the (AI) rubber meet the (business) road?

In this session, Spencer will break down a project where he was put in charge of integrating Azure OpenAI into an application. We’ll discuss how he leveraged Microsoft’s Semantic Kernel to rapidly iterate and give the LLM access to data within the target system, how he used prompt engineering and retrieval-augmented generation (RAG) to enhance the efficacy of the AI’s responses, and how he cost-optimized the LLM as the project went on, reducing the costs from the initial deployment by 10 times.

Come to this jam-packed session and get the lessons learned from integrating AI using .NET as well as an in-depth overview of the tools involved.