In this session, we will explore how to deploy local reasoning models using AutoGen for .NET, facilitating seamless interactions between Ollama and LM Studio. We’ll cover the fundamentals of setting up and configuring these tools, optimizing local inference for reasoning tasks, and leveraging AutoGen to orchestrate multi-agent workflows.

Attendees will gain hands-on experience via demonstration in integrating locally hosted LLMs for efficient, private, and cost-effective AI applications.