Compare GLM, Qwen, and Gemma local LLMs - benchmarks, context sizing, and when home GPU inference beats cloud token costs.

Learn how to build interactive AI evaluation reports in .NET to communicate model quality, boost transparency, and engage your team.

AI systems are powerful, but hard to constrain, measure, and control. Let's see how Microsoft.Extensions.AI.Evaluation helps with AI systems development.

Kernel Memory gives us a simple and flexible way of indexing and searching documents and websites using our own models and vector storage solutions using .NET.

It turns out that AI orchestration is remarkably well equipped to handle building a virtual game master. Let's see how it works.