.NET agent eval tooling gets a dedicated toolkit

AgentEval is a MIT-licensed .NET toolkit for AI-agent evaluation, including tool-usage validation, RAG quality metrics, stochastic evaluation, and model comparison for Microsoft Agent Framework and Microsoft.Extensions.AI workflows. Why it matters: Agent evaluation is moving from Python-only experiments into application-framework-native tooling. Teams building agents in .NET can start measuring tool behavior and RAG quality closer to the production stack.

Try this: If a .NET agent workflow is in scope, run AgentEval on one narrow tool-call or RAG task and compare its checks against the same task's existing test coverage.