Evaluating AI Applications in .NET: Quality, Safety and CI
Evaluate LLM apps in .NET with Microsoft.Extensions.AI.Evaluation: quality and safety evaluators, golden datasets, LLM-as-judge, caching, reports and CI gates.
18 articles about Microsoft.Extensions.AI: in-depth .NET and AI guides, senior interview questions and AI news on DotNet AI Hub.
Evaluate LLM apps in .NET with Microsoft.Extensions.AI.Evaluation: quality and safety evaluators, golden datasets, LLM-as-judge, caching, reports and CI gates.
Map the 2026 AI in .NET ecosystem: Microsoft.Extensions.AI, Agent Framework, Semantic Kernel, vector data, MCP, ML.NET, ONNX and Foundry, and when to use each.
Master function calling in C# with Microsoft.Extensions.AI: AIFunctionFactory, FunctionInvokingChatClient, parallel calls, approvals, security and tests.
Learn observability and cost control for .NET LLM apps, covering OpenTelemetry GenAI conventions, token tracking, caching, model routing and 429 retries.
Run LLMs locally in .NET with ONNX Runtime GenAI, Ollama and Foundry Local: small language models, GPUs and NPUs, quantization and IChatClient.
Build Model Context Protocol servers and clients in C# with the official SDK 2.x: tools, resources, Streamable HTTP, OAuth, security and VS Code setup.
Build AI agents in C# with Microsoft Agent Framework 1.x: ChatClientAgent, sessions, tools, MCP, workflows, human approval, hosting and migration.
Master Microsoft.Extensions.AI: IChatClient, IEmbeddingGenerator, streaming, tool calling, middleware pipelines, DI registration, custom clients and testing.
A practical guide to the OpenAI .NET SDK: ChatClient, streaming, tool calls, structured outputs, the Responses API, embeddings, images, audio and retries.
A practical guide to prompt engineering for .NET developers, covering prompt anatomy, few-shot examples, reasoning models, templates and injection risks.
Build production RAG in C#, covering ingestion, chunking, embeddings, hybrid retrieval, reranking, grounded prompts, citations and evaluation in .NET.
Get reliable JSON from LLMs in C#: JSON mode vs structured outputs, typed Microsoft.Extensions.AI responses, JSON Schema from types, validation and retries.
Learn how embeddings and vector databases work in .NET: similarity metrics, HNSW indexes, Microsoft.Extensions.VectorData and pgvector, SQL Server and Qdrant.
Senior .NET interview questions on Microsoft.Extensions.AI, streaming, function calling, structured output, provider abstraction, retries and testing LLM code.
GitHub made the Copilot SDK generally available on June 2, 2026, letting .NET, TypeScript, Python and Go apps embed Copilot's agent runtime via a stable API.
Microsoft Agent Framework reached 1.0 on April 2, 2026, with stable .NET and Python packages for agents and workflows while key integrations stayed in preview.
Microsoft shipped the first preview of Microsoft Agent Framework on October 1, 2025, an open-source .NET and Python successor to Semantic Kernel and AutoGen.
Microsoft declared Microsoft.Extensions.AI and the Vector Data extensions generally available in May 2025, giving .NET a stable, provider-neutral AI layer.