#ai
ai

Building a RAG assistant with Microsoft Graph and .NET

Microsoft Graph supplies calendar, mail and document data that can be indexed with Azure AI Search and passed to a language model to produce sourced answers. The article walks through a .NET retrieval-augmented generation flow with code for loading context, chunking documents and calling the model. It stresses least-privilege scopes and permission-aware retrieval, which matter for any enterprise assistant.

Microsoft Agent Framework: Exposing and Calling Agents over A2A in .NET

This post shows how to host a Microsoft Agent Framework agent over the Agent-to-Agent (A2A) protocol in ASP.NET Core and call it from a separate client as if it were local. It covers the agent card, session handling and the JSON-RPC endpoint.

Reviewing Agent-Written .NET Code: Green Builds Can Still Hide Bugs

Mehdi Mohseni argues that coding agents now write much of the code, but developers still need the judgment to spot code that looks right and is wrong. Using ASP.NET Core examples, he shows how generated code can compile, pass tests and still hide a fail-open security check or a silent misconfiguration. A practical read for anyone reviewing agent output.

TypeSafe Jev .NET SDK 0.7.0: Experimental Images and Bounding Boxes

The community TypeSafe Jev .NET SDK 0.7.0 adds experimental image input and a Box question type that returns a normalized bounding box for a target in an image. The release also brings nullable usage counts, stricter request validation and zstd compression. Developers experimenting with vision requests in C# should read on.

Microsoft Agent Framework: Human-in-the-Loop Tool Approval with .NET

Agent Framework can pause an agent before a sensitive tool runs, using ApprovalRequiredAIFunction, until a person approves. The author shows the approval loop in a console app and over the Responses protocol on Microsoft Foundry. On Foundry, an approved booking still ends in a failed run, a caveat every hosted approval flow should account for.