#ai
ai

PostSharp 2027.0 gives AI coding agents the real API and build facts

PostSharp 2027.0 adds tooling that helps AI coding agents work correctly in PostSharp projects, including a plugin for Claude Code and Codex. The release also brings CLI commands that show which aspects were applied to a declaration after a build, per-message error documentation, and an aspect test framework. These are useful for .NET developers who write or maintain aspects.

A C# MCP Server with Single-Use Order Approvals

Martin Pisacreta built a small .NET 8 MCP server where the order cancellation tool requires a separately recorded, single-use, expiring approval instead of trusting the model's confirmation. The article walks through the claim-before-use approval store, the tool contract and the limits of the design, backed by 12 passing tests.

Visual Studio 2026 v18.11 adds fail-fast builds and agentic debugging

Visual Studio 2026 v18.11 and its 18.11.1 servicing update add an opt-in setting that stops a solution build as soon as one project fails. Copilot Chat, the Debugger Agent and the Profiler Agent also received major changes. These updates touch everyday .NET 10 and C# 14 work, from compile loops to profiling and Git.

Building an AI Knowledge Assistant with ASP.NET Core

This tutorial shows how to grow a single LLM call into a production-ready AI feature on ASP.NET Core. It covers authentication, retrieval-augmented generation, security and failure handling. It is a practical roadmap for .NET developers who want the model to stay a replaceable dependency inside their application.

CritterWatch 1.1, Bobcat 1.0 and AI Skills 1.17 ship; Stoat preview arrives

JasperFx shipped a coordinated Critter Stack release wave: CritterWatch 1.1, Bobcat 1.0, AI Skills 1.17 and a Stoat 0.5.0 preview. CritterWatch's MCP server now exposes 83 tools, and Bobcat 1.0 turns existing test methods into executable specifications. Worth a look if you run Wolverine or Marten in production or write integration tests on the .NET stack.

How Uno Platform developers keep AI-written .NET code trustworthy

Uno Platform's Matt Mattei explains how he checks code that AI agents write for .NET and Uno Platform apps. He combines written specs, runtime checks, lint hooks and change-cost probes. The post gives working .NET developers a concrete review checklist for agent-written features.

PostgreSQL extension for VS Code: explore, query and troubleshoot

Microsoft's PostgreSQL extension brings connecting, browsing schemas, writing and running SQL, and asking GitHub Copilot about the connected database into VS Code. The post walks through four workflows, from exploring a first table to reviewing a performance recommendation. It is a practical guide for .NET developers who work against PostgreSQL and want to stay in their editor.

Mostlylucid.Relevance: SQLite-backed recommendations for .NET apps

Part 5 of Scott Galloway's series packages the recommendation and intervention ideas from earlier parts into Mostlylucid.Relevance, a framework that runs inside the application process and keeps its state in SQLite. It can serve several isolated domains at once, and an optional native package adds an HNSW vector index. The package also ships an AGENTS.md guide describing extension points and invariants for developers and their coding assistants.

Controlling Claude Code permission prompts in a .NET project

Auto mode in Claude Code still lets an AI classifier decide which actions are safe. The author shows how to add ask and deny rules to a .NET project's settings file to keep control over EF Core migrations, running the app and database updates. He also explains that a deny rule wins over allow and ask rules, whichever settings file holds it.

MCP C# SDK 2.0 Makes HTTP Stateless by Default

Microsoft released version 2.0 of the official MCP C# SDK, implementing the 2026-07-28 Model Context Protocol revision. Streamable HTTP servers are now stateless by default, and Multi Round-Trip Requests (MRTR) let interactive tools ask clients for input. Releases 2.1 to 2.3 added hybrid session serving, a subscriptions/listen handler and several OAuth and discovery fixes.

Migrating Semantic Kernel agents to Microsoft Agent Framework

This walkthrough shows how to move a tool-using ASP.NET Core agent from Semantic Kernel to Microsoft Agent Framework step by step. The Kernel-centered model gives way to IChatClient, AIAgent and AIFunctionFactory. It is a practical plan for teams already running Semantic Kernel agents.

Vector search comes to OrmLite with ServiceStack v10.4 embedding columns

ServiceStack v10.4 adds a [Vector] attribute to OrmLite, so embeddings from an AI model can be stored with your rows. Distance functions such as Sql.CosineDistance() combine with filters, joins and tenant rules in one typed query. For .NET developers building RAG features, this removes the need for a separate vector store to keep in sync.