#ai
ai

A secure enterprise chat with React, .NET 10 and Microsoft Foundry

The article targets the common mistake of calling the model straight from the front end with the API key in JavaScript, and instead wires React to a .NET 10 Minimal API that talks to Microsoft Foundry without any keys. It walks through Entra ID authentication, a server-owned system prompt, Server-Sent Events streaming and IP-based rate limiting as the protections that separate a demo from a product.

From Local RAG to an AI Agent in C# with Ollama and Qdrant – Part 3

The third part of the series moves a local C# agent from free-form tool calling to deterministic Agent Workflows in Microsoft Agent Framework. A workflow collects deployment status, errors and Qdrant documentation in a fixed order, then hands the evidence to a tool-less agent for analysis, with a human approval gate before sensitive actions.

.NET 10 + Pinecone: integrating a vector database

A tutorial that wires .NET 10 into Pinecone, the managed vector database, using HttpClient and the REST data-plane endpoints instead of the archived C# SDK. It covers options binding, DI registration, upsert and similarity query, plus validation that keeps embeddings consistent.

Building AI Agents in C# with Microsoft Agent Framework

Microsoft Agent Framework lets .NET developers turn a console app into an AI agent that can call tools with only a few lines of code. The article walks through creating the agent, wiring C# functions as tools, testing it locally, and moving the same code to production on Microsoft Foundry Hosted Agents.

LLM tokens measured in C#: why AI can't count the R's in strawberry

The model's failure on the "strawberry" question isn't a counting problem: it never sees letters, only numeric pieces called tokens. Using Microsoft.ML.Tokenizers 2.0.1 and the gpt-5 tokenizer, the author measures this from C# and shows that the word alone is a single token with ID 101830, so the r's inside it stay out of reach. The piece also covers how token cost varies by language, by numbers, and by random text such as GUIDs, plus how to count tokens in .NET.

Faking a Yes: 6 Attacks on the Human Confirmation in a .NET 10 MCP Server

A developer red-teamed the confirmation step of a refund MCP server built on ASP.NET Core with the official C# SDK (ModelContextProtocol 2.3.0). Six attacks — plain-JSON requestState, replaying another user's approval, injected form fields and a pre-checked consent box — each led to a concrete server-side defense, plus a checklist you can apply to your own tools.

FAIRouter reaches NuGet: choosing a language model per task in a few lines of C#

FAIRouter, an open-source C# router that picks a language model per request and validates the reply with a judge model, is now published on NuGet as FAI.Router (0.1.0, .NET 10). A few lines of code connect OpenRouter or any OpenAI-compatible endpoint, score answers, collect feedback and train the router's weights.

A reusable Claude Code skill for reviewing ASP.NET Core endpoint changes

Nick Cosentino explains how to package a recurring .NET review job as a project-scoped Claude Code skill. The example reviews endpoint changes across validation, authorization, response mapping and persistence, and the article stresses clear limits on what the agent may run. It is a practical starting point for teams that want repeatable AI-assisted reviews of ASP.NET Core code.

Using AI agents to clean up dead code, stale packages and feature flags

A NimblePros Halloween post walks through removing the accumulated cruft of long-lived .NET codebases: unused private members, unreferenced public types, unused or vulnerable NuGet packages and stale feature flags. The method pairs compiler analyzers and dotnet CLI checks with an AI agent that investigates edge cases, guided by a reusable skill file. It is a practical playbook for teams who never find time to clean up.

Claude Code for .NET Developers: A Practical Agentic Workflow

Claude Code is an agent that reads a repository, plans changes, edits files and runs dotnet build and dotnet test until the code passes. Mehdi Mohseni's guide shows how a .NET team can set it up with a CLAUDE.md, a PostToolUse build hook, plan mode and permission guardrails. It is worth reading if you want the agent to check its own work.

Microsoft Fabric IQ: ontologies for Data Agents and Operations Agents

Microsoft Fabric IQ is a new Fabric workload that maps OneLake tables, Power BI semantic models and real-time Eventhouse streams to shared business entities. Its Ontology item, currently in preview, lets Fabric Data Agents and Operations Agents work with business concepts instead of raw schemas. Read on if you are deciding whether to model business meaning before connecting LLMs to your data.

Six checks an AI Telegram assistant needs before the model runs

A developer built a Telegram assistant in n8n that can send email and book meetings, with its decisions guarded by a small ASP.NET Core API on .NET 10. The post lists six checks that run before the model sees a request: chat allowlist, duplicate updates, stale messages, voice length, contact ambiguity and time zones. It is a useful checklist for any bot that triggers side effects.