Articles
Building AI agents with .NET and the cloud — 61 guides.
Consuming MCP Servers from .NET: The Client Side
Most MCP writing is about building servers. The harder engineering is on the client — you are handing a model a tool list you did not write, from a process you did not start, and it can change under you at runtime.
Multi-Tenant AI Agents in .NET: Isolation That Actually Holds
Every tenant boundary you rely on in a normal web app — the connection string, the row filter, the claim — gets crossed differently once a model is in the loop. Here is where the leaks actually happen and what to do about each.
Human-in-the-Loop Approvals in Microsoft Agent Framework
An agent that can issue refunds needs a stop button. Agent Framework has two mechanisms for this — tool approval and workflow request ports — and picking the wrong one leaves you holding state you cannot survive a restart with.
Rate Limiting LLM Calls in .NET: Tokens, Not Requests
Provider quotas are measured in tokens per minute, but almost every .NET rate limiter counts requests. That mismatch is why your agent still gets 429s under a limiter that says it is doing its job.
Redacting PII Before It Reaches the Model: A .NET Pattern
Once a customer record leaves your process and lands in a model provider log, you cannot get it back. Here is a redaction layer for .NET that sits in front of the model, survives tool calls, and does not quietly break your prompts.
Vector Search in SQL Server 2025 with EF Core 10: One Less Database
SQL Server 2025 has a native vector type and EF Core 10 speaks it. For a lot of .NET teams that removes a whole moving part from the architecture — here is what it does well, and the ceiling you should check first.
Securing a Remote MCP Server in C#: OAuth 2.1 and Protected Resource Metadata
The moment an MCP server leaves localhost it becomes a public API with tool-calling attached. Here is what the spec actually requires, what the C# SDK gives you, and the parts you still have to think about.
Agentic RAG in .NET: When One Retrieval Is Not Enough
Classic RAG runs one search and hopes. Agentic RAG lets the model decide what to look up, how often, and when it has enough — here is what that costs and how to build it in C#.
Why Your .NET AI Agent Feels Slow (And What to Fix First)
Perceived latency in an agent is rarely the model. A latency budget for .NET agents — where the seconds actually go, measured, and the fixes ordered by what they return.
CodeAct in the Microsoft Agent Framework: What .NET Developers Need to Know
CodeAct collapses the tool-calling loop into one generated program and reports large latency and token savings — but it is Python-only today. What it is, why it works, and what a .NET team can use right now.
Model Routing and Fallback in .NET: One Interface, Several Models
Route each request to the cheapest model that can handle it, and fail over when a provider degrades — built on Microsoft.Extensions.AI with C# you can drop into an existing app.
Prompt Injection in .NET Agents: What Actually Works as a Defence
Prompt injection is not a prompt problem, so prompt fixes do not solve it. A .NET engineer's guide to the defences that hold — capability scoping, provenance tracking, output gating — with C# you can lift.
30 .NET AI & Agent Interview Questions (With Answers That Actually Land)
The AI questions .NET developers are being asked in 2026 — fundamentals, Microsoft.Extensions.AI, the Agent Framework, RAG, tools and production concerns — with model answers and what each one is really testing.
Run Your Whole AI Agent Stack Locally with Aspire (Ollama + Qdrant + Traces)
Wire an LLM, a vector database and your API into one F5 with Aspire — no docker-compose, no API keys during development, and OpenTelemetry traces of every model call for free.
RAG vs Fine-Tuning: How to Actually Decide (A .NET Engineer's Guide)
RAG or fine-tuning? A decision framework based on what your problem actually is — knowledge, behaviour, format or cost — plus what each one really costs to run on .NET.
Migrating from Semantic Kernel to the Microsoft Agent Framework: A C# Walkthrough
A line-by-line C# migration from Semantic Kernel agents to the Microsoft Agent Framework — namespaces, agent creation, threads, tools, invocation, options and DI, with before/after code for each.
Text-to-SQL in .NET: Letting Users Query a Database in Plain English (Safely)
Build a natural-language-to-SQL feature in C# — schema grounding, a read-only execution boundary, statement validation and the failure modes that decide whether it survives production.
Choosing a Vector Database for .NET: pgvector vs Qdrant vs Azure AI Search vs SQL Server
A practical comparison of the vector stores .NET can talk to — pgvector, Qdrant, Azure AI Search, SQL Server 2025, Redis, Cosmos DB and SQLite — and why the choice matters less than you think.
The A2A (Agent2Agent) Protocol for .NET Developers
What the A2A (Agent2Agent) protocol is, how it differs from MCP, and how .NET developers build A2A agents in C# with the A2A SDK and Microsoft Agent Framework.
The Agent Harness in Microsoft Agent Framework (.NET Guide)
The Agent Harness in Microsoft Agent Framework gives .NET agents sandboxed shell execution, file access, and human-in-the-loop approvals. How to wire it up.