<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Agentic .NET</title><description>Practical, in-depth guides on building production AI agents with .NET — the Microsoft Agent Framework, Semantic Kernel, MCP, and deploying agents on Azure and GKE. Written by a working principal engineer.</description><link>https://agenticdotnet.com/</link><item><title>Adding Memory and State to Your .NET Agent</title><link>https://agenticdotnet.com/blog/agent-memory-state-persistence-dotnet/</link><guid isPermaLink="true">https://agenticdotnet.com/blog/agent-memory-state-persistence-dotnet/</guid><description>A stateless agent forgets everything between messages. How to give a .NET agent short-term memory with threads, persist it across sessions, and add long-term memory.</description><pubDate>Tue, 14 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Building Your Own MCP Server in C#</title><link>https://agenticdotnet.com/blog/build-mcp-server-csharp/</link><guid isPermaLink="true">https://agenticdotnet.com/blog/build-mcp-server-csharp/</guid><description>Expose your tools to any AI agent by building an MCP server in C#. A practical walkthrough of the Model Context Protocol server SDK, defining tools, and choosing a transport.</description><pubDate>Tue, 14 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Build Your First Tool-Using AI Agent in C#</title><link>https://agenticdotnet.com/blog/build-tool-using-ai-agent-csharp/</link><guid isPermaLink="true">https://agenticdotnet.com/blog/build-tool-using-ai-agent-csharp/</guid><description>A step-by-step tutorial: build an AI agent in C# with the Microsoft Agent Framework that calls your own tools, remembers the conversation, and chains multiple tool calls.</description><pubDate>Tue, 14 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Choosing a Model for Your .NET Agent</title><link>https://agenticdotnet.com/blog/choosing-a-model-for-dotnet-agent/</link><guid isPermaLink="true">https://agenticdotnet.com/blog/choosing-a-model-for-dotnet-agent/</guid><description>GPT-class, small, or open-weight? A practical framework for picking the right LLM for a .NET agent, balancing capability, latency, cost, and where the model runs.</description><pubDate>Tue, 14 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Cost Control for Production AI Agents in .NET</title><link>https://agenticdotnet.com/blog/cost-control-production-ai-agents-dotnet/</link><guid isPermaLink="true">https://agenticdotnet.com/blog/cost-control-production-ai-agents-dotnet/</guid><description>AI agent bills scale with usage and can surprise you. Practical techniques for controlling token spend in .NET agents: right-sizing, caching, context trimming, and budgets.</description><pubDate>Tue, 14 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Deploy a .NET AI Agent to Azure Container Apps</title><link>https://agenticdotnet.com/blog/deploy-dotnet-ai-agent-azure-container-apps/</link><guid isPermaLink="true">https://agenticdotnet.com/blog/deploy-dotnet-ai-agent-azure-container-apps/</guid><description>Take a .NET AI agent from your laptop to production on Azure Container Apps: containerize it, wire up secrets with managed identity, deploy, and scale to zero when idle.</description><pubDate>Tue, 14 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Running a .NET AI Agent on Google Kubernetes Engine (GKE)</title><link>https://agenticdotnet.com/blog/deploy-dotnet-ai-agent-gke/</link><guid isPermaLink="true">https://agenticdotnet.com/blog/deploy-dotnet-ai-agent-gke/</guid><description>Deploy a .NET AI agent to GKE the production way: containerize, authenticate with Workload Identity instead of keys, expose it through an ingress, and autoscale on load.</description><pubDate>Tue, 14 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Function Calling vs MCP: When to Use Which in .NET</title><link>https://agenticdotnet.com/blog/function-calling-vs-mcp-dotnet/</link><guid isPermaLink="true">https://agenticdotnet.com/blog/function-calling-vs-mcp-dotnet/</guid><description>Should a tool be a C# method or an MCP server? A clear decision guide for .NET agents on when to use built-in function calling versus the Model Context Protocol.</description><pubDate>Tue, 14 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Multi-Agent Orchestration in .NET: Graph Workflows Explained</title><link>https://agenticdotnet.com/blog/multi-agent-orchestration-dotnet-graph-workflows/</link><guid isPermaLink="true">https://agenticdotnet.com/blog/multi-agent-orchestration-dotnet-graph-workflows/</guid><description>Coordinating multiple AI agents by prompt alone is fragile. Here is how the Microsoft Agent Framework&apos;s graph-based workflows make multi-agent systems in .NET explicit, testable, and observable.</description><pubDate>Tue, 14 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Observability for AI Agents with OpenTelemetry in .NET</title><link>https://agenticdotnet.com/blog/observability-ai-agents-opentelemetry-dotnet/</link><guid isPermaLink="true">https://agenticdotnet.com/blog/observability-ai-agents-opentelemetry-dotnet/</guid><description>When an agent misbehaves, logs are not enough. How to instrument a .NET agent with OpenTelemetry so you can see every tool call, token, and decision it made.</description><pubDate>Tue, 14 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Giving Your .NET Agent a Knowledge Base: RAG in C#</title><link>https://agenticdotnet.com/blog/rag-knowledge-base-dotnet-agent/</link><guid isPermaLink="true">https://agenticdotnet.com/blog/rag-knowledge-base-dotnet-agent/</guid><description>Your agent does not know your documents — until you add retrieval. A practical guide to RAG in .NET: embeddings, a vector store, and grounding an agent in your own data.</description><pubDate>Tue, 14 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Securing AI Agents in .NET: Auth, Secrets, and Guardrails</title><link>https://agenticdotnet.com/blog/securing-ai-agents-dotnet/</link><guid isPermaLink="true">https://agenticdotnet.com/blog/securing-ai-agents-dotnet/</guid><description>An AI agent that can call tools is a new attack surface. A practical security checklist for .NET agents: authenticating callers, protecting secrets, and guardrailing tool use.</description><pubDate>Tue, 14 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Semantic Kernel vs the Microsoft Agent Framework: Which Should You Use in 2026?</title><link>https://agenticdotnet.com/blog/semantic-kernel-vs-microsoft-agent-framework/</link><guid isPermaLink="true">https://agenticdotnet.com/blog/semantic-kernel-vs-microsoft-agent-framework/</guid><description>Semantic Kernel or the Microsoft Agent Framework? Since the 1.0 GA merge, the answer changed. A clear breakdown of what to use for new projects and how to migrate existing ones.</description><pubDate>Tue, 14 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Streaming AI Agent Responses to a Web UI in .NET</title><link>https://agenticdotnet.com/blog/streaming-ai-agent-responses-web-ui-dotnet/</link><guid isPermaLink="true">https://agenticdotnet.com/blog/streaming-ai-agent-responses-web-ui-dotnet/</guid><description>Waiting for a full agent response feels broken. Learn how to stream tokens from a .NET agent to the browser with Server-Sent Events, so answers appear word-by-word.</description><pubDate>Tue, 14 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Structured Output from .NET Agents: Getting Reliable JSON in C#</title><link>https://agenticdotnet.com/blog/structured-output-dotnet-agents-json/</link><guid isPermaLink="true">https://agenticdotnet.com/blog/structured-output-dotnet-agents-json/</guid><description>An agent that returns prose is hard to program against. How to get reliable, strongly-typed JSON out of a .NET agent — with schemas, typed responses, and validation.</description><pubDate>Tue, 14 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Testing and Evaluating AI Agents in .NET</title><link>https://agenticdotnet.com/blog/testing-evaluating-ai-agents-dotnet/</link><guid isPermaLink="true">https://agenticdotnet.com/blog/testing-evaluating-ai-agents-dotnet/</guid><description>AI agents are non-deterministic, but that does not make them untestable. A practical strategy for unit-testing tools, mocking the model, and evaluating agent quality in .NET.</description><pubDate>Tue, 14 Jul 2026 00:00:00 GMT</pubDate></item><item><title>The Microsoft Agent Framework for .NET: A Developer&apos;s Guide</title><link>https://agenticdotnet.com/blog/microsoft-agent-framework-dotnet-guide/</link><guid isPermaLink="true">https://agenticdotnet.com/blog/microsoft-agent-framework-dotnet-guide/</guid><description>Microsoft Agent Framework 1.0 unifies Semantic Kernel and AutoGen into one .NET SDK for building AI agents. Here is what it is, why it exists, and how to build your first agent in C#.</description><pubDate>Mon, 13 Jul 2026 00:00:00 GMT</pubDate></item><item><title>Model Context Protocol for .NET Developers: Giving Your Agent Real Tools</title><link>https://agenticdotnet.com/blog/model-context-protocol-dotnet-agent-framework/</link><guid isPermaLink="true">https://agenticdotnet.com/blog/model-context-protocol-dotnet-agent-framework/</guid><description>A practical guide to Model Context Protocol (MCP) for .NET developers: connect a Microsoft Agent Framework agent to an MCP server and expose your own agent as one.</description><pubDate>Mon, 13 Jul 2026 00:00:00 GMT</pubDate></item></channel></rss>