This archive page showcases our in-depth coverage of agentic AI, a crucial aspect of software engineering that involves designing and implementing intelligent systems capable of autonomous decision-making and action. By exploring the principles, architectures, and best practices of agentic AI in .NET, software engineers can develop more robust and efficient AI-powered applications. Our articles pr…
8 articles since Aug 2026
Explore the architectural differences, extensibility patterns, and performance trade‑offs of Claude Agent SDK vs Semantic Kernel—essential reading for senior engineers building production AI agents.
Learn how to design, test, and operate MCP server versioning and backward compatibility at scale, with concrete patterns, CI/CD pipelines, and real‑world case studies.
Learn how to harden Model Context Protocol (MCP) servers against prompt injection and tool abuse with real‑world .NET patterns, sandboxing, and observability.
Learn how senior engineers can reliably deploy agentic AI workloads on Azure AI Foundry using Kubernetes, with concrete architecture, code, cost, and failure‑mode guidance.
Explore the Semantic Kernel vs LangChain latency and throughput benchmarks with real‑world data, code snippets, and actionable guidance for senior engineers building agentic AI services.
Learn how to architect, implement, and operate a production‑grade agent harness in ASP.NET Core using Semantic Kernel, MCP, and Azure services – the five‑layer approach that scales.
Explore a production‑grade NVIDIA NOOA vs LangChain comparison, covering architecture, performance, Azure integration, and real‑world .NET use cases for agentic AI.
Explore a production‑grade Agentic AI Customer Support Platform Architecture, from multi‑agent orchestration in .NET to Azure AI Foundry integration, with concrete code, scaling tactics, and hard‑won lessons.