<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>AnetLab Blog</title><description>Senior engineering practice: RAG and AI/LLM on .NET, integrations, legacy modernisation. No marketing.</description><link>https://anetlab.com/</link><language>en-us</language><item><title>Contextum: the document pipeline to Markdown for AI agents</title><link>https://anetlab.com/blog/contextum-document-pipeline/</link><guid isPermaLink="true">https://anetlab.com/blog/contextum-document-pipeline/</guid><description>AnetLab Contextum: a five-stage pipeline between an agent and an LLM — Markdown conversion, context compression, idempotent delivery and an honest loss registry.</description><pubDate>Wed, 21 Oct 2026 00:00:00 GMT</pubDate><category>AI/LLM</category><category>.NET</category><category>RAG</category><author>project@anetlab.ru</author></item><item><title>RAG evaluation on .NET: Recall@5, MRR and the release gate</title><link>https://anetlab.com/blog/rag-evaluation-dotnet/</link><guid isPermaLink="true">https://anetlab.com/blog/rag-evaluation-dotnet/</guid><description>How to measure RAG quality on .NET: a Golden Set of 50–100 questions, computing Recall@5 and MRR, measuring faithfulness and eval-as-a-release-gate in CI.</description><pubDate>Tue, 20 Oct 2026 00:00:00 GMT</pubDate><category>AI/LLM</category><category>.NET</category><category>RAG</category><category>Evaluation</category><author>project@anetlab.ru</author></item><item><title>Agentic workflows in enterprise: patterns and anti-patterns</title><link>https://anetlab.com/blog/agentic-workflows-enterprise/</link><guid isPermaLink="true">https://anetlab.com/blog/agentic-workflows-enterprise/</guid><description>When agents pay off in corporate processes and when a deterministic workflow is enough: architecture, typical failures and a rollout checklist.</description><pubDate>Mon, 19 Oct 2026 00:00:00 GMT</pubDate><category>AI/LLM</category><category>Agents</category><category>Architecture</category><author>project@anetlab.ru</author></item><item><title>Engineering leadership in AI products: evaluation, roles, delivery</title><link>https://anetlab.com/blog/engineering-leadership-ai/</link><guid isPermaLink="true">https://anetlab.com/blog/engineering-leadership-ai/</guid><description>What changes in a tech lead’s job with AI products: eval as an engineering practice, ownership of the answer, team topology and the CI/CD/CE cycle.</description><pubDate>Mon, 19 Oct 2026 00:00:00 GMT</pubDate><category>AI/LLM</category><category>Leadership</category><category>Team</category><author>project@anetlab.ru</author></item><item><title>Enterprise AI architecture: four decisions that decide everything</title><link>https://anetlab.com/blog/enterprise-ai-architecture/</link><guid isPermaLink="true">https://anetlab.com/blog/enterprise-ai-architecture/</guid><description>A practical guide to the architecture of corporate AI systems: RAG vs fine-tuning, agents vs workflows, quality evaluation and governance.</description><pubDate>Sun, 18 Oct 2026 00:00:00 GMT</pubDate><category>AI/LLM</category><category>Architecture</category><category>Evaluation</category><author>project@anetlab.ru</author></item><item><title>Production RAG: a 50-point checklist for production</title><link>https://anetlab.com/blog/production-rag-checklist/</link><guid isPermaLink="true">https://anetlab.com/blog/production-rag-checklist/</guid><description>A checklist for taking RAG to production: security, quality evaluation, observability, cost control and content lifecycle governance.</description><pubDate>Sat, 17 Oct 2026 00:00:00 GMT</pubDate><category>RAG</category><category>AI/LLM</category><category>Checklist</category><category>Evaluation</category><author>project@anetlab.ru</author></item><item><title>Taking an AI PoC to production: 90 days by phases</title><link>https://anetlab.com/blog/ai-poc-to-production/</link><guid isPermaLink="true">https://anetlab.com/blog/ai-poc-to-production/</guid><description>Why AI pilots do not reach production and how to fix it: Golden Set, eval pipeline, integration with the corporate context, LLMOps and a readiness checklist.</description><pubDate>Fri, 16 Oct 2026 00:00:00 GMT</pubDate><category>AI/LLM</category><category>Delivery</category><category>LLMOps</category><category>Evaluation</category><author>project@anetlab.ru</author></item><item><title>Modernising legacy .NET: WCF, AppDomains and the AI bridge</title><link>https://anetlab.com/blog/legacy-dotnet-modernisation/</link><guid isPermaLink="true">https://anetlab.com/blog/legacy-dotnet-modernisation/</guid><description>What really breaks when moving from .NET Framework to modern .NET: BinaryFormatter, AppDomains, WCF, YARP, Strangler Fig and the AI Bridge pattern.</description><pubDate>Thu, 15 Oct 2026 00:00:00 GMT</pubDate><category>.NET</category><category>Legacy</category><category>Modernisation</category><author>project@anetlab.ru</author></item><item><title>MCP for enterprise: protocol, security and boundaries</title><link>https://anetlab.com/blog/mcp-for-enterprise/</link><guid isPermaLink="true">https://anetlab.com/blog/mcp-for-enterprise/</guid><description>How to embed MCP in the corporate environment: the protocol primitives, the security model, schema bloat, call auditing and the choice between MCP, REST and Kafka.</description><pubDate>Wed, 14 Oct 2026 00:00:00 GMT</pubDate><category>AI/LLM</category><category>MCP</category><category>Integrations</category><author>project@anetlab.ru</author></item><item><title>.NET and Azure for AI systems: a reference architecture</title><link>https://anetlab.com/blog/dotnet-azure-ai-architecture/</link><guid isPermaLink="true">https://anetlab.com/blog/dotnet-azure-ai-architecture/</guid><description>How to assemble a production-ready AI system on .NET and Azure: async pipeline, RAG, Polly, observability and cost control — with working code.</description><pubDate>Tue, 13 Oct 2026 00:00:00 GMT</pubDate><category>.NET</category><category>AI/LLM</category><category>Architecture</category><category>RAG</category><author>project@anetlab.ru</author></item><item><title>Building a RAG pipeline on .NET: a practical walkthrough</title><link>https://anetlab.com/blog/rag-pipeline-dotnet/</link><guid isPermaLink="true">https://anetlab.com/blog/rag-pipeline-dotnet/</guid><description>A step-by-step build of a production-ready RAG on .NET 10 — from text extraction to the evaluation pipeline. With the real decisions, not abstractions.</description><pubDate>Tue, 06 Oct 2026 00:00:00 GMT</pubDate><category>RAG</category><category>.NET</category><category>AI/LLM</category><category>MCP</category><author>project@anetlab.ru</author></item><item><title>RAG on .NET: an architecture that survives production</title><link>https://anetlab.com/blog/rag-na-dotnet/</link><guid isPermaLink="true">https://anetlab.com/blog/rag-na-dotnet/</guid><description>Why naive RAG breaks on real data, and how we build a .NET pipeline: chunking, hybrid search, evaluation and cost control.</description><pubDate>Mon, 28 Sep 2026 00:00:00 GMT</pubDate><category>RAG</category><category>.NET</category><category>AI/LLM</category><author>project@anetlab.ru</author></item></channel></rss>