RAG in .NET: The Complete Series
Last updated: 28 July 2026 Retrieval-Augmented Generation is a pattern, not a framework, and the gap between a RAG tutorial and a RAG pipeline that stays healthy in production is substantial. This series covers what…
-
-
Agentic AI AI & Generative AI Claude Developer Life & Productivity General Development Microsoft MVP & Career
Microsoft MVP in AI for the 8th Year Running
Microsoft awarded me the Most Valuable Professional Award for the 8th year in a row. The disk was shipped and each year it still means something. I don’t take it for granted. Eight years is…
-
AI & Generative AI Developer Life & Productivity MVP & Career Process Improvement Productivity Prototyping
I’ve Seen This Pattern Before. Are You Building for What Comes After Cheap AI Access?
I shut down a SaaS product a few years ago. Not because the idea was wrong, and not because the market wasn’t there. Because the platform underneath it changed ownership, repriced its API overnight, and…
-
How to Get the Most Out of Claude Code: Tips From Real-World Use
I’ve been using Claude Code heavily across AI engineering work: RAG pipelines, .NET MCP servers, content automation, agentic workflows. The way I use it now looks nothing like how I started. Most write-ups on Claude…
-
AI & Generative AI Claude Generative AI Microsoft Agent Framework Prompt Engineering RAG Semantic Kernel
A Developer’s Guide to Building RAG Systems: Lessons from the Trenches
I have spent a good while now building RAG pipelines across a number of engagements, mostly for documentation sites, and the gap between the tutorials and the reality of production is substantial. This post is…
-
When an Azure WebJob Aborts With No Error: Diagnosing a Silent Kill in a RAG Ingestion Pipeline
A continuous Azure WebJob stopped mid-run with no exception, no stack trace, and no shutdown message. Here’s why the Web App memory chart lied, and how to find out who killed your process.
-
RAG Chunker Fast Path That Measured a Placeholder Instead of 40 KB of Code
A RAG chunker’s “is this small enough to skip splitting?” check ran against placeholder text, not the real code it stood in for — so oversized code-heavy chunks sailed straight past the embedding model’s token limit.
-
The 8192-Token Cliff: Why Your .NET RAG Pipeline Throws Random 500s
A production RAG agent threw intermittent 500s because nobody guarded the upper length of the embedding query – here is the two-tier fix and the multi-turn edge case that hides it.
-
Building a RAG Administration Tool with .NET, Elasticsearch and OpenAI
When you build and ship a RAG pipeline, you quickly discover that the real work is not the initial vectorisation pass. It is keeping the pipeline healthy after that. Documents get deleted, re-crawled content fails…
