AI Code Assistants: Cursor, Claude Code and Copilot in Production
Six months of AI coding assistants on a real .NET and Python codebase: where they genuinely help, where they generate noise, and what they cost.
AI tooling you can actually ship.
Practical guides for AI agents, retrieval pipelines and GEO tooling. Every post names the model, the version and the step that failed first.
Three ways in
6 postsTutorials
Step-by-step for agents, retrieval pipelines, workflow automation and GEO infrastructure.
4 postsComparisons
Two tools, same job. Here is where each one is faster, cheaper, or more annoying.
4 postsReviews
What a tool is like once the novelty wears off and the traffic arrives.
Latest
Prompt Engineering in Production Is a Systems Problem
The prompt is the smallest part of the system. What determines output quality is the context, the constraints, the feedback loop and the evaluation set.
Read the guideRecently published
All 14 posts →Write GEO Content That Gets Cited by Answer Engines
Structure pages so generative engines can lift them — a 40-60 word direct answer, extractable facts, matching structured data, and crawler access.
LLM Router vs LiteLLM Proxy vs Hosted Gateways: A Practical Guide
Three ways to route across models, compared on control, fallback behaviour, cost control, observability and portability — including when you need none of them.
Build Your First RAG Pipeline That Doesn't Hallucinate
A working retrieval-augmented pipeline with chunking, reranking and an evaluation harness — plus the three failure modes that produce confident wrong answers.
Embedding Model Review: Open-Source vs Hosted for RAG
bge-m3, gte, nomic-embed against hosted APIs: multilingual reach, long text, dimension cost, retrieval quality and the index rebuild trap.
Who writes this
Henry Xiang
I build and run multi-tenant AI content automation in production — agents, retrieval pipelines, and the GEO layer that makes them findable. Everything here was wired into a system with real traffic before it was written up.
Everything here is tested against a multi-tenant pipeline in production. No sponsored verdicts, no review copies unless the post says so.
- Architecturethe actual pipeline
- Correctionstell me a version is stale
- Moneyhow affiliate links work here
- FeedRSS