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.
Tagged “llm”
10 articles.
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.
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.
How to Evaluate an LLM Pipeline So You Can Change It Safely
Build an evaluation set from real production traffic, assert on properties instead of exact strings, and wire it into CI so prompt changes ship on evidence.
Dify vs Flowise: Which LLM App Builder Survives Production?
Dify and Flowise compared after running both in production — orchestration model, RAG depth, self-hosting cost, API reuse and upgrade risk.
LangChain vs LlamaIndex: Which RAG Framework Fits Your Stack
LangChain optimises for agent chains and tool use; LlamaIndex optimises for ingestion and retrieval. Where each one actually saves you engineering time.
How to Cut Your LLM API Cost Without Breaking Quality
Measure first, then route, cache, shorten, batch, and quantize — a practical order of operations for cutting LLM spend without shipping worse output.
Langfuse Review: Six Months of LLM Tracing in Production
What Langfuse actually did for my LLM pipeline: trace capture, token accounting, online evals and self-hosting reality, including what I regret.