<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>LLMs Engineering — Writing</title><description>Practitioner notes on shipping LLM systems: RAG, agents, fine-tuning, and LLMOps.</description><link>https://llmsengineer.com/</link><language>en-us</language><item><title>What is RAG, and when should you use it?</title><link>https://llmsengineer.com/blog/what-is-rag/</link><guid isPermaLink="true">https://llmsengineer.com/blog/what-is-rag/</guid><description>A plain-English guide to retrieval-augmented generation — what it is, what problem it solves, and when it&apos;s the right tool (and when it isn&apos;t).</description><pubDate>Wed, 13 May 2026 00:00:00 GMT</pubDate></item><item><title>What is an AI agent? A plain-English guide</title><link>https://llmsengineer.com/blog/what-is-an-ai-agent/</link><guid isPermaLink="true">https://llmsengineer.com/blog/what-is-an-ai-agent/</guid><description>Agents are not chatbots. A plain-English explanation of what AI agents actually are, where they help, and where they make things worse.</description><pubDate>Tue, 12 May 2026 00:00:00 GMT</pubDate></item><item><title>What is LLMOps, and why does production AI break without it?</title><link>https://llmsengineer.com/blog/what-is-llmops/</link><guid isPermaLink="true">https://llmsengineer.com/blog/what-is-llmops/</guid><description>Shipping an AI feature is the start, not the finish. LLMOps — in plain English — is everything you need so it keeps working once real users find it.</description><pubDate>Mon, 11 May 2026 00:00:00 GMT</pubDate></item><item><title>Fine-tuning, prompting, or RAG: which one do you actually need?</title><link>https://llmsengineer.com/blog/fine-tuning-vs-prompting-vs-rag/</link><guid isPermaLink="true">https://llmsengineer.com/blog/fine-tuning-vs-prompting-vs-rag/</guid><description>Three very different ways to make an AI behave the way you want — explained without jargon, with a simple rule for picking between them.</description><pubDate>Sun, 10 May 2026 00:00:00 GMT</pubDate></item><item><title>Different ways to build a RAG system, in plain English</title><link>https://llmsengineer.com/blog/rag-stacks-compared/</link><guid isPermaLink="true">https://llmsengineer.com/blog/rag-stacks-compared/</guid><description>Naive RAG, hybrid retrieval, reranking, multi-vector. The main approaches to building a RAG system — without the jargon.</description><pubDate>Sat, 09 May 2026 00:00:00 GMT</pubDate></item><item><title>Agentic RAG: when your assistant should think before it searches</title><link>https://llmsengineer.com/blog/agentic-rag/</link><guid isPermaLink="true">https://llmsengineer.com/blog/agentic-rag/</guid><description>What happens when retrieval-augmented generation meets AI agents — and why it can turn a Q&amp;A bot into a research assistant.</description><pubDate>Fri, 08 May 2026 00:00:00 GMT</pubDate></item><item><title>From RAG demo to production: the checklist nobody gave you</title><link>https://llmsengineer.com/blog/rag-production-checklist/</link><guid isPermaLink="true">https://llmsengineer.com/blog/rag-production-checklist/</guid><description>Most RAG systems look great in a notebook and embarrassing in production. Here is the gap nobody warns you about, and the checklist that closes it.</description><pubDate>Thu, 07 May 2026 00:00:00 GMT</pubDate></item><item><title>Choosing an LLMOps stack: LangSmith, LangFuse, LangWatch compared</title><link>https://llmsengineer.com/blog/llmops-stack-comparison/</link><guid isPermaLink="true">https://llmsengineer.com/blog/llmops-stack-comparison/</guid><description>Three tools, overlapping pitches, very different strengths in practice. Where each one wins, and how to pick without locking yourself in.</description><pubDate>Wed, 06 May 2026 00:00:00 GMT</pubDate></item><item><title>Building reliable AI agents: evaluation, guardrails, and the loop that won&apos;t end</title><link>https://llmsengineer.com/blog/building-reliable-agents/</link><guid isPermaLink="true">https://llmsengineer.com/blog/building-reliable-agents/</guid><description>Agents fail in characteristic ways. Here are the failure modes worth designing for — and the patterns that turn an unreliable agent into something you can deploy.</description><pubDate>Tue, 05 May 2026 00:00:00 GMT</pubDate></item></channel></rss>