<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Plain-English AI on Xavier Tai</title><link>https://xaviertai.com/topics/plain-english-ai/</link><description>Recent content in Plain-English AI on Xavier Tai</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Mon, 06 Jul 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://xaviertai.com/topics/plain-english-ai/index.xml" rel="self" type="application/rss+xml"/><item><title>RAG for non-engineers: what it is and where it actually helps</title><link>https://xaviertai.com/writing/rag-for-non-engineers/</link><pubDate>Mon, 06 Jul 2026 00:00:00 +0000</pubDate><guid>https://xaviertai.com/writing/rag-for-non-engineers/</guid><description>&lt;p>Retrieval-augmented generation is a simple idea with an awkward name.&lt;/p>
&lt;p>Before an AI answers you, it looks something up first.&lt;/p>
&lt;p>That is the whole trick. A normal language model answers from memory, the way a student writes an exam from whatever is in their head. RAG hands that same student an open book and says: check the relevant page before you write. The model still does the writing. It has just stopped guessing about facts it was never taught.&lt;/p></description></item></channel></rss>