<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Context · westerweel.work</title><link>https://westerweel.work/en/tags/context/</link><description>Latest pieces in Context on westerweel.work</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sat, 07 Nov 2026 23:12:18 +0100</lastBuildDate><atom:link href="https://westerweel.work/en/tags/context/index.xml" rel="self" type="application/rss+xml"/><item><title>Context is everything</title><link>https://westerweel.work/en/posts/2026-11-04-context-is-everything/</link><pubDate>Wed, 04 Nov 2026 00:00:00 +0000</pubDate><guid>https://westerweel.work/en/posts/2026-11-04-context-is-everything/</guid><description>An agent that guesses is usually missing context, not intelligence. From an MCP that sends agents to the knowledge base to SREna, a local SRE agent: the knowledge base is what prevents hallucination, not the model.</description></item></channel></rss>