<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Prompting Patterns on Vibe Coding</title><link>https://vibecoding.rest/series/prompting-patterns/</link><description>Recent content in Prompting Patterns on Vibe Coding</description><generator>Hugo</generator><language>en</language><lastBuildDate>Mon, 09 Feb 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://vibecoding.rest/series/prompting-patterns/index.xml" rel="self" type="application/rss+xml"/><item><title>Breaking Big Tasks Into Agent-Sized Steps</title><link>https://vibecoding.rest/posts/breaking-down-big-tasks/</link><pubDate>Mon, 09 Feb 2026 00:00:00 +0000</pubDate><guid>https://vibecoding.rest/posts/breaking-down-big-tasks/</guid><description>&lt;p&gt;Vague, large prompts produce vague, large diffs — and vague diffs are the hardest kind to review. The fix isn&amp;rsquo;t a cleverer prompt; it&amp;rsquo;s decomposition.&lt;/p&gt;&#10;&lt;h2 id="signs-a-task-is-too-big"&gt;Signs a task is too big&lt;/h2&gt;&#10;&lt;ul&gt;&#10;&lt;li&gt;You can&amp;rsquo;t describe what &amp;ldquo;done&amp;rdquo; looks like in one sentence&lt;/li&gt;&#10;&lt;li&gt;The task touches more than two or three unrelated parts of the system&lt;/li&gt;&#10;&lt;li&gt;You&amp;rsquo;d need to check in multiple times even if a human were doing it&lt;/li&gt;&#10;&lt;/ul&gt;&#10;&lt;p&gt;If any of these are true, break it down before prompting.&lt;/p&gt;</description></item><item><title>Context Is the Whole Game</title><link>https://vibecoding.rest/posts/context-is-the-whole-game/</link><pubDate>Mon, 02 Feb 2026 00:00:00 +0000</pubDate><guid>https://vibecoding.rest/posts/context-is-the-whole-game/</guid><description>&lt;p&gt;When an agent produces something wrong, the instinct is to blame the model. Most of the time, the real cause is upstream: it was missing context a human in the same seat would have had automatically.&lt;/p&gt;</description></item></channel></rss>