<?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>Ai-Pipelines on Chris Hughes | Development Journal</title><link>https://blog.chughes.co/tags/ai-pipelines/</link><description>Recent content in Ai-Pipelines on Chris Hughes | Development Journal</description><generator>Hugo -- 0.161.1</generator><language>en-us</language><lastBuildDate>Tue, 24 Mar 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://blog.chughes.co/tags/ai-pipelines/index.xml" rel="self" type="application/rss+xml"/><item><title>The Three Misses</title><link>https://blog.chughes.co/posts/2026-03-24-the-three-misses-why-ai-pipelines-need-the-right-club-for-ev/</link><pubDate>Tue, 24 Mar 2026 00:00:00 +0000</pubDate><guid>https://blog.chughes.co/posts/2026-03-24-the-three-misses-why-ai-pipelines-need-the-right-club-for-ev/</guid><description>&lt;p&gt;&lt;em&gt;Written with Claude. The field visit, the data analysis, the issue filing, and this blog post were all done in one session.&lt;/em&gt;&lt;/p&gt;
&lt;p&gt;&lt;img alt="A golf course diagram showing three types of misses" loading="lazy" src="https://blog.chughes.co/images/2026-03-24-the-three-misses-why-ai-pipelines-need-the-right-club-for-ev/hero.svg"&gt;&lt;/p&gt;
&lt;h2 id="the-core-problem"&gt;The Core Problem&lt;/h2&gt;
&lt;p&gt;The worst thing an AI pipeline can do is put a plausible falsehood in a delivered report that nobody catches. Not a typo. Not a formatting issue. A statement that reads like a field observation, passes review because it sounds right, and lands in front of a client as fact.&lt;/p&gt;</description></item></channel></rss>