<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>AI on Cliff Hults</title><link>https://www.haguest.com/tags/ai/</link><description>Recent content in AI on Cliff Hults</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>© 2026 Cliff Hults</copyright><lastBuildDate>Sat, 11 Apr 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://www.haguest.com/tags/ai/index.xml" rel="self" type="application/rss+xml"/><item><title>Prompt Engineering Isn't Magic — Here's How I Did It in Production</title><link>https://www.haguest.com/posts/2026-04-11-prompt-engineering-in-production/</link><pubDate>Sat, 11 Apr 2026 00:00:00 +0000</pubDate><guid>https://www.haguest.com/posts/2026-04-11-prompt-engineering-in-production/</guid><description>&lt;p>Most prompt engineering content is written by people who have never shipped AI into a real system. This post is different.&lt;/p>
&lt;p>I&amp;rsquo;m a Staff DevOps Engineer. I&amp;rsquo;ve spent time integrating AWS Bedrock into actual production workflows inside a FedRAMP High environment, not demos, not notebooks, not prototypes. Real systems with real constraints and real failure modes.&lt;/p>
&lt;p>Here&amp;rsquo;s what I learned.&lt;/p></description></item></channel></rss>