<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Loop-Engineering on David R. Longnecker - Converting Coffee to Code</title><link>https://drlongnecker.com/tags/loop-engineering/</link><description>Recent content in Loop-Engineering on David R. Longnecker - Converting Coffee to Code</description><generator>Hugo</generator><language>en</language><lastBuildDate>Fri, 07 Aug 2026 09:00:00 -0600</lastBuildDate><atom:link href="https://drlongnecker.com/tags/loop-engineering/index.xml" rel="self" type="application/rss+xml"/><item><title>Building the Loop Around the Agent</title><link>https://drlongnecker.com/blog/2026/08/building-the-loop-around-the-agent/</link><pubDate>Fri, 07 Aug 2026 09:00:00 -0600</pubDate><guid>https://drlongnecker.com/blog/2026/08/building-the-loop-around-the-agent/</guid><description>&lt;p&gt;Years before any of this had a name, I had a script on my homelab box that restarted a flaky transcode job, checked the log for a specific error string, and gave up after five tries instead of running all night. It was maybe fifteen lines of PowerShell, later rewritten in Rust once I got tired of PowerShell&amp;rsquo;s startup time on that box. The retry logic was never the interesting part. The giving-up logic was. A script that retries forever isn&amp;rsquo;t automation, it&amp;rsquo;s a slow-motion outage with a delay timer.&lt;/p&gt;</description></item></channel></rss>