<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Spring-Integration on Hullabalooing</title>
    <link>https://cruver.ai/tags/spring-integration/</link>
    <description>Recent content in Spring-Integration on Hullabalooing</description>
    <generator>Hugo</generator>
    <language>en</language>
    <lastBuildDate>Tue, 16 Jun 2026 15:54:23 +0000</lastBuildDate>
    <atom:link href="https://cruver.ai/tags/spring-integration/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>My Job Is to Write Loops</title>
      <link>https://cruver.ai/side-projects/posts/writing-loops-not-prompts/</link>
      <pubDate>Tue, 16 Jun 2026 15:54:23 +0000</pubDate>
      <guid>https://cruver.ai/side-projects/posts/writing-loops-not-prompts/</guid>
      <description>&lt;p&gt;Boris Cherny, the creator of Claude Code, said something recently that matched my own experience: &amp;ldquo;I don&amp;rsquo;t prompt Claude anymore&amp;hellip; my job is to write loops.&amp;rdquo; Peter Steinberger put it more bluntly: &amp;ldquo;You should be designing loops that prompt your agents.&amp;rdquo;&lt;/p&gt;&#xA;&lt;p&gt;I&amp;rsquo;ve been building LLM-powered pipelines on top of Spring Integration for a while, and those two lines named what I had been doing without quite realizing it. My time had stopped going into prompts. It was going into the loops around them.&lt;/p&gt;</description>
    </item>
    <item>
      <title>I Built an AI Video Pipeline. It&#39;s Mostly Enterprise Integration Patterns.</title>
      <link>https://cruver.ai/writing/posts/ai-video-pipeline-eip/</link>
      <pubDate>Sun, 24 May 2026 00:00:00 +0000</pubDate>
      <guid>https://cruver.ai/writing/posts/ai-video-pipeline-eip/</guid>
      <description>&lt;p&gt;I&amp;rsquo;ve spent the last few weeks building a documentary video generation pipeline. A topic goes in (say: &amp;ldquo;Sankebetsu brown bear incident 1915 Hokkaido&amp;rdquo;) and a finished mp4 comes out (a ten-minute narrated documentary, 27 scenes, original visuals, voiced by a documentary-grade TTS), all running on a homelab cluster.&lt;/p&gt;&#xA;&lt;p&gt;Between those two endpoints sits a chain of eight passes that hand off to each other. Several fan out to &amp;ldquo;do N things in parallel and aggregate.&amp;rdquo; Several produce artifacts measured in MB per scene that should not be shoved through a message broker. A few are the right place to put a human in the loop, where one minute of editorial review saves hours of GPU time downstream.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Three Production Apps, Zero Code: What Keip Actually Looks Like in Practice</title>
      <link>https://cruver.ai/homelab/posts/keip-connect-real-world-apps/</link>
      <pubDate>Fri, 13 Mar 2026 00:00:00 -0600</pubDate>
      <guid>https://cruver.ai/homelab/posts/keip-connect-real-world-apps/</guid>
      <description>&lt;h2 id=&#34;three-production-apps-zero-code-what-keip-actually-looks-like-in-practice&#34;&gt;Three Production Apps, Zero Code: What Keip Actually Looks Like in Practice&lt;a class=&#34;anchor&#34; href=&#34;#three-production-apps-zero-code-what-keip-actually-looks-like-in-practice&#34;&gt;#&lt;/a&gt;&lt;/h2&gt;&#xA;&lt;p&gt;In the past month I shipped three integration apps to my home cluster: a Spanish translator that replies in audio, a health tracking bot I can query from any room in my house, and a camera alert system that decides for itself what&amp;rsquo;s worth telling me about. Each one took under an hour to have running. None of them required me to write a single line of application code.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
