<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Open-Source Projects on René Zander | AI Automation Consultant</title><link>https://renezander.com/projects/</link><description>Recent content in Open-Source Projects on René Zander | AI Automation Consultant</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sun, 06 Sep 2026 09:00:00 +0200</lastBuildDate><atom:link href="https://renezander.com/projects/index.xml" rel="self" type="application/rss+xml"/><item><title>capcut-cli: A Deterministic Boundary, Running in Public</title><link>https://renezander.com/projects/capcut-cli/</link><pubDate>Sun, 06 Sep 2026 09:00:00 +0200</pubDate><guid>https://renezander.com/projects/capcut-cli/</guid><description>&lt;h2 id="where-the-model-has-to-stop">Where the model has to stop&lt;/h2>
&lt;p>The interesting question in an AI pipeline is never whether a model can do the work. It is where the model is required to stop.&lt;/p>
&lt;p>Timing, subtitle placement, track layout and cut points are arithmetic. They belong in code that returns the same output on every run, that can be diffed against the last version, linted before it ships, and rolled back when it is wrong. Segment selection and hook copy are judgment calls, and those belong to a model or a person. Almost every stalled pilot I get called into has those two halves mixed together, which is why nobody can say what broke.&lt;/p></description></item></channel></rss>