<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Software-Engineering on René Zander | AI Automation Consultant</title><link>https://renezander.com/tags/software-engineering/</link><description>Recent content in Software-Engineering on René Zander | AI Automation Consultant</description><generator>Hugo</generator><language>en</language><lastBuildDate>Wed, 03 Jun 2026 09:00:00 +0000</lastBuildDate><atom:link href="https://renezander.com/tags/software-engineering/index.xml" rel="self" type="application/rss+xml"/><item><title>Most of Your AI Skills Will Rot. Here's Which Ones Compound.</title><link>https://renezander.com/blog/ai-skills-rot-vs-compound/</link><pubDate>Wed, 03 Jun 2026 09:00:00 +0000</pubDate><guid>https://renezander.com/blog/ai-skills-rot-vs-compound/</guid><description>&lt;p>Prompts rot. Captured failures compound. Most of the AI skills you are building are mostly prompt, which is why most of them will not survive the year.&lt;/p>
&lt;p>Not because the prompts are bad. A skill&amp;rsquo;s value is maybe twenty percent instruction and eighty percent scar tissue, and only that second part lasts. The instruction rots the moment the thing it describes moves. Encode how your team deploys and it works until the pipeline changes. Then you are debugging a prompt at 2am, with less to go on than if you had written the script yourself.&lt;/p></description></item></channel></rss>