<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Lessons-Learned on EBKAC.ORG</title>
    <link>https://ebkac.org/tags/lessons-learned/</link>
    <description>Recent content in Lessons-Learned on EBKAC.ORG</description>
    <generator>Hugo</generator>
    <language>en-gb</language>
    <lastBuildDate>Tue, 17 Mar 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://ebkac.org/tags/lessons-learned/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Lernreise 7/7: n8n, a Dead ThinkPad, and What&#39;s Next</title>
      <link>https://ebkac.org/blog/lernreise-07-tools-and-next/</link>
      <pubDate>Tue, 17 Mar 2026 00:00:00 +0000</pubDate>
      <guid>https://ebkac.org/blog/lernreise-07-tools-and-next/</guid>
      <description>&lt;p&gt;Every project like this ends with a set of opinions you did not have before. Here are mine.&lt;/p&gt;&#xA;&lt;hr&gt;&#xA;&lt;p&gt;&lt;strong&gt;n8n&lt;/strong&gt;&lt;/p&gt;&#xA;&lt;p&gt;I will be charitable and say: n8n is excellent for linear workflows of three to five nodes. Trigger, action, done. For anything more complex, it becomes something I would describe, with some restraint, as binary toxic waste.&lt;/p&gt;&#xA;&lt;p&gt;Visual workflow tools have an inherent problem: the visual representation is the code. You cannot refactor it the way you refactor code. You cannot diff it sensibly. You cannot review it in a pull request. When a node is producing wrong output and you need to understand why, you are clicking through a canvas, unfolding nested expressions, reading JavaScript embedded in a UI field that was not designed to hold much JavaScript.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Lernreise 6/7: What AI Actually Can (and Cannot) Do</title>
      <link>https://ebkac.org/blog/lernreise-06-lessons-ai/</link>
      <pubDate>Mon, 16 Mar 2026 00:00:00 +0000</pubDate>
      <guid>https://ebkac.org/blog/lernreise-06-lessons-ai/</guid>
      <description>&lt;p&gt;I want to write this post carefully, because the nuance matters and most things written about AI productivity are not careful.&lt;/p&gt;&#xA;&lt;p&gt;The AI tools I used this week were remarkable and frustrating in roughly equal measure, at different times, for different reasons. Both things are true. Neither cancels the other.&lt;/p&gt;&#xA;&lt;hr&gt;&#xA;&lt;p&gt;Start with the remarkable.&lt;/p&gt;&#xA;&lt;p&gt;The wiki documentation was worth the experiment on its own. Every piece of infrastructure I provisioned, every workflow component I built, ended up documented in the Gitea wiki in language that a human could read and learn from. Not command logs. Actual explanations: what was built, why this approach was chosen, what to watch out for. This is documentation that would never have existed if I had done the work alone, because I am the kind of person who documents things enthusiastically on day one and then never again.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
