<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Automation on Steve Wilson</title>
    <link>/tags/automation/</link>
    <description>Recent content in Automation on Steve Wilson</description>
    <generator>Hugo</generator>
    <language>en</language>
    <lastBuildDate>Sat, 22 Aug 2026 22:18:19 +0100</lastBuildDate>
    <atom:link href="/tags/automation/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Using AI to help do things</title>
      <link>/posts/using-ai-to-help-do-things/</link>
      <pubDate>Sat, 22 Aug 2026 22:18:19 +0100</pubDate>
      <guid>/posts/using-ai-to-help-do-things/</guid>
      <description>&lt;p&gt;I&amp;rsquo;ve been using AI more and more, but not really in the way the breathless articles tend to describe it. I don&amp;rsquo;t ask it to go away and magically solve my life. Most of the time it&amp;rsquo;s more like having a technical assistant sat next to me who is very fast at reading, reasonably good at pattern matching, and occasionally far too confident.&lt;/p&gt;&#xA;&lt;p&gt;The pattern is usually the same. I provide the actual situation: logs, screenshots, code, command output, measurements, photos or whatever constraints apply. It suggests likely causes or next things to try. I test those on the real system, or against the thing I&amp;rsquo;m physically working on, then feed the result back. After a few rounds the conversation is no longer generic advice, it&amp;rsquo;s about the specific problem in front of me.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
