<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Claude on Blog | Tomáš Tomeček</title>
    <link>https://blog.tomecek.net/tags/claude/</link>
    <description>Recent content in Claude on Blog | Tomáš Tomeček</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en-us</language>
    <lastBuildDate>Mon, 19 Jan 2026 09:00:00 +0200</lastBuildDate><atom:link href="https://blog.tomecek.net/tags/claude/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Ambient Code followup: PR merged</title>
      <link>https://blog.tomecek.net/post/ambient-code-merged/</link>
      <pubDate>Mon, 19 Jan 2026 09:00:00 +0200</pubDate>
      
      <guid>https://blog.tomecek.net/post/ambient-code-merged/</guid>
      <description>&lt;p&gt;This is a followup to &lt;a href=&#34;https://blog.tomecek.net/post/ambient-code/&#34;&gt;my previous post about how I tried Ambient Code&lt;/a&gt;.&lt;/p&gt;
&lt;p&gt;TL;DR: &lt;a href=&#34;https://github.com/packit/specfile/pull/508&#34;&gt;I opened a PR (#specfile/508)&lt;/a&gt; and had to take over in the end.&lt;/p&gt;
&lt;img src=&#34;https://blog.tomecek.net/img/ice.JPG&#34; style=&#34;width: 640px;&#34;&gt;
&lt;h2 id=&#34;where-did-we-end&#34;&gt;Where did we end?&lt;/h2&gt;
&lt;p&gt;Claude Code proposed a solid implementation plan to us, Stella (the staff engineer agent) approved it.&lt;/p&gt;</description>
    </item>
    
    <item>
      <title>Ambient Code: first impressions</title>
      <link>https://blog.tomecek.net/post/ambient-code/</link>
      <pubDate>Mon, 12 Jan 2026 19:00:00 +0200</pubDate>
      
      <guid>https://blog.tomecek.net/post/ambient-code/</guid>
      <description>Ambient Code is a platform (not covered here) and a collection of AI coding agents and workflows designed to help with software development. I decided to give it a shot and see how well their agents can analyze and contribute to one of our projects in Packit org.
The first tool we are going to use is called agentready. It checks how well a project is maintained and suited for AI-assisted development.</description>
    </item>
    
    <item>
      <title>First test of Claude Sonnet 4.5 for an agent that backports a patch for an RPM</title>
      <link>https://blog.tomecek.net/post/agentic-ai-claude-sonnet-4-5/</link>
      <pubDate>Mon, 06 Oct 2025 08:00:00 +0200</pubDate>
      
      <guid>https://blog.tomecek.net/post/agentic-ai-claude-sonnet-4-5/</guid>
      <description>&lt;p&gt;One of the daily tasks we have when developing AI agents is to review their
runs. We have to read dozens of decisions so we can evaluate if the agents did
the right thing. If not, we have to adjust our user prompts, system prompts, and
tools.&lt;/p&gt;
&lt;p&gt;Let&amp;rsquo;s review how Sonnet 4.5 performs while backporting a complex patch
(with multiple conflicts).&lt;/p&gt;
&lt;img src=&#34;https://blog.tomecek.net/img/mushroom-2025.png&#34; style=&#34;width: 800px;&#34;&gt;</description>
    </item>
    
  </channel>
</rss>
