
  <rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
    <channel>
      <title>Cracked AI Engineering</title>
      <link>https://www.crackedaiengineering.com/blog</link>
      <description>A blog created with Next.js and Tailwind.css</description>
      <language>en-us</language>
      <managingEditor>undefined (Pat Nadolny)</managingEditor>
      <webMaster>undefined (Pat Nadolny)</webMaster>
      <lastBuildDate>Sat, 11 Apr 2026 00:00:00 GMT</lastBuildDate>
      <atom:link href="https://www.crackedaiengineering.com/tags/ai-engineering/feed.xml" rel="self" type="application/rss+xml"/>
      
  <item>
    <guid>https://www.crackedaiengineering.com/blog/ai-evals-explained</guid>
    <title>Evals: The New Unit Test</title>
    <link>https://www.crackedaiengineering.com/blog/ai-evals-explained</link>
    <description>How I think about evals at Cora AI — and why the unit test analogy is the right mental model for engineers coming from a traditional software background.</description>
    <pubDate>Sat, 11 Apr 2026 00:00:00 GMT</pubDate>
    <author>undefined (Pat Nadolny)</author>
    <category>ai</category><category>best-practices</category><category>ai-engineering</category>
  </item>

  <item>
    <guid>https://www.crackedaiengineering.com/blog/the-orchestration-sweet-spot</guid>
    <title>The Orchestration Sweet Spot</title>
    <link>https://www.crackedaiengineering.com/blog/the-orchestration-sweet-spot</link>
    <description>Between the rigid determinism of workflow automation and the chaos of free-roaming agents lies the architecture worth building. Here&#39;s how we think about it at Cora.</description>
    <pubDate>Tue, 07 Apr 2026 00:00:00 GMT</pubDate>
    <author>undefined (Pat Nadolny)</author>
    <category>ai</category><category>engineering</category><category>agents</category><category>ai-engineering</category>
  </item>

    </channel>
  </rss>
