
  <rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
    <channel>
      <title>Articles by Dan Orlando</title>
      <link>https://danorlando.com/blog</link>
      <description>How-to&#39;s, discoveries and other useful nuggets fit for developer consumption.</description>
      <language>en-us</language>
      <managingEditor>undefined (Dan Orlando)</managingEditor>
      <webMaster>undefined (Dan Orlando)</webMaster>
      <lastBuildDate>Mon, 20 Apr 2026 00:00:00 GMT</lastBuildDate>
      <atom:link href="https://danorlando.com/tags/designpatterns/feed.xml" rel="self" type="application/rss+xml"/>
      
  <item>
    <guid>https://danorlando.com/blog/genai/context-engineering</guid>
    <title>Context Engineering: The Missing Layer</title>
    <link>https://danorlando.com/blog/genai/context-engineering</link>
    <description>A paper found that simply repeating the prompt before generation jumped accuracy from 21% to 97% on one benchmark. Everyone filed it under &quot;prompting tricks.&quot; The mechanism is architectural, and it&#39;s the clearest proof that context engineering and prompt engineering have completely different ceilings. Most teams are optimizing the wrong layer.</description>
    <pubDate>Mon, 20 Apr 2026 00:00:00 GMT</pubDate>
    <author>undefined (Dan Orlando)</author>
    <category>generativeai</category><category>agenticai</category><category>architecture</category><category>designpatterns</category>
  </item>

    </channel>
  </rss>
