<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>Prompt-Caching on Loop &amp; Retry</title>
    <link>https://loopandretry.github.io/tags/prompt-caching/</link>
    <description>Recent content in Prompt-Caching on Loop &amp; Retry</description>
    <image>
      <title>Loop &amp; Retry</title>
      <url>https://loopandretry.github.io/images/og-default.png</url>
      <link>https://loopandretry.github.io/images/og-default.png</link>
    </image>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Mon, 20 Jul 2026 21:00:00 -0400</lastBuildDate>
    <atom:link href="https://loopandretry.github.io/tags/prompt-caching/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Prompt caching: what actually gets cached, and when it silently misses</title>
      <link>https://loopandretry.github.io/posts/prompt-caching-silent-misses/</link>
      <pubDate>Mon, 20 Jul 2026 21:00:00 -0400</pubDate>
      <guid>https://loopandretry.github.io/posts/prompt-caching-silent-misses/</guid>
      <description>Prompt caching can cut your input-token bill by 90% on the reused part of a request — or do nothing at all, with no error to tell you which. It&amp;rsquo;s an exact-prefix match with a short TTL, and small, common mistakes in how agents build requests break it silently. Here&amp;rsquo;s what actually gets cached, the five ways real agents lose the discount without noticing, and how to check whether yours is.</description>
    </item>
  </channel>
</rss>
