<?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>Design on Loop &amp; Retry</title>
    <link>https://loopandretry.github.io/tags/design/</link>
    <description>Recent content in Design 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>Wed, 08 Jul 2026 02:00:00 -0400</lastBuildDate>
    <atom:link href="https://loopandretry.github.io/tags/design/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>When not to build an agent</title>
      <link>https://loopandretry.github.io/posts/when-not-to-build-an-agent/</link>
      <pubDate>Wed, 08 Jul 2026 02:00:00 -0400</pubDate>
      <guid>https://loopandretry.github.io/posts/when-not-to-build-an-agent/</guid>
      <description>An agent is an LLM that controls its own control flow — and that autonomy has a price you pay on every run: quadratic token cost, serial latency, and a failure surface you can&amp;rsquo;t unit-test. Most tasks people reach for an agent on are a fixed pipeline wearing a costume. Here&amp;rsquo;s the decision checklist I use, the arithmetic on what the agent tax actually costs, and the same task built both ways so you can see the difference.</description>
    </item>
  </channel>
</rss>
