<?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>Cole-Medin on Intelligent Artifact</title>
    <link>https://intelligentartifact.com/tags/cole-medin/</link>
    <description>Recent content in Cole-Medin on Intelligent Artifact</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Tue, 01 Sep 2026 17:06:40 +0000</lastBuildDate>
    <atom:link href="https://intelligentartifact.com/tags/cole-medin/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>11 Tiny Coding Agent Fixes With a Stupid Amount of Payoff — Cole Medin</title>
      <link>https://intelligentartifact.com/posts/11-tiny-coding-agent-fixes-stupid-payoff/</link>
      <pubDate>Tue, 01 Sep 2026 17:06:40 +0000</pubDate>
      <guid>https://intelligentartifact.com/posts/11-tiny-coding-agent-fixes-stupid-payoff/</guid>
      <description>Cole Medin&amp;#39;s 11 small, high-leverage fixes for making any coding agent more reliable — from writing for the agent (not the human) and keeping rules under ~200 lines, to moving guarantees into deterministic hooks and never letting the writer approve its own work.</description>
    </item>
  </channel>
</rss>
