<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Claude Code on Gary&#39;s Blog</title>
    <link>https://GaaraZhu.github.io/tags/claude-code/</link>
    <description>Recent content in Claude Code on Gary&#39;s Blog</description>
    <generator>Hugo</generator>
    <language>en</language>
    <managingEditor>sec.gary@gmail.com (GaryZhu)</managingEditor>
    <webMaster>sec.gary@gmail.com (GaryZhu)</webMaster>
    <lastBuildDate>Sun, 17 May 2026 22:00:00 +1200</lastBuildDate>
    <atom:link href="https://GaaraZhu.github.io/tags/claude-code/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Gate: a deterministic PII boundary between your data and AI agents</title>
      <link>https://GaaraZhu.github.io/introducing-gate/</link>
      <pubDate>Sun, 17 May 2026 22:00:00 +1200</pubDate><author>sec.gary@gmail.com (GaryZhu)</author>
      <guid>https://GaaraZhu.github.io/introducing-gate/</guid>
      <description>&lt;h2 id=&#34;the-thing-that-should-have-been-a-2-am-incident&#34;&gt;The thing that should have been a 2 a.m. incident&lt;/h2&gt;&#xA;&lt;p&gt;You wire a database tool into your coding agent. PostgreSQL, Databricks, an internal HTTP API — whatever. The agent is &lt;em&gt;useful&lt;/em&gt;. It joins tables you&amp;rsquo;d forgotten existed, drafts the migration, and writes the report. Productivity goes up.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
