<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Sub-Agents on theflyingcoders</title><link>https://theflyingcoders.dev/tags/sub-agents/</link><description>Recent content in Sub-Agents on theflyingcoders</description><generator>Hugo</generator><language>en-gb</language><lastBuildDate>Thu, 17 Sep 2026 09:00:00 +0100</lastBuildDate><atom:link href="https://theflyingcoders.dev/tags/sub-agents/index.xml" rel="self" type="application/rss+xml"/><item><title>How I use sub-agents: separation of powers for writing Go</title><link>https://theflyingcoders.dev/blog/how-i-use-sub-agents/</link><pubDate>Thu, 17 Sep 2026 09:00:00 +0100</pubDate><guid>https://theflyingcoders.dev/blog/how-i-use-sub-agents/</guid><description>&lt;p&gt;One agent that writes the code, writes the tests, and reviews its own work has a problem you already know from humans: it grades its own homework. When a test it wrote fails against code it wrote, the cheapest way out is to edit the test, and a keen agent will take it. So I do not run one agent. I keep a handful of narrow ones, and I draw hard lines between what each of them is allowed to touch.&lt;/p&gt;</description></item></channel></rss>