<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Workflow on ferkakta.dev</title><link>https://ferkakta.dev/tags/workflow/</link><description>Recent content in Workflow on ferkakta.dev</description><generator>Hugo</generator><language>en-US</language><copyright>Copyright fizz.</copyright><lastBuildDate>Thu, 12 Mar 2026 09:00:00 -0600</lastBuildDate><atom:link href="https://ferkakta.dev/tags/workflow/index.xml" rel="self" type="application/rss+xml"/><item><title>AI coding tools assume single-threaded users</title><link>https://ferkakta.dev/ai-tools-assume-single-threaded-users/</link><pubDate>Thu, 12 Mar 2026 09:00:00 -0600</pubDate><guid>https://ferkakta.dev/ai-tools-assume-single-threaded-users/</guid><description>&lt;p&gt;In January, Claude Code was generating so many artifacts that my main project&amp;rsquo;s &lt;code&gt;docs/&lt;/code&gt; directory was filling up with plans and handoffs from multiple orgs, multiple projects, and multiple dates. I sketched a Hive partition scheme — &lt;code&gt;org/project/dt=YYYY-MM-DD/&lt;/code&gt; — to tame the mess. I never built it.&lt;/p&gt;
&lt;p&gt;The plan singleton problem came later and turned out to be worse. Claude Code&amp;rsquo;s plan mode stores one plan per session. Switch workstreams and the old plan haunts you. Start a new plan and the old one gets destroyed. No amount of directory structure fixes that — the singleton lives inside the session, not on disk. Both problems grow from the same root: AI coding tools assume you&amp;rsquo;re doing one thing at a time.&lt;/p&gt;</description></item></channel></rss>