<?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>Delegation on {IT}</title><link>https://igortkanov.com/computers/delegation/</link><description>Recent content in Delegation on {IT}</description><generator>Hugo</generator><language>en-us</language><copyright>Copyright © 2026 {IT}. All rights reserved. Unless otherwise stated, all text, images, diagrams, and other original content on this blog may not be reproduced, distributed, or used without prior written permission.</copyright><lastBuildDate>Mon, 25 May 2026 19:19:04 +0000</lastBuildDate><atom:link href="https://igortkanov.com/computers/delegation/index.xml" rel="self" type="application/rss+xml"/><item><title>STATUS.md: a shared file for multi-agent work</title><link>https://igortkanov.com/status-md-for-multi-agent-work/</link><pubDate>Mon, 25 May 2026 19:19:04 +0000</pubDate><guid>https://igortkanov.com/status-md-for-multi-agent-work/</guid><description>&lt;p&gt;When I work on a bigger task – a new feature, a Terraform change, a small PoC – I usually run it across multiple agents at once. Claude Code in one window for the code, a Cowork session in another for planning and content, sometimes Desktop Claude in a third.&lt;/p&gt;
&lt;p&gt;The split works well until I switch between them and have to type some flavour of &amp;ldquo;where are we?&amp;rdquo; so the agent can guess. Each one has its own TODO list. None of them can see the others&amp;rsquo;. And so I end up as the human message bus, with the context windows filling up with status updates instead of actual work.&lt;/p&gt;</description></item></channel></rss>