<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Agents on Rakesh Mothukuri</title><link>https://rakeshmothukuri.dev/tags/agents/</link><description>Recent content in Agents on Rakesh Mothukuri</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>© 2026</copyright><lastBuildDate>Thu, 29 Oct 2026 21:03:45 +0000</lastBuildDate><atom:link href="https://rakeshmothukuri.dev/tags/agents/index.xml" rel="self" type="application/rss+xml"/><item><title>Building a Software Factory: The Work Around the Model</title><link>https://rakeshmothukuri.dev/posts/the-work-around-the-model/</link><pubDate>Thu, 29 Oct 2026 21:03:45 +0000</pubDate><guid>https://rakeshmothukuri.dev/posts/the-work-around-the-model/</guid><description>&lt;p&gt;I have been building a software factory: a system in which agents take a piece of work from an idea to a change that is ready to merge. What follows isn&amp;rsquo;t a blueprint. It&amp;rsquo;s a few things that surprised me, and that I&amp;rsquo;d probably mention to anyone setting out to do the same&lt;/p&gt;
&lt;h2 class="relative group"&gt;The model was rarely the problem
&lt;div id="the-model-was-rarely-the-problem" class="anchor"&gt;&lt;/div&gt;
&lt;span
class="absolute top-0 w-6 transition-opacity opacity-0 ltr:-left-6 rtl:-right-6 not-prose group-hover:opacity-100"&gt;
&lt;a class="group-hover:text-primary-300 dark:group-hover:text-neutral-700 !no-underline" href="#the-model-was-rarely-the-problem" aria-label="Anchor"&gt;#&lt;/a&gt;
&lt;/span&gt;
&lt;/h2&gt;
&lt;p&gt;I had assumed most of the effort would go into the model: choosing it, prompting it, working round its mistakes. A fair amount did, and that work is real. But there were times when the model was doing perfectly reasonable work and very little of use came out the other end.&lt;/p&gt;</description></item></channel></rss>