<?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>Mcp on Chris Hughes | Development Journal</title><link>https://blog.chughes.co/tags/mcp/</link><description>Recent content in Mcp on Chris Hughes | Development Journal</description><generator>Hugo -- 0.161.1</generator><language>en-us</language><lastBuildDate>Sun, 26 Apr 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://blog.chughes.co/tags/mcp/index.xml" rel="self" type="application/rss+xml"/><item><title>Same Architecture, Different Verdicts: Eight Signals for Scale-Contingent Design</title><link>https://blog.chughes.co/posts/2026-04-26-same-architecture-different-verdicts-eight-signals-for-scale/</link><pubDate>Sun, 26 Apr 2026 00:00:00 +0000</pubDate><guid>https://blog.chughes.co/posts/2026-04-26-same-architecture-different-verdicts-eight-signals-for-scale/</guid><description>&lt;p&gt;&lt;em&gt;Written with Claude.&lt;/em&gt;&lt;/p&gt;
&lt;p&gt;&lt;img alt="A wood-and-brass hand plane on the left labeled &amp;lsquo;single firm&amp;rsquo;, a networked LCD-and-antenna power tool on the right labeled &amp;lsquo;fleet&amp;rsquo;" loading="lazy" src="https://blog.chughes.co/images/2026-04-26-same-architecture-different-verdicts-eight-signals-for-scale/hero.svg"&gt;&lt;/p&gt;
&lt;h2 id="writing-the-counterfactual-made-the-answer-obvious"&gt;Writing the Counterfactual Made the Answer Obvious&lt;/h2&gt;
&lt;p&gt;The problem we were solving is simple to state: every piece of equipment in an engineering assessment report needs a defensible replacement cost. Where did that number come from? How confident are we in it? Could a client or a peer reviewer trace it back to a source? Answering those questions for hundreds of items across dozens of projects is the whole job. The system we built to do it had one sentence at its core: put the correct number into a file safely.&lt;/p&gt;</description></item></channel></rss>