<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Enterprise Architecture on No Semicolons</title><link>https://nosemicolons.com/tags/enterprise-architecture/</link><description>Recent content in Enterprise Architecture on No Semicolons</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Mon, 08 Jun 2026 12:22:37 +0000</lastBuildDate><atom:link href="https://nosemicolons.com/tags/enterprise-architecture/index.xml" rel="self" type="application/rss+xml"/><item><title>The AI Code Generation Capability Gap: Why Your Model Can't Handle Enterprise-Level Architecture</title><link>https://nosemicolons.com/posts/ai-code-generation-enterprise-architecture-gap/</link><pubDate>Mon, 08 Jun 2026 12:22:37 +0000</pubDate><guid>https://nosemicolons.com/posts/ai-code-generation-enterprise-architecture-gap/</guid><description>&lt;p>Ever asked ChatGPT to generate a microservices architecture and gotten back what looks more like a monolith wearing a disguise? You&amp;rsquo;re not alone. I&amp;rsquo;ve been experimenting with AI code generation for enterprise projects over the past year, and there&amp;rsquo;s a fascinating gap between what these models can do brilliantly and where they completely miss the mark.&lt;/p>
&lt;p>The truth is, while AI excels at generating clean functions and solving algorithmic problems, it struggles with the big picture stuff that makes enterprise software actually work in production. Let me share what I&amp;rsquo;ve discovered about these limitations and some workarounds that have saved my projects.&lt;/p></description></item></channel></rss>