<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Ai on helder esteves</title><link>https://helderesteves.com/tags/ai/</link><description>Recent content in Ai on helder esteves</description><generator>Hugo</generator><language>en-us</language><copyright>© Helder Esteves</copyright><lastBuildDate>Mon, 06 Jul 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://helderesteves.com/tags/ai/index.xml" rel="self" type="application/rss+xml"/><item><title>AI Coding Agents Don't Fix Bad Architecture. They Amplify It.</title><link>https://helderesteves.com/posts/ai-agents-expose-your-architecture/</link><pubDate>Mon, 06 Jul 2026 00:00:00 +0000</pubDate><guid>https://helderesteves.com/posts/ai-agents-expose-your-architecture/</guid><description>&lt;p>Every team using AI coding agents right now is running the same natural experiment, whether they realize it or not. Same models, same prompts, wildly different results. Some teams ship agent-generated PRs that need a light review and go straight to merge. Others spend more time untangling what the agent broke than they would have spent writing the code by hand.&lt;/p>
&lt;p>The instinct is to blame the model, or the prompt, or the developer&amp;rsquo;s skill at &amp;ldquo;AI-assisted workflows.&amp;rdquo; I think that&amp;rsquo;s mostly wrong. What actually separates those teams is architecture, and the agents are just the fastest, most unforgiving auditor your codebase has ever had.&lt;/p></description></item></channel></rss>