<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>OpenSpec on Pocket Dev</title><link>/tags/openspec/</link><description>Recent content in OpenSpec on Pocket Dev</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sun, 03 May 2026 10:00:00 -0400</lastBuildDate><atom:link href="/tags/openspec/index.xml" rel="self" type="application/rss+xml"/><item><title>Stop Winging It: How I Use OpenSpec to Keep AI Changes Structured and Costs Sane</title><link>/posts/openspec-spec-driven-development-ai-agents/</link><pubDate>Sun, 03 May 2026 10:00:00 -0400</pubDate><guid>/posts/openspec-spec-driven-development-ai-agents/</guid><description>&lt;p&gt;I&amp;rsquo;ve been burned enough times by AI-generated code that &amp;ldquo;solved&amp;rdquo; the wrong problem to know that the issue usually isn&amp;rsquo;t the model — it&amp;rsquo;s the absence of any agreement on what we&amp;rsquo;re building before the first file gets touched. The AI goes, I approve changes that look reasonable, and somewhere around the third follow-up session I realize we drifted from the original intent two sessions ago.&lt;/p&gt;</description></item></channel></rss>