<?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>Developer Tools on jamesm.blog</title>
    <link>https://jamesm.blog/tags/developer-tools/</link>
    <description>Recent content in Developer Tools on jamesm.blog</description>
    <image>
      <title>jamesm.blog</title>
      <url>https://jamesm.blog/papermod-cover.png</url>
      <link>https://jamesm.blog/papermod-cover.png</link>
    </image>
    <generator>Hugo</generator>
    <language>en</language>
    <lastBuildDate>Mon, 06 Apr 2026 00:05:00 +0100</lastBuildDate>
    <atom:link href="https://jamesm.blog/tags/developer-tools/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>What Actually Belongs in My AI Dev Stack in 2026</title>
      <link>https://jamesm.blog/ai/what-actually-belongs-in-my-ai-dev-stack-2026/</link>
      <pubDate>Mon, 06 Apr 2026 00:05:00 +0100</pubDate>
      <guid>https://jamesm.blog/ai/what-actually-belongs-in-my-ai-dev-stack-2026/</guid>
      <description>&lt;p&gt;There is a big difference between using AI for development and having an actual AI development stack.&lt;/p&gt;
&lt;p&gt;Most developers still seem to be operating with a single-tool mindset. They pick one assistant, one model, one editor, and then expect it to handle everything from planning and architecture to implementation, debugging, review, and documentation.&lt;/p&gt;
&lt;p&gt;That approach breaks down quickly.&lt;/p&gt;
&lt;p&gt;In practice, the best AI workflow in 2026 is not about finding one perfect tool. It is about assembling a small stack where each part has a clear job. Fast models handle cheap iteration. Stronger models handle harder reasoning. Specs keep the whole process coherent. Review loops stop you from shipping nonsense with confidence.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
