<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Coding-Agents on Advancing Engineering</title><link>https://www.advancingengineering.dev/tags/coding-agents/</link><description>Recent content in Coding-Agents on Advancing Engineering</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sat, 08 Aug 2026 22:22:43 +0100</lastBuildDate><atom:link href="https://www.advancingengineering.dev/tags/coding-agents/index.xml" rel="self" type="application/rss+xml"/><item><title>The Context Store</title><link>https://www.advancingengineering.dev/posts/2026-08-contextstore/</link><pubDate>Fri, 07 Aug 2026 16:01:13 +0100</pubDate><guid>https://www.advancingengineering.dev/posts/2026-08-contextstore/</guid><description>&lt;p&gt;You know the loop. You ask an agent to add authentication. It adds authentication. You ask for structured logging, then for tests, then for a CI step to run those tests, then a health check endpoint because the deploy needs one. Six prompts later you have a working feature, and you&amp;rsquo;ve spent the whole session doing what a template used to do in fifteen minutes: filling in the blanks one at a time, just prompted instead of coded.&lt;/p&gt;
&lt;p&gt;That&amp;rsquo;s not automation. That&amp;rsquo;s scaffolding through a chat window.&lt;/p&gt;</description></item></channel></rss>