<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Production AI on Bruce on AI Engineering</title><link>http://www.heyuan110.com/tags/production-ai/</link><description>Recent content in Production AI on Bruce on AI Engineering</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sat, 18 Apr 2026 16:00:00 +0800</lastBuildDate><atom:link href="http://www.heyuan110.com/tags/production-ai/index.xml" rel="self" type="application/rss+xml"/><item><title>Harness Engineering: Build the 6 Layers Backwards (6→1, Not 1→6)</title><link>http://www.heyuan110.com/posts/ai/2026-04-18-harness-six-layers-reverse-build/</link><pubDate>Sat, 18 Apr 2026 16:00:00 +0800</pubDate><guid>http://www.heyuan110.com/posts/ai/2026-04-18-harness-six-layers-reverse-build/</guid><description>&lt;p&gt;&lt;img src="http://www.heyuan110.com/posts/ai/2026-04-18-harness-six-layers-reverse-build/cover.webp"
 alt="Harness Engineering 6 layers reverse build strategy"
 
 loading="lazy"
 decoding="async"
 fetchpriority="low"
 width="1200"
 height="630"
/&gt;
&lt;/p&gt;
&lt;p&gt;The 6 layers of Harness Engineering are not equal.&lt;/p&gt;
&lt;p&gt;That sentence breaks the standard advice. Every talk, every framework diagram, every &amp;ldquo;what is Harness Engineering&amp;rdquo; explainer puts the 6 layers in a tidy stack and tells you to build them in order: Context → Tools → Execution → Memory → Evaluation → Recovery. Sensible, easy to teach, completely wrong if you actually want a stable agent in production.&lt;/p&gt;</description></item></channel></rss>