<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Agent on Mi&amp;Bee Blog</title><link>/en/tags/agent/</link><description>Recent content in Agent on Mi&amp;Bee Blog</description><generator>Hugo -- gohugo.io</generator><language>en</language><managingEditor>蓝宝石的傻话</managingEditor><lastBuildDate>Wed, 10 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="/en/tags/agent/rss.xml" rel="self" type="application/rss+xml"/><item><title>Harness Engineering: Putting Reins and Brakes on AI</title><link>/en/posts/aihelper/harness-engineering-guide/</link><pubDate>Sun, 15 Feb 2026 00:00:00 +0000</pubDate><guid>/en/posts/aihelper/harness-engineering-guide/</guid><description>&lt;h2 id="what-is-harness-engineering"&gt;What is Harness Engineering?&lt;/h2&gt;
&lt;p&gt;Definition: &lt;strong&gt;Harness Engineering is the discipline of designing constraints, feedback loops, tool systems, and verification mechanisms around AI agents.&lt;/strong&gt;&lt;/p&gt;
&lt;p&gt;This definition sounds very academic, so let&amp;rsquo;s understand it through a vivid metaphor:&lt;/p&gt;
&lt;blockquote&gt;
&lt;p&gt;&lt;strong&gt;Harnessing a Thousand-Mile Horse&lt;/strong&gt;: A thousand-mile horse (AI Agent) has powerful running capabilities, but without a rider, it might run randomly, injure passersby, or even rush off a cliff. Harness Engineering equips this horse with reins (constraints), brakes (safety controls), whip (incentive mechanisms), and a rider (monitoring), ensuring it travels safely on the correct path.&lt;/p&gt;</description></item><item><title>Loop Engineering: Designing AI's Self-Driving Systems</title><link>/en/posts/aihelper/loop-engineering-guide/</link><pubDate>Wed, 10 Jun 2026 00:00:00 +0000</pubDate><guid>/en/posts/aihelper/loop-engineering-guide/</guid><description>&lt;h2 id="what-is-loop-engineering"&gt;What Is Loop Engineering?&lt;/h2&gt;
&lt;p&gt;&lt;strong&gt;Definition&lt;/strong&gt; (Addy Osmani, June 2026): Loop engineering is replacing yourself as the person who prompts the agent. You design the system that does it instead. The loop is a recursive goal where you define a purpose and the AI iterates until complete.&lt;/p&gt;
&lt;p&gt;Simply put: Loop Engineering = letting the system start its own workflows.&lt;/p&gt;
&lt;p&gt;&lt;strong&gt;Example&lt;/strong&gt;:&lt;/p&gt;
&lt;ul&gt;
&lt;li&gt;Traditional way: You discover bug → You say &amp;ldquo;fix this bug&amp;rdquo; → AI fixes it&lt;/li&gt;
&lt;li&gt;Loop Engineering: System automatically discovers bug → System says &amp;ldquo;fix this bug&amp;rdquo; → AI fixes it&lt;/li&gt;
&lt;/ul&gt;
&lt;h2 id="origins"&gt;Origins&lt;/h2&gt;
&lt;p&gt;The evolution of this concept:&lt;/p&gt;</description></item></channel></rss>