<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Governance on A Field CTO Perspective</title><link>https://gaberger.github.io/tags/governance/</link><description>Recent content in Governance on A Field CTO Perspective</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Tue, 13 Oct 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://gaberger.github.io/tags/governance/index.xml" rel="self" type="application/rss+xml"/><item><title>Inside the AI Harness: The Substrate Around the Chat</title><link>https://gaberger.github.io/2026/10/inside-the-ai-harness/</link><pubDate>Tue, 13 Oct 2026 00:00:00 +0000</pubDate><guid>https://gaberger.github.io/2026/10/inside-the-ai-harness/</guid><description>&lt;p>&lt;em>Written by a practitioner who has spent three years building AI apps, harnesses and code development tools. See&lt;/em> About the author &lt;em>at the end.&lt;/em>&lt;/p>
&lt;h2 id="why-the-harness-matters">Why the harness matters&lt;/h2>
&lt;p>In 2026, what an AI agent can actually do depends less on the model and more on the software wrapped around it. That wrapper is the harness.&lt;/p>
&lt;p>A language model on its own is a function: text in, text out. It cannot read a file, run a test, remember yesterday, or check its own work. Everything that lets it do those things lives outside the weights.&lt;/p></description></item></channel></rss>