<?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>Harness on Artem Demchyshyn</title><link>https://demchaav.github.io/blog/tags/harness/</link><description>Recent content in Harness on Artem Demchyshyn</description><image><title>Artem Demchyshyn</title><url>https://demchaav.github.io/blog/images/og-default.png</url><link>https://demchaav.github.io/blog/images/og-default.png</link></image><generator>Hugo</generator><language>en-GB</language><lastBuildDate>Tue, 25 Aug 2026 12:00:00 +0100</lastBuildDate><atom:link href="https://demchaav.github.io/blog/tags/harness/index.xml" rel="self" type="application/rss+xml"/><item><title>Why Harness Is Becoming One of the Key Parts of AI Development</title><link>https://demchaav.github.io/blog/posts/why-harness-matters-in-ai/</link><pubDate>Tue, 25 Aug 2026 12:00:00 +0100</pubDate><guid>https://demchaav.github.io/blog/posts/why-harness-matters-in-ai/</guid><description>Models are already smart enough for a huge amount of real work. What is missing is the software layer around them — the one that defines how a task is executed, verified, corrected and finished. A look at why harness is becoming the interesting part of agentic AI.</description></item></channel></rss>