<?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>Agents on Joor0x - Developer &amp; Algorithmic Trader</title><link>https://joor0x.github.io/tags/agents/</link><description>Recent content in Agents on Joor0x - Developer &amp; Algorithmic Trader</description><generator>Hugo -- 0.125.7</generator><language>en-us</language><lastBuildDate>Sun, 12 Jul 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://joor0x.github.io/tags/agents/index.xml" rel="self" type="application/rss+xml"/><item><title>Human as a Tool: The Agent Pattern Where You Work for the Machine</title><link>https://joor0x.github.io/posts/human-as-a-tool/</link><pubDate>Sun, 12 Jul 2026 00:00:00 +0000</pubDate><guid>https://joor0x.github.io/posts/human-as-a-tool/</guid><description>In the human-as-a-tool pattern, the AI agent orchestrates and calls the human like any other tool — for the shrinking list of tasks only we can do. For now.</description></item><item><title>Metrics for Your AI Workers: Build a Personal Agent Benchmark</title><link>https://joor0x.github.io/posts/build-your-own-agent-benchmark/</link><pubDate>Tue, 30 Jun 2026 00:00:00 +0000</pubDate><guid>https://joor0x.github.io/posts/build-your-own-agent-benchmark/</guid><description>Public leaderboards measure someone else&amp;#39;s tasks. Build a small benchmark around your own work and you get real metrics: promote the agents that deliver, quit the ones that don&amp;#39;t.</description></item></channel></rss>