<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Automation on My Home</title><link>http://mayf3.github.io/tags/automation/</link><description>Recent content in Automation on My Home</description><generator>Hugo -- gohugo.io</generator><language>zh-cn</language><lastBuildDate>Sat, 23 May 2026 10:00:00 +0800</lastBuildDate><atom:link href="http://mayf3.github.io/tags/automation/index.xml" rel="self" type="application/rss+xml"/><item><title>How My AI Agent Content Pipeline Writes Articles for Me</title><link>http://mayf3.github.io/post/2026-05-23-ai-agent-content-pipeline-en/</link><pubDate>Sat, 23 May 2026 10:00:00 +0800</pubDate><guid>http://mayf3.github.io/post/2026-05-23-ai-agent-content-pipeline-en/</guid><description>I Only Do Two Things Now Record thoughts. Review drafts. And finally click publish.
Recording thoughts means speaking into my phone. Reviewing means reading finished articles in Feishu documents and leaving comments paragraph by paragraph. Clicking publish is the very last step. Everything else — topic selection, writing, multi-round review, distribution — is handled by a team of AI agents.
I call this system the &amp;ldquo;Content Collaboration Pipeline.&amp;rdquo; It&amp;rsquo;s not fully automatic.</description></item></channel></rss>