<?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>Guardrails on Engineering Playbook</title><link>https://learn.tanhdev.com/tags/guardrails/</link><description>Recent content in Guardrails on Engineering Playbook</description><image><title>Engineering Playbook</title><url>https://learn.tanhdev.com/vesviet.png</url><link>https://learn.tanhdev.com/vesviet.png</link></image><generator>Hugo</generator><language>vi</language><lastBuildDate>Thu, 25 Jun 2026 08:00:00 +0700</lastBuildDate><atom:link href="https://learn.tanhdev.com/tags/guardrails/index.xml" rel="self" type="application/rss+xml"/><item><title>Kiến trúc Human-in-the-loop (HITL): Cơ Chế Kiểm Soát &amp; Can Thiệp Con Người Cho Autonomous AI Swarms</title><link>https://learn.tanhdev.com/series/agentic-system-architecture/part-6-human-in-the-loop/</link><pubDate>Thu, 25 Jun 2026 08:00:00 +0700</pubDate><guid>https://learn.tanhdev.com/series/agentic-system-architecture/part-6-human-in-the-loop/</guid><description>Thiết kế hệ thống Can thiệp Con người (Human-in-the-Loop) giúp kiểm soát rủi ro, phê duyệt giao dịch và đảm bảo an toàn tuyệt đối cho Autonomous AI Swarms.</description></item></channel></rss>