<?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>Calibrated Autonomy on Haxlys's Blog</title><link>https://hugo-blog-static-site.haxlys.workers.dev/frameworks/calibrated-autonomy/</link><description>Recent content in Calibrated Autonomy on Haxlys's Blog</description><generator>Hugo -- 0.152.2</generator><language>kr-ko</language><lastBuildDate>Tue, 07 Jul 2026 19:12:31 +0900</lastBuildDate><atom:link href="https://hugo-blog-static-site.haxlys.workers.dev/frameworks/calibrated-autonomy/index.xml" rel="self" type="application/rss+xml"/><item><title>Addy Osmani의 Agentic Autonomy Levels — AI 에이전트에게 어디까지 맡길 것인가</title><link>https://hugo-blog-static-site.haxlys.workers.dev/posts/agentic-autonomy-levels-addy-osmani/</link><pubDate>Tue, 07 Jul 2026 19:12:31 +0900</pubDate><guid>https://hugo-blog-static-site.haxlys.workers.dev/posts/agentic-autonomy-levels-addy-osmani/</guid><description>Addy Osmani의 Agentic Autonomy Levels는 AI 에이전트 활용을 0~5단계로 나누고, 더 높은 자율성보다 더 강한 검증·되돌리기·범위 통제가 먼저 필요하다고 말한다.</description></item></channel></rss>