<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Data Boundaries on Fondsites</title><link>https://fondsites.com/tags/data-boundaries/</link><description>Recent content in Data Boundaries on Fondsites</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Fri, 15 May 2026 18:32:29 +0300</lastBuildDate><atom:link href="https://fondsites.com/tags/data-boundaries/feed.xml" rel="self" type="application/rss+xml"/><item><title>AI Agent Data Boundaries: Minimization, Redaction, and Retention</title><link>https://fondsites.com/ai-agents/guidebooks/agent-data-boundaries-redaction/</link><pubDate>Fri, 15 May 2026 00:00:00 +0000</pubDate><guid>https://fondsites.com/ai-agents/guidebooks/agent-data-boundaries-redaction/</guid><description>&lt;p&gt;AI agents work by seeing enough of a task to act on it. That useful fact creates an uncomfortable habit: people keep giving the agent more context because more context feels safer. A support ticket gets the whole account history. A research assignment gets the entire document archive. A coding task gets logs, chat excerpts, customer examples, and production traces. The agent may perform better, but the workflow has quietly copied material into places where it may not belong.&lt;/p&gt;</description></item></channel></rss>