<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Ai-Observability on Kevin Keller</title><link>https://kevinkeller.org/tags/ai-observability/</link><description>Recent content in Ai-Observability on Kevin Keller</description><generator>Hugo -- gohugo.io</generator><language>en</language><managingEditor>kellerkev@gmail.com (Kevin Keller)</managingEditor><webMaster>kellerkev@gmail.com (Kevin Keller)</webMaster><copyright>© 2026 Kevin Keller</copyright><lastBuildDate>Fri, 13 Nov 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://kevinkeller.org/tags/ai-observability/index.xml" rel="self" type="application/rss+xml"/><item><title>Cortex Agents in Microsoft Sentinel: Closing the AI Blind Spot in Your SIEM</title><link>https://kevinkeller.org/posts/cortex-agents-microsoft-sentinel-siem/</link><pubDate>Fri, 13 Nov 2026 00:00:00 +0000</pubDate><author>kellerkev@gmail.com (Kevin Keller)</author><guid>https://kevinkeller.org/posts/cortex-agents-microsoft-sentinel-siem/</guid><description>Microsoft Sentinel&amp;rsquo;s native Snowflake connector shows your SOC logins and queries, but nothing about what Cortex Agents did. Here&amp;rsquo;s a reference implementation that sends agent traces, token usage and access history into Sentinel, so analysts can follow an agent conversation down to the data it touched.</description></item></channel></rss>