<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>SentryML</title><description>Engineering-focused coverage of ML observability and MLOps. Model monitoring, drift detection, training/serving skew, debugging production model failures, evaluation pipelines, and the tooling that actually works at scale.</description><link>https://sentryml.com/</link><language>en</language><item><title>The Authority Gap Is an Observability Problem: What MLOps Teams Should Borrow</title><link>https://sentryml.com/posts/bridging-the-ai-agent-authority-gap-continuous-observability/</link><guid isPermaLink="true">https://sentryml.com/posts/bridging-the-ai-agent-authority-gap-continuous-observability/</guid><description>A new framing of AI agent risk argues that delegation, not identity, is the missing telemetry. ML platform teams already have the substrate to fix it.</description><pubDate>Sun, 03 May 2026 00:00:00 GMT</pubDate><category>agents</category><category>observability</category><category>mlops</category><category>telemetry</category><category>governance</category><author>SentryML Editorial</author></item><item><title>What this site is for</title><link>https://sentryml.com/posts/welcome/</link><guid isPermaLink="true">https://sentryml.com/posts/welcome/</guid><description>SentryML covers ML observability and MLOps from a production-engineering perspective. Here&apos;s what we publish.</description><pubDate>Sat, 02 May 2026 00:00:00 GMT</pubDate><category>meta</category><author>SentryML Editorial</author></item></channel></rss>