<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/db833c83807a442ab0e948b062f2fa89&quot; frameborder=&quot;0&quot; width=&quot;1280&quot; height=&quot;960&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>960</height><width>1280</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>960</thumbnail_height><thumbnail_width>1280</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/db833c83807a442ab0e948b062f2fa89-89d01821d4cca485.gif</thumbnail_url><duration>245.311733</duration><title>Surfit Demo #2: Agent Intelligence &amp;amp; Threat Detection</title><description>In this demo, I showcased how Surfeit enables intelligent agent workflows, which we call Ripples, to enhance threat detection and system interactions. We have two active workflows that trigger actions across platforms like GitHub and AWS, with a TrustScore of 70 based on approval rates and action volume. I highlighted our threat detection rules, including a critical multi-system burst detection that escalates to human review if necessary. Additionally, I walked through an incident involving the Ops agent that raised flags for potential misuse. I encourage you to review the dashboard for any pending approvals and familiarize yourself with the metrics we track to ensure our agents operate safely.</description></oembed>