<?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/25a0e92e46d54ef4b84ffe9101b8305b&quot; frameborder=&quot;0&quot; width=&quot;2580&quot; height=&quot;1935&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1935</height><width>2580</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1935</thumbnail_height><thumbnail_width>2580</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/25a0e92e46d54ef4b84ffe9101b8305b-43974db0fe25132b.gif</thumbnail_url><duration>224.754</duration><title>Demonstrating Cyrus: Real-Time Incident Detection with Natural Language Processing</title><description>In this video, Jeremy and I demonstrate how our Cyrus product works by defining incidents in natural language and receiving real-time notifications. We set up a camera in our living room and activated several incidents, such as someone opening a drawer and taking a laptop. The system successfully detected these actions and provided immediate notifications, showcasing its effectiveness without the need for training new models. We encourage you to explore how easily you can define incidents and leverage our technology for enhanced monitoring. Please let us know if you have any questions or feedback!</description></oembed>