<?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/50448e2e178b489dac7949a56c9a4fdd&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/50448e2e178b489dac7949a56c9a4fdd-df7e04a9474e0cf2.gif</thumbnail_url><duration>488.274</duration><title>AI On Call Buddy for Incident Debugging</title><description>This Loom explains how Atomic Work supports on-call and operations management, and demonstrates using an AI on-call coworker to handle incident triage and debugging. It covers linking infrastructure and services to owner and escalation contacts, runbooks, criticality, and an on-call shift roster with roles like primary and secondary. The speaker simulates creating an incident, assigns it to an on-call buddy, and shows the coworker performing tool calling to investigate systems, analyzing logs, identifying blast radius and hypotheses, and triggering a Teams war room named by the incident ID. The Loom emphasizes reducing MTTR and improving SLAs through faster root-cause investigation, and mentions the ability to create multiple custom coworkers like on-call analyzer and incident responder.</description></oembed>