<?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/61234b77725e4f308230c0bc0a039bdb&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/61234b77725e4f308230c0bc0a039bdb-dd395d5069648823.gif</thumbnail_url><duration>558.612</duration><title>CMDB Integrity Audit with AI Coworker</title><description>This Loom demonstrates an Atomic Work Platform AI coworker for running a CMDB Integrity Check to verify CMDB records against real sources. It sets up guardrails to avoid modifying data and can be scheduled monthly or quarterly or run ad hoc, then generates an HTML report attached to the service request. In a prior run, it audited 890 CIs with a 30 day threshold and found 7 shadow AWS resources and several Go CIs, including stale orphaned items and relationships missing from the CMDB. The report highlights potentially costly resources, such as configurations still running after owner CIs have departed, to show whether the CMDB is more than basic inventory.</description></oembed>