<?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/ee02ff601c334b5a9823ee5c5adffcf8&quot; frameborder=&quot;0&quot; width=&quot;1670&quot; height=&quot;1252&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1252</height><width>1670</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1252</thumbnail_height><thumbnail_width>1670</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/ee02ff601c334b5a9823ee5c5adffcf8-81e0a9348dfd401a.gif</thumbnail_url><duration>134.204</duration><title>Auditing Medical Bills With Private AI</title><description>In this Loom, I explain how medical bill audits work because about 80% of bills contain errors and patients often do not know how to fight back. I show a system that uses a local MedGemma model to detect billing issues in under a minute, then redacts patient identifiers before any cloud call. Only the redacted text is sent to cloud Opus 4.7, and the results can flag disputable charges like duplicates and out of network violations. I can show you a demo, and the end of the recording includes a sample disputed letter.</description></oembed>