<?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/a451244dc4b04c64953590f05a76be3a&quot; frameborder=&quot;0&quot; width=&quot;1920&quot; height=&quot;1440&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1440</height><width>1920</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1440</thumbnail_height><thumbnail_width>1920</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/a451244dc4b04c64953590f05a76be3a-6301a60cbd18d02d.gif</thumbnail_url><duration>165.899067</duration><title>AI Evidence Package for Healthcare Fraud Cases</title><description>I explain how we built the Visual BLR Evidence Packageer to fix fraud investigations that are still stuck in manual, 20th century processes. We use three specialized agents, an extractor that pulls key facts like patient name, invoice, and dates from uploaded PDFs, an audit agent that checks compliance against regulations like the Anti Kickback Statute and the False Claims Act, and a legal writing agent that produces a final report. In a real world test against a high profile health care fraud case, our workflow reduced investigation time from weeks to about 60 seconds with high precision. No action was explicitly requested from viewers.</description></oembed>