<?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/4566650d72784c799e7f7ec002af1124&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/4566650d72784c799e7f7ec002af1124-20713e4eabd135be.gif</thumbnail_url><duration>104.619</duration><title>AI Returns Disposition Agent for Resale Decisions</title><description>This Loom demos a Returns Disposition Agent that helps process thousands of returns using vision and reasoning to decide recovery outcomes. The agent receives item images and handwritten notes, assigns a condition score, and uses tool calls to assess condition, compute resale and recovery economics, and check warehouse capacity before selecting a path such as resale, refurbish, or liquidation. It runs through a queue of five items and produces recommendations for human review, including whether to recover amounts like $700 versus $120 from the same SOFA.</description></oembed>