<?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/6c446dc5c32c454b8e015334c8a31721&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/6c446dc5c32c454b8e015334c8a31721-387d1ef47597de4d.gif</thumbnail_url><duration>140.3992</duration><title>Understanding Follow-Up Questions on TaxGPT 📊</title><description>In this video, I explain the importance of follow-up questions on the TaxGPT research platform. I demonstrate how these questions help guide agents to provide detailed responses, ensuring clarity and cross-referencing of concepts. Using the example of the Research and Development Credit, I show how follow-up questions can narrow down information and maintain jurisdictional awareness. No action requested from viewers.</description></oembed>