<?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/2257457de3d64cbe92839f65f7a5fb4f&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/2257457de3d64cbe92839f65f7a5fb4f-00bbcb3c13d78144.gif</thumbnail_url><duration>173.077</duration><title>Using AI to Summarize and Extract Actions</title><description>This Loom demonstrates how to use the Unicron track document workflow to upload and analyze PDFs with AI. After signing into the account and opening the interface, viewers can upload a research paper, use checkbox options, and ask exact questions to extract content from the PDF. The video shows verifying that answers are generated from the document by checking the related resources expansion and proof based on the AI generated text. It also explains using summary and action summaries to generate one paragraph and related action items from the PDF, powered by Gamma 4 and the Google Gemini API.</description></oembed>