<?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/d4a7810a2a5142f7b46beaa7f382d0a9&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/d4a7810a2a5142f7b46beaa7f382d0a9-0fcfeaf04ef1524f.gif</thumbnail_url><duration>636.005</duration><title>Social-RAG: Retrieving from Group Interactions to Socially Ground AI Generation</title><description>In this video, I introduce Social RAG, a new workflow that improves AI interactions in group settings. I discuss how AI agents can provide relevant recommendations by understanding group context, which is crucial for effective communication. I also share insights from our deployment of PaperPing, a Slack bot that tailors paper recommendations based on group interactions, and the positive feedback we&apos;ve received from over 500 researchers.</description></oembed>