<?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/97e320bc0f024e55a1de36d0ee624992&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/97e320bc0f024e55a1de36d0ee624992-bf9a4885b4b5c54e.gif</thumbnail_url><duration>167.799</duration><title>Contextual Action Engine for Restaurant Booking</title><description>This Loom demonstrates a contextual action engine in ChatGPT for booking a restaurant. It shows the engine using past preferences, including the Westford location and vegetarian requirements, to recommend options with vegetarian selections. The presenter selects a restaurant and adjusts the party size, mentioning a part size of 1 and then showing options for Friday at Tender Greens. The booking can be completed directly from within the system using the user’s prior history.</description></oembed>