<?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/8782a3255552449d97d21a5d765df345&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/8782a3255552449d97d21a5d765df345-06984f577c36b288.gif</thumbnail_url><duration>90.523222</duration><title>2026-09-19 Cursor AITX Hackathon - Caret</title><description>This Loom introduces a simple translation workflow and shows how it integrates with Verse i on a skills-based AI system. The demo highlights selecting text and pressing translate, noting it works with Verse i’s API and is built using Cursor. It explains that the system stores reusable skills such as summarizing, translating, revising, and proofreading, and can add custom skills that call other apps, including stitching together a Chrome app to book flights. The conversation also mentions Cursor tab autocomplete and the idea of autocomplete that understands the user and helps with computer actions.</description></oembed>