{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/4d73055370e4436c86d4dc7262f8ffbe\" frameborder=\"0\" width=\"1662\" height=\"1246\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1246,"width":1662,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1246,"thumbnail_width":1662,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/4d73055370e4436c86d4dc7262f8ffbe-0260a38f9d9b08fa.gif","duration":129.322666,"title":"Velo Multi Agent Trip Planner Demo","description":"This Loom describes Velo, a multi agent system that plans trips based on a user’s prompt, interests, and budget. In the demo, the user is in Montreal for four days and wants historical places, Persian food, cafes, walking, and bookstores with a budget of $1.50 per day, then clicks “plan my day” to generate and edit the plan. The sequential agents update a landing page that lets users choose spending tradeoffs such as walking, transit, or taxi with a map that refreshes based on transit choice. The interface also supports reordering the plan and exploring stay options like hotels or Airbnbs."}