video1.0<iframe src="https://www.loom.com/embed/4d73055370e4436c86d4dc7262f8ffbe" frameborder="0" width="1662" height="1246" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>12461662Loomhttps://www.loom.com12461662https://cdn.loom.com/sessions/thumbnails/4d73055370e4436c86d4dc7262f8ffbe-0260a38f9d9b08fa.gif129.322666This 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.