{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/ce79913d41644162b5d179f9c31b43c7\" frameborder=\"0\" width=\"1920\" height=\"1440\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1440,"width":1920,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1440,"thumbnail_width":1920,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/ce79913d41644162b5d179f9c31b43c7-bcf8170571e204e8.gif","duration":235.856,"title":"SlydeIn","description":"This Loom explains SlideIn, a sign in layer for human backed AI agents, and how it answers the accountability question of agent actions. It demonstrates admitting a verified research delegate into a shared workspace, where the agent can read public policy and create tasks but cannot email, make payments, or access customer data. SlideIn makes the agent’s purpose, permissions, request, and workspace receipt visible, including principals and defined expiry boundaries. The speaker then prompts the agent to prepare a task within scope, authorizes the admission, and shows the workspace updating with the permitted action."}