{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/c1b7845b1fc142ccbe31800f22d123bf\" frameborder=\"0\" width=\"1110\" height=\"832\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":832,"width":1110,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":832,"thumbnail_width":1110,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/c1b7845b1fc142ccbe31800f22d123bf-cc4d1fed3ff40094.gif","duration":112.396,"title":"Sightline Video Incident Detection Demo","description":"This Loom introduces Sightline, an application that lets users scan index videos for scenario-specific incidents like traffic incidents, worker safety, or drowning. Orlando and Solomon explain that the configured Sightline agent reviews an uploaded video, marks potential incidents, and can validate flagged areas. They demonstrate a test where the team highlights a drowning area the agent initially missed, and then the agent confirms it. Due to time and bandwidth constraints, the agent takes a few minutes to analyze incidents, with the end goal of generating a report to enable user action."}