{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/5e733a54748e4f82809014e4f38a7b93\" frameborder=\"0\" width=\"2560\" height=\"1920\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1920,"width":2560,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1920,"thumbnail_width":2560,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/5e733a54748e4f82809014e4f38a7b93-6ee2225f126dae34.gif","duration":88.821354,"title":"Dispatch IQ Replans Emergencies with AI","description":"This Loom explains how Dispatch IQ uses a multi-agent system to re-plan a service company’s day when disruptions occur. It describes a plumbing scenario where a sick technician and an emergency require rearranging crews while customers wait, with AI agents generating re-planning logic that a dispatcher reviews and approves. In each round, six agents propose plans in parallel, a plane-code scoring process evaluates simulated bad days, and a critic agent turns results into lessons, with five of six champions influenced by the critics. In a 50-day locked test, the team improved outcomes versus a baseline by 38 versus 12 for random search, raising on-time jobs from 59% to 74% and reducing mis-emergency promises from 13 to 4."}