{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/ac459d6f5e3b49738d7a8864a7aec1a8\" 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/ac459d6f5e3b49738d7a8864a7aec1a8-af46f4521fabb1e6.gif","duration":322.214,"title":"Coordinating Multi-Agent Research with Superhuman Go","description":"This Loom demonstrates how Superhuman Go and Cohando can coordinate multiple agents to research grant opportunities from an incoming email. The presenter highlights a mock non profit request about grants and sends a question to the Superhuman Go agent, which creates an approval step and then a Cohando task assigned to an Instinct agent. The Instinct agent assesses sources such as community grants, a City of Kitchener grant, an Ontario provincial grant, and OTF, including amount windows, screening outcomes, recommended priorities, and assumptions. After the task is marked done and reviewed, the presenter shows running a follow up task to look for federal grants for children learning AI."}