{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/6028d1ffaece4d0a830918972c1f7e59\" frameborder=\"0\" width=\"1662\" height=\"1246\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1246,"width":1662,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1246,"thumbnail_width":1662,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/6028d1ffaece4d0a830918972c1f7e59-9d9a845be1bc8e97.gif","duration":141.739,"title":"GTeam Demo","description":"This Loom explains Gteam, a team version of Gbrain that builds a company knowledge base from multiple agents. It uses Zero Entropy to parse individual Gbrain users, filter relevant data, and send a more comprehensive set of relevant pages to a central Gbrain, running five versions to increase coverage. The demo shows filtering 23 Markdown files so only research-related documents are shared, excluding irrelevant items like teletrip planning. It also illustrates chatting with the knowledge base to answer questions such as what active projects the company is working on, noting onboarding to a research lab previously took three weeks."}