{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/1b322e52d1b54dc0925e6759c4067c3b\" frameborder=\"0\" width=\"1440\" height=\"1080\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1080,"width":1440,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1080,"thumbnail_width":1440,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/1b322e52d1b54dc0925e6759c4067c3b-be07b6ddd9a66ce8.gif","duration":214.144,"title":"Team Oasis Uses AI to Support Local Journalists","description":"This Loom from Team Oasis explains a platform that uses AI agent swarms to support local journalists by collecting information from public city government data sources. It addresses the issue of local news losing funding and shutting down, by generating daily story beats and report drafts based on Houston databases and reporter criteria like zip code or neighborhood. The CTO describes an architecture that sources data from Houston public databases, stores it in shared memory on Supabase, validates it with reporter agents, and then formats it via editor and publisher agents, published through Cloudflare. A demo shows users logging in to review AI-generated items with summaries, source data for fact checking, and options to download or connect an API for publishing."}