{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/b1654933117244e38d21467fda51085c\" frameborder=\"0\" width=\"1108\" height=\"831\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":831,"width":1108,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":831,"thumbnail_width":1108,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/b1654933117244e38d21467fda51085c-d2cdd09b9127e97a.gif","duration":407.354,"title":"Automated research pt2: from project to delivery","description":"This Loom explains how the author uses an automated research and build pipeline to turn competitive research into staged in-app sharing features. They run a periodic “Best Practices” research agent that breaks work into pre-alpha and post-alpha projects, then share the resulting project with a build agent that executes a full sequence from briefing and reviewing through implementation and staging. The author notes this specific run took about six hours and added sharing options to Insights, including a public link that can be made private or public. They also point out a current UI issue where an invited user shows as pending incorrectly, and they show the design produced by the UX Translate agent and the related QA checks."}