{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/46959ff3a5fa4874851b457f753973d2\" 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/46959ff3a5fa4874851b457f753973d2-1e67c9c685c13b7f.gif","duration":166.656,"title":"Serro Program Memory for AI Agents","description":"This Loom explains how Serro supports the idea of companies owning their own memory and data. It describes how, after integrating data sources, Sero detects ongoing initiatives, related sources, and reporting, then promotes them to programs. The AI TPM feature streams live activities into an activity timeline, retaining alignments, scope, work streams, owners, and milestones, while proposing changes for publishing or approval. It also highlights program memory access from AI coding tools like Codex and CloudCode and the ability to set up prompt-based widgets and recurring reports for up-to-date views."}