{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/64041e3dcb3743ac9ab766598363704a\" frameborder=\"0\" width=\"1114\" height=\"835\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":835,"width":1114,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":835,"thumbnail_width":1114,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/64041e3dcb3743ac9ab766598363704a-b5d747b750fb5ecd.gif","duration":70.498,"title":"naki","description":"This Loom explains how shared knowledge and agent memory work to solve the same bug simultaneously across a team. It notes that every team has four people and four agents working on the same task, but agents have vulnerabilities around memory and shared context. When a skill is invoked, Unaki pulls a live workflow context through a hook from the shared knowledge memory. The memory updates through a webhook so when one agent learns something, all agents are immediately informed."}