{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/8c560fabd0304f63aacf4543a9856b54\" frameborder=\"0\" width=\"1232\" height=\"924\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":924,"width":1232,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":924,"thumbnail_width":1232,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/8c560fabd0304f63aacf4543a9856b54-f7a7658084c0f87b.gif","duration":137.973,"title":"Agent Memory Palaces to Reduce Hallucinations","description":"This Loom explains an Agent Palace approach to reduce hallucinations by using a memory palace concept for agent information retrieval. Bert says Agent Palace stores company knowledge as markdown files in G-Brain and lets different agents “walk through” to fetch the correct details. He demonstrates with an Acme Robotics example using QM as nufo.ai to generate a new engineering onboarding page by coordinating with engineering and legal for items like an NDA and I-9, tracing results into a memorable log. Runtime improved from 46 seconds with 32 tool calls to 34 seconds with 21 tool calls after repeated runs."}