<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/b57a03163087455b895e1e773757dc01&quot; frameborder=&quot;0&quot; width=&quot;1440&quot; height=&quot;1080&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1080</height><width>1440</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1080</thumbnail_height><thumbnail_width>1440</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/b57a03163087455b895e1e773757dc01-b49d841abbacfaa6.gif</thumbnail_url><duration>136.541</duration><title>Protecting Confidentiality During Investment Onboarding</title><description>This Loom demonstrates a two-brain AI setup for onboarding in investment banking while preserving confidential privacy. The system uses a shared project brain with organization-wide knowledge and a personal employee brain that auto-syncs role relevant context to each person’s MCP connected tools. It shows an example with Sophia at Y Investment Bank, where her private notes on Project Velocity labeled internal only are not shared to a new employee. The Loom opens an onboarding window for “Edward” and confirms that only recently synced project brain information is available, not Sophia’s confidential data.</description></oembed>