Biomedical researchers have the same AI agents as everyone else, but can't point them at their actual data. Patient records can't leave the medical center, so the agent never sees them. Institutions already host compliant model inference. The gap sits at the agent layer.

This talk covers how we use Biorouter to close that gap at UCSF and connect it to Jupyter. Biorouter is an open-source research agent that routes work across institutionally hosted, local, and commercial models, with the private-public boundary enforced at the source, and MCP connectors to where the data lives: a 7-million-patient OMOP electronic health record database and the SPOKE knowledge graph. With the Jupyter integration, researchers keep their existing notebooks and gain access to institutionally hosted inference and clearance for protected health data.

In this session, we will demo the Jupyter integration and a few examples it has enabled: replicating a published study, building research applications, curating a knowledge graph, and using Biorouter Copilot to work directly in patient- and clinician-facing clinical software.