On November 10, Google Cloud CEO Thomas Kurian announced Gemini for healthcare, available in preview in the U.S. starting today. It extends the universal Gemini agent introduced at Gemini at Work in October to health systems and health plans, and is built from four parts: healthcare skills, system connectors, a partner ecosystem, and one governed platform. It can assemble a patient history across care settings, prepare charts before visits, build prior-authorization packets against payer policy and draft appeals, and help payers check requests against medical policy and explain out-of-pocket costs. Google says the platform is built to support HIPAA compliance and that clinical data is never used to train its foundation models.
Key Takeaways
- ✓Status: U.S. preview, available today, joining the existing solutions for legal, financial services, and government services (official blog)
- ✓Connectors: Google lists 27, spanning EHRs, eligibility and claims, terminology and coding, coverage rules, clinical guidelines, productivity, and security; Epic and Oracle Health EHR access is read-only, with no write-back to the chart
- ✓Pain point: Google says clinicians spend nearly 28 hours a week manually reconciling fragmented information (company figure)
- ✓MCP: InterSystems provides a FHIR MCP Server, and Keragon connects 400+ healthcare apps through a single MCP integration
- ✓Ecosystem: 16 systems integrators, including Accenture, Deloitte, KPMG, PwC, and TCS, help with deployment; model choice lets routine admin steps go to low-cost models
Key Decision Metrics at a Glance
Turn your technical choice into a development budget
Compare 40 dev plans & simulate token costs vs $20/mo subscriptions
Project Links & Resources
Direct AccessIn-Depth Technical Analysis
Core Background and Industry Pain Points
Healthcare is one of the hardest places to deploy AI agents: patient records, coverage policies, and clinical evidence sit in EHR, claims, and admin systems that do not talk to each other. Google Cloud says clinicians spend nearly 28 hours a week manually reconciling this information (company figure). At Gemini at Work on October 8, Google introduced the universal Gemini agent. Gemini for healthcare, announced November 10, is its version for health systems and health plans, available in preview in the U.S. starting today.
Architecture Highlights and Underlying Mechanisms
The solution has four parts. First, skills: reusable multi-step instructions written by domain experts for records synthesis, pre-visit preparation, coverage review, and benefit determination, and organizations can write their own. Second, connectors: Google lists 27, including Epic and Oracle Health (read-only, no write-back to the chart), the InterSystems FHIR MCP Server, Optum eligibility, CMS coverage rules, and ICD-10 and RxNorm lookups. Third, a partner ecosystem. Fourth, one governed platform: every agent has its own identity, inherits the user's existing role-based permissions, keeps full audit logs and verifiable citations, and can route tasks between Google and partner models.
Authoritative Benchmarks and Measured Comparisons
Google published no quantitative evaluation such as accuracy or time saved. It cites statements from HCA Healthcare, Northwell Health, Optum, Blue Cross Blue Shield of Massachusetts, and the American Society of Clinical Oncology (ASCO). For now, the results are vendor claims, and real performance will depend on data from preview customers.
Developer Adoption and Getting Started
For healthcare IT teams, the notable design choice is the heavy use of MCP-style connectors: Keragon links more than 400 healthcare apps through a single MCP integration. A practical path is to start with low-risk use cases such as pre-visit summaries over the read-only EHR connectors, then wire prior-authorization packet assembly into existing review workflows. Google says the platform is built to support HIPAA compliance, but teams still need their own compliance review and agreements such as a BAA before going live. The preview is U.S.-only for now.
Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.