OpenAI announced three updates to ChatGPT for Healthcare: computer-use agents that click, type and move across existing software such as EHRs and payer portals to finish multi-step work, improved trusted clinical search, and more than 20 new healthcare plugins. In OpenAI evaluations GPT-6 Astra earned 94.3% of rubric points on Stanford's HealthAdminBench and GPT-6 Luna 91.8% at 98% lower cost. CVS Health, Cigna, Abridge and Ambience are piloting or running it, and the capabilities are available today through the OpenAI API, ChatGPT for Healthcare and ChatGPT for Clinicians.

Key Takeaways

  • ✓Computer-use agents read screens, click and type to move information between EHRs, scheduling systems and payer portals, handling prior authorizations, referrals and discharge planning steps that APIs do not reach
  • ✓On EHR inbox tasks, 99% of 325 reviewed tasks were rated clinically safe, and physicians chose very or extremely helpful in 93% of 646 assessments
  • ✓On Stanford's independent HealthAdminBench, GPT-6 Astra earned 94.3% of rubric points and GPT-6 Luna 91.8% while costing 98% less at 8.5 cents per task (both at maximum reasoning effort, OpenAI-run evaluation)
  • ✓CVS Health cleared a months-long document-sending backlog over a weekend and is open sourcing an Agent Kit built on the Agents SDK; Cigna went from concept to deployment in under eight weeks
  • ✓More than 20 new healthcare plugins include UpToDate Expert AI, Metriport, Photon, Redox and Stedi; role-based access, audit logs and human approval steps are supported, HIPAA use requires a BAA, and data is not used for training
OpenAI Upgrades ChatGPT for Healthcare: Computer-Use Agents for EHRs and Payer Portals, 20+ New Healthcare Plugins, GPT-6 Luna at 8.5 Cents per Task
🖼️Official Media
Click to view high-res
🧭

Turn your technical choice into a development budget

Compare 40 dev plans & simulate token costs vs $20/mo subscriptions

🔬

In-Depth Technical Analysis

Background

Healthcare is fragmented: after a clinician orders an MRI, the details an insurer needs are already in the chart, yet someone still has to copy them into a separate portal to request prior authorization. OpenAI announced on X and its blog an upgrade to ChatGPT for Healthcare built around computer-use agents that operate the software teams already use.

How it works

Agents read screens, click, type and move between EHRs, scheduling systems and payer portals to finish multi-step workflows that APIs do not fully cover. Organizations choose which applications agents can reach and which steps need human review, backed by role-based access controls and audit logs. OpenAI also improved trusted clinical search, which finds, evaluates and cites medical evidence, and added more than 20 healthcare plugins, also usable inside the EHR through ChartGPT.

Numbers that matter

In OpenAI's own evaluation of EHR inbox work, 99% of 325 reviewed tasks were rated clinically safe and physicians rated responses very or extremely helpful in 93% of 646 assessments. On HealthAdminBench, an independent benchmark from Stanford researchers, GPT-6 Astra earned 94.3% of rubric points and GPT-6 Luna 91.8% while costing 98% less at 8.5 cents per task, both at maximum reasoning effort. In a blind review of clinical search with over 1,300 physician ratings, the updated experience scored higher on all eight dimensions.

What it means for developers

The capabilities are available today through the OpenAI API, ChatGPT for Healthcare and ChatGPT for Clinicians; U.S. clinicians can sign up for a free Clinicians account and developers can follow OpenAI's computer use guide. CVS Health is open sourcing an Agent Kit built on the Agents SDK as a reference. Workflows with protected health information must use BAA-covered services with the required security and retention settings.

Action HubReady to adopt this in production?

Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.

Up NextX Debate: AI Commentator Chubby Says Claude Code and Opus 5.5 Have Been His Daily Driver for Two Months and GPT Is "Not Close," but Concedes Computer Use Is Still GPT's Edge; 150+ Replies Focus on Splitting Work by Task and the Same-Day Claude Login Outage
Read Now→