Artificial intelligence news.
Straight from the original announcements.

OpenAI adds computer-use agents and plugins to ChatGPT for Healthcare

November 16, 2026, 07:00By the AI News Bites Editorial TeamSource: OpenAI

OpenAI is expanding ChatGPT for Healthcare with computer-use agents, improved clinical search and more than 20 healthcare plugins. The company says the updates are designed to help healthcare teams work across existing software while keeping human review and deployment controls in place.

Key points
  • OpenAI is adding computer-use agents for clinical and administrative workflows.
  • The agents can navigate existing healthcare software and support human review.
  • Clinical search updates cover evidence discovery, evaluation and citations.
  • More than 20 healthcare plugins are available today in ChatGPT for Healthcare.
  • OpenAI says healthcare content is not used to train models.

Agents can work across existing healthcare software

OpenAI says its computer-use agents can navigate software that healthcare teams already use by reading screens, clicking, typing and moving between applications. The company describes workflows including preparing documentation, coordinating care and completing administrative tasks across disconnected systems.

The updated capabilities include models OpenAI describes as more capable, safe and affordable for clinical and administrative workflows. The company is also adding access controls and audit logs for secure deployments. Organizations can choose which applications agents can access and define which steps require human review.

In an example shown by OpenAI, a clinician uses Voice in the ChatGPT app to ask an agent to follow up on an MRI request. The agent reviews the chart and drafts an order and a patient reply for the clinician to review.

OpenAI reports stronger clinical search results

OpenAI is also updating trusted clinical search in ChatGPT for Healthcare and ChatGPT for Clinicians. The changes affect how ChatGPT finds, evaluates and cites medical evidence, with the goal of helping clinicians connect evidence to clinical questions and translate it into practical next steps.

According to OpenAI, physicians assessed the updated experience in a blind evaluation covering real-world clinical questions across multiple specialties, including multi-turn conversations. In over 1300 reviews, physicians rated the updated experience more highly across all eight dimensions evaluated, including factual correctness, safety, actionability and source authoritativeness.

More than 20 healthcare plugins are available

OpenAI says more than 20 new healthcare plugins from companies across clinical care, care coordination and business operations are available today in ChatGPT for Healthcare, including through ChartGPT, which brings ChatGPT into the EHR workflow.

The listed plugins include Aiva, Assort Health, Elation Health, Ferry Health, IMO Health, KMED, Luma Health, Notable, Oracle HDI, PenguinAI, Photon, Redox, Stedi, Subsalt, Trizetto, Turquoise and UpToDate Expert AI.

OpenAI gives examples such as reviewing patient records and hospital protocols, preparing prescriptions for clinician review, coordinating patient outreach, checking insurance eligibility and analyzing healthcare costs and operational performance. The examples combine tools in a single ChatGPT conversation, including checking appointments with Luma Health and insurance eligibility with TriZetto, or comparing MRI-related coverage and negotiated rates using IMO Health, Stedi and Turquoise Health.

Controls and data protections remain part of deployment

For workflows involving protected health information and intended to be HIPAA-compliant, OpenAI says organizations must use eligible services covered by their Business Associate Agreement with OpenAI, apply required security and retention settings, and extend protections to connected systems. OpenAI also says content shared with ChatGPT for Healthcare is not used to train models.

The updates are aimed at organizations that want to bring evidence, healthcare tools and actions into one platform, while allowing them to control agent access and require human review for selected steps. OpenAI says healthcare organizations including Abridge, Ambience, Cigna Healthcare and CVS Health are deploying agents for tasks such as processing referrals, moving documents between systems and bringing together information for care teams.

Related news

Snorkel AI says gated training lifts Qwen3.8-27B on professional tasks
ResearchNovember 19, 2026, 15:32

Snorkel AI says gated training lifts Qwen3.8-27B on professional tasks

Snorkel AI says it raised Qwen3.8-27B's pass@1 performance on OpenAI's GDPval gold set from 31.9% to 40.7% by combining expert-built training data with binary-gated…

Snorkel AI boosts Qwen3.8-27B on difficult professional tasks
ResearchNovember 19, 2026, 15:32

Snorkel AI boosts Qwen3.8-27B on difficult professional tasks

Snorkel AI says it raised Qwen3.8-27B's pass@1 score on OpenAI's GDPval benchmark from 31.9% to 40.7% by combining expert-built training data with a modified…

Products and tools
Products and toolsNovember 16, 2026, 07:00

OpenAI reports healthcare results for computer-use agents

OpenAI is sharing new results on computer-use agents for healthcare, including clinical safety, helpfulness and administrative workflow performance. The company is also…