Products & Tools

OpenAI adds over 20 healthcare plugins and upgrades clinical search

OpenAI Adds Over 20 Healthcare Plugins and Upgrades Clinical Search
OpenAI Adds Over 20 Healthcare Plugins and Upgrades Clinical SearchAI-generated
By Rebecca Stone3 min read

By Rebecca Stone

On November 16, 2026, OpenAI added more than 20 healthcare plugins for ChatGPT for Healthcare, after more than 1,300 physician reviews rated its revised clinical search above the prior system on all eight measured dimensions.

OpenAI's update spans ChatGPT for Healthcare and ChatGPT for Clinicians. It pulls medical evidence, patient information and operational tools into one governed conversation, rather than leaving users to move among an EHR, hospital policies, scheduling software and payer portals.

OpenAI's release matters to hospitals and payers because it combines the clinical record with billing, scheduling and operational tasks in one place. OpenAI says deployment still depends on operational governance: every connected system needs defined access, review requirements and data protections.

OpenAI frames the release as an operating layer around the clinician. Its documented workflows move from records to evidence, then into policy, specialist coverage or payment data. Clinical decisions and the administrative steps around them sit in the same sequence.

What changed in ChatGPT for Healthcare?

OpenAI says more than 20 new plugins span clinical care, care coordination and business operations. Supported tasks include reviewing records, preparing prescriptions for clinician review, checking insurance eligibility, and analyzing costs and operational performance.

The revised clinical search changes how ChatGPT finds, evaluates and cites medical evidence in both products. OpenAI describes the answers this way: “The answers are designed to connect relevant evidence to clinical questions and practical next steps, with citations clinicians can inspect.”

The clinical-search revision is separate from the connector catalog. OpenAI says the change also reaches individual clinicians, for whom improved search and select plugins are available. In team deployments, citations sit alongside tools for records, evidence, scheduling, benefits and operations.

OpenAI presents the plugins as a way to carry evidence into practical next steps. Prescription preparation remains subject to clinician review.

How do the healthcare plugins work together?

OpenAI's examples show connectors operating as a chain. Each example assigns a narrow task to a named service, then passes the result into the next part of a clinical or administrative workflow.

  • Heart failure follow-up: A primary care physician can retrieve an outside hospital's discharge summary through Metriport after the patient is hospitalized elsewhere. ChatGPT identifies medication changes, then draws on UpToDate Expert AI for recommended follow-up monitoring. OpenAI says the workflow links both sources.
  • Insulin pump admission: Aiva supplies hospital-policy information, including required nursing checks and documentation, for an inpatient nurse admitting a patient who uses an insulin pump. Amion's on-call directory identifies the covering endocrinologist so the nurse can contact that clinician.
  • Knee MRI cost: IMO Health identifies the procedure code for a knee MRI without contrast. Stedi checks insurance eligibility and benefits. Turquoise Health supplies the plan's negotiated rate for the code at two hospitals. The workflow also identifies additional information needed to estimate what the patient would owe.
  • Pre-visit and referrals: Luma Health and TriZetto can build a pre-visit confirmation list. Assort Health and Ferry Health can combine referral trends with outstanding scheduling work.

Each chain divides a case into specialized checks. Records establish what happened, policy establishes required actions, staffing establishes who can respond, and coding, eligibility and rate data establish expected cost. OpenAI describes this as one connected workflow, with each service occupying a defined role.

These examples also span the three categories OpenAI assigned to the release. A discharge summary supports clinical care, a covering endocrinologist supports care coordination, and a benefits check supports business operations. The workflows can combine those categories while leaving each connector responsible for its own source data.

What can the computer-use agents do?

OpenAI also announced computer-use capabilities for healthcare teams. Its agents read screens, click, type and move between existing applications to help with referrals, prior authorizations, discharge planning and outreach.

OpenAI described work with Abridge, Ambience, Cigna Healthcare and CVS Health. Organizations can configure application access and approvals and record audit logs, giving them control over what an agent can reach and which steps require authorization.

The computer-use announcement is distinct from the plugin release. OpenAI's description places both under organization configuration

Source: unite.ai

Share this article:

More from Rebecca Stone

Rebecca Stone

Show full bio

Correspondent covering companies, deals and strategy in artificial intelligence and machine learning at AI In Context.

728 articles

Related articles

  1. OpenAI Makes ChatGPT for Clinicians Free for Verified US Providers
  2. OpenAI Connects Epic EHR Data and Public Health Sources to ChatGPT
  3. OpenAI Launches ChatGPT Health, a Dedicated Health Data Experience
  4. OpenAI Says GPT-5.5 Instant Now Rival Doctors on Health Questions
  5. OpenAI Launches Health in ChatGPT With Medical Record Connections

« Previous articleNext article »