Introducing Amazon Connect Health: Agentic AI for healthcare, built for the people who deliver it

Today, we’re announcing Amazon Connect Health, a purpose-built agentic AI solution that handles high-volume administrative tasks such as appointment scheduling, clinical documentation, and medical coding, keeping providers informed and in control while delivering proven results across the care continuum.

Healthcare depends on human connection, yet repetitive administrative work pulls professionals away from patient care. Healthcare provider organizations handle millions of patient calls annually, with staff spending up to 80% of call handle time compiling data across disparate systems for routine tasks like appointment scheduling. Meanwhile, millions of clinicians and administrative staff face continual documentation and administrative burden that keeps them from focusing on care delivery. Ultimately, this impacts patients, with 89% citing ‘ease of navigation’ challenges as their primary reason for switching providers.

At AWS, we’ve spent years working alongside healthcare organizations to modernize data infrastructure and improve clinical workflows. Our customers have told us they are excited about AI’s promise but did not want another tool to evaluate, integrate, and maintain. They need AI built for healthcare that works inside systems their teams already use daily. Amazon Connect Health delivers value to healthcare organizations today and puts them on a path for transformative patient, clinician, and staff experiences in the future. Rather than simply streamlining existing processes to work faster, Amazon Connect Health enables entirely new ways of working. Clinicians focus on care while insights surface seamlessly, patients receive scheduling assistance instantly without staff manually compiling data, and medical billing completes in minutes instead of days without sacrificing accuracy.

Amazon Connect Health builds on Amazon Connect, AWS’s AI-powered solution for delivering personalized customer experiences at scale that serves tens of thousands of businesses worldwide and handles over 16 million interactions daily. We’re bringing that proven technology to healthcare, purpose-built for patient engagement and care delivery.

Amazon Connect Health: Agentic AI built for healthcare

Amazon Connect Health is a new agentic AI solution from AWS that handles the high-volume administrative tasks that burden healthcare teams. It enables clinicians and staff to focus on patients. It incorporates responsible AI and trust as core features, not afterthoughts. AWS’s industry-leading enterprise grade security and reliability are built into the solution.

For healthcare provider organizations

Amazon Connect Health offers agentic AI capabilities for patient engagement that are pre-integrated with Amazon Connect. Available today:

• Patient verification (generally available): Conversational patient identity verification with real-time EHR integration to eliminate manual record lookup.
• Appointment management (preview): Natural language voice scheduling with 24/7 availability, real-time insurance verification, and EHR integration. Patients are able to book, reschedule or cancel without hold times.

Key benefits:

• 24/7 patient access with minimal wait times.
• Reduced administrative burden by streamlining scheduling and verification, freeing staff to focus on patient care.
• Robust reporting, analytics, and multi-channel engagement because it is built natively into Amazon Connect with world-class reporting, analytics, and multi-channel engagement, rather than a siloed solution.
• Purpose-built for healthcare with understanding of call context, patient preferences, and seamless escalation to staff when situations require a human touch.

For healthcare tech builders

Builders in EHR companies, healthcare ISVs (Independent Software Vendors), and tech-enabled providers can leverage a unified SDK to directly integrate Amazon Connect Health’s point of care capabilities into their existing workflows. Each capability is fully managed and modular, enabling builders to incrementally add agentic capabilities through the same SDK without requiring new integration projects. Available today:

• Patient insights (preview): Surfaces visit-specific insights including patient summaries, health events since last visit, and HCC (Hierarchical Condition Categories) recapture from structured and unstructured longitudinal patient records.
• Ambient documentation (generally available): Generates clinical notes from patient-clinician conversations in real time, automatically formatted into existing EHR templates. Supports 22+ specialties and offers traceability from generated notes to transcripts.
• Medical coding (preview): Generates ICD-10 and CPT codes from clinical notes with confidence scores and full source traceability

Key benefits:

• Reduced administrative burden for clinicians with output linked back to the source data to drive trust. Clinicians get more face time with patients.
• Accelerated revenue cycles for provider organizations with medical codes ready to review by the time each patient visit ends.
• Speed development timelines and reduce undifferentiated heavy lifting for engineering teams, who no longer need to spend months or years building these capabilities, optimizing AI accuracy, or maintaining them as the underlying AI capabilities evolve.
• Integrate AI into existing workflows in less than a week. Unlike solutions requiring screen and workflow changes, the unified SDK enables direct integration into EHR screens and digital front doors.

Healthcare AI that can be trusted

The first question any clinician or healthcare team member asks about AI is: Can I trust this? Amazon Connect Health builds trust and safety into the product. Every patient insight, clinical note, and billing code traces back to its source transcript or patient chart data. Clinicians tap any AI output and view the underlying evidence immediately. The solution combines supervised fine-tuning, reinforcement learning, LLM reasoning, and information retrieval trained with healthcare domain expert guidelines and real-world data. Critical capabilities undergo rigorous validation through manual evaluation and automated testing, meeting AWS standards for robustness, safety, and scalability. Patient-facing verification and scheduling agents automatically escalate to a human when needed.

Making human-AI collaboration real for healthcare

Healthcare customers tell us their vision for AI extends beyond faster workflows. They want completely new experiences where clinicians and staff feel supported by a trusted teammate that handles routine tasks and frees them to deliver exceptional patient care. Amazon Connect Health works backwards from the humans who use it. For example, we build AI agent personalities using the OCEAN framework, grounding communication style and task handling in human personality traits. Users communicate in their own distinct tone and style, minimizing friction and enabling better experiences for patients and staff.

Unlocking data to deliver meaningful AI experiences

Agentic AI in healthcare is only as good as the data it can access. However, healthcare data often arrives fragmented across multiple systems and formats. For customers who do not have their data in a unified format, Amazon Connect Health addresses this with pre-built connectivity into AWS HealthLake, a petabyte-scale healthcare data layer that transforms disparate records into actionable intelligence. Amazon Connect Health capabilities, such as patient insights, integrate with AWS HealthLake in a few clicks. AWS HealthLake also reduces manual effort for normalizing external records (e.g., transforming CCDA files into FHIR format) through a purpose-built data transformation agent, which just launched in preview. Additionally, we are working with partners such as Redox who have pre-existing integration with 100+ EHRs and 35+ HIEs (Health Information Exchanges) to help customers seamlessly integrate their data. As a combination of these capabilities, customers can point agents to unified data sources to receive context-driven intelligence, enabling clinicians to make informed decisions without piecing together information from multiple systems.

What our customers are seeing

What inspires us most about the future are the stories we hear from customers. In addition to UC San Diego Health, who shared their story in SVP, AWS Applied AI Solutions, Colleen Aubrey’s About Amazon blog, see how more customers are using Amazon Connect Health capabilities to improve the patient and clinician experience below.

Amazon One Medical: Amazon One Medical, a national in-person and virtual primary care organization, has been at the forefront of putting Amazon Connect Health to work in real clinical settings, and the results speak for themselves: ambient documentation now spans more than a million visits, with strong clinician adoption and regular weekly usage. This year, they’re expanding to intelligent medical coding, further reducing the administrative burden that slows healthcare organizations down.

Netsmart: “Since deploying Amazon Connect Health, Netsmart has seen ambient documentation adoption increase by 275% across our network of more than 1,300 client organizations. Providers are spending less time on administrative tasks and more time with patients — and we’re seeing that translate directly into improved staff retention.” — Matthew Arnheiter, SVP Innovation, Netsmart

Veradigm: “We are collaborating with AWS on purpose-built offerings across the healthcare AI stack. Amazon Connect Health’s ambient capability is pre-integrated into our Electronic Health Record (EHR), enabling clinical documentation and saving hours of time for clinicians daily. We intend to expand this collaboration with newer agents such as medical coding and patient insights. Building performant agents require a robust AI-ready data foundation. We have selected HealthLake as our Agentic AI data and API layer, which underpins multiple applications ranging from patient insights to care coordination. We are migrating our historical data spanning decades into HealthLake, enabling us to real-time stream data from EHR systems to power interactive applications and workflows. This transformation empowers our teams to build world-class agents, freeing them from managing the underlying agentic data infrastructure.“— Tehsin Syed, CPTO, Veradigm.

Greenway Health: “Greenway has earned the trust of ambulatory practices by staying focused on practical innovation—and AWS has been a key partner in that journey. We have a long track record of innovating with AWS, including work with AWS HealthLake to advance interoperability and accelerate our agent capabilities. Amazon Connect Health represents an important next step for AI in healthcare, and Greenway is impressed by AWS’s healthcare-specific design and emphasis on responsible AI and trust. Greenway is excited to partner with AWS to continue embedding agent experiences—such as AI-powered scheduling, patient insights, and medical coding—into Greenway workflows, helping clinicians work more efficiently.” — David Cohen, CPTO, Greenway Health

Pelago, the leading specialty substance use care provider, reclaimed hundreds of clinician hours per month and enabled the team to deliver higher-quality care after deploying Amazon Connect Health’s point-of-care capabilities. For a care setting where the therapeutic relationship is everything, giving clinicians back their attention has made a measurable difference.

How to get started

Amazon Connect Health is now available in US East (N. Virginia) and US West (Oregon). Healthcare provider organizations can get started through Amazon Connect, and healthcare ISV and EHR developers can access point-of-care capabilities through the unified SDK. To learn more, visit the Amazon Connect Health page, speak with your AWS account team or contact an AWS Representative.

Amazon Connect Health is built on HIPAA-eligible AWS infrastructure. AWS has been named the winner of the Best in KLAS for Public Cloud award for two consecutive years.