Workforce & Training
AI applied to healthcare workforce development: clinical skills training, credentialing support, upskilling programs for allied health roles, and AI tutoring embedded in training content. Evaluation centers on completion and placement outcomes at named health system partners, employer integration depth, and whether AI capability is core to the training model or a content layer on conventional coursework.
The AI Health Index grades 23 workforce and training vendors, covering the products a health system buys to recruit, schedule, credential, upskill and retain clinical staff, along with the simulation and competency tools used to train them. It is one of the smaller categories inside a graded population of 554, and it is the one where the distance between what a product touches and what its vendor publishes is widest. 0 of 23 vendors earn an A on HIPAA and BAA Posture, even though these systems routinely hold clinician performance records, and the simulation tools among them often train on patient material.
| Vendor | Category | AI Centrality | Website |
|---|---|---|---|
|
I
IntelyCare
IntelyCare matches nurses and nursing assistants to open shifts, and the machine learning does two jobs rather than one: it optimises the match and it optimises the price. Facilities pay a flat rate for the platform, and the wage offered for a given shift is set according to how easy or hard that shift is to fill. Founded in 2016 near Boston by David Coppins, Ike Nnah and Chris Caulfield, and based in Quincy, Massachusetts, it has raised roughly 174 million dollars. A 45 million dollar Series B in 2020 drew Endeavour Vision, Kaiser Permanente Ventures and Generator Ventures; a 115 million dollar Series C in April 2022 led by Janus Henderson took the valuation above 1.1 billion dollars. Coppins moved from chief executive to executive chairman, and Matthew Levesque now leads the company. In January 2026 it acquired CareRev, the on demand workforce platform for acute care, with both brands continuing to operate. That took the company from its post acute origins into hospitals and produced a combined offering spanning permanent staff, internal resource pools and contingent labour in one system. Anyone searching for CareRev is looking at this group. The employment model is a deliberate counter position in a market of gig platforms. Nurses on the platform, called IntelyPros, are employed as W2 workers with health, retirement and education benefits, which the company frames as giving the flexibility of gig work without the instability of traditional agency work. The technology learns from every interaction, taking in nurse and facility preferences and a two way rating system to improve matching over time, and the company states it creates shifts before facilities recognise their own need. Hours are validated by geofencing when a nurse checks in and out through the mobile application. Reported performance is a fill rate around three times the industry average, which the company describes as the highest in the market.
|
Workforce & Training | B | intelycare.com |
|
V
Verbal
Verbal AI Technologies, founded in 2024 and led by co founder and chief executive Waleed Mohsen, audits healthcare interactions for compliance rather than conducting them. It sits alongside an organisation's existing communication systems, logs every call, and analyses call transcripts in real time and retrospectively together with clinical notes and secure chat messages, checking each against the organisation's own written clinical, safety and billing protocols. Models are trained per customer on that customer's compliance requirements across roles and service lines, and the customer validates the model's accuracy before it is released to users. Outputs include adaptive compliance checklists, audits of clinical notes for completeness and regulatory adequacy, detection of documentation gaps and inconsistencies, topic analysis across an entire interaction history, and conversational measures such as speaking pace, talk to listen ratio and sentiment, surfaced through dashboards tracking adherence and compliance trends. The company frames its position against ambient scribes directly, arguing that summarising a conversation is not the same as evaluating it. One characteristic sets this record apart from everything else in this index: the platform audits clinical notes whether a human or an artificial intelligence agent produced them, and the company names agent developers as a customer type alongside healthcare organisations. In October 2025 it was named a qualified solution on Mayo Clinic Platform, making it available to that network's affiliated organisations.
|
Healthcare Administrative Automation | A | tryverbal.com |
|
C
ClinicalKey AI
Generative clinical reference layer built on ClinicalKey, Elsevier Health's point of care content platform. Launched February 2024 as the publisher's answer to conversational clinical search, and materially expanded in February 2026. Record scoped to ClinicalKey AI rather than to Elsevier, whose portfolio spans scientific publishing and research analytics with no clinical relevance, following the UpToDate and DynaMed precedent. Note also that a separate Elsevier product, ClinicalPath, was assessed for this index in July 2025 and rejected for carrying no artificial intelligence claim; the rejection does not carry over to this record. The corpus is a proprietary, copyright cleared knowledge base refreshed daily, spanning Elsevier point of care content, reference texts including Braunwald's Heart Disease, Goldman-Cecil Medicine and the Nelson Textbook of Pediatrics, society guidelines from bodies including the American College of Cardiology and the European Society for Medical Oncology, and, since February 2026, full text from more than 130 premium journals including The Lancet and the New England Journal of Medicine. Earlier material described third party journals as abstracts only, so the February 2026 release is a real change in what the model can read rather than a restatement. Three mechanisms distinguish it. Responses carry traceability to the specific paragraph in the source rather than to the document. A real time citation validation step checks that a generated response is grounded in the evidence it cites. And the clinician can toggle explicitly between adult and paediatric context, which makes the population a set parameter rather than an assumption. Access is through web, a mobile application with voice dictation, single sign on into the record using the Smart on Fhir standard, and an application programming interface. Continuing education and maintenance of certification credit accrue from use. Available in more than 50 countries. One structural fact belongs on the record: the product was developed in partnership with OpenEvidence, which is separately indexed here and now a direct competitor at scale.
|
Clinical Reference & Evidence | C | elsevier.com |
|
D
DynaMed
Point of care disease reference from EBSCO Clinical Decisions, a division of EBSCO Information Services, and one of the two reference incumbents this segment is measured against alongside UpToDate. Content rests on a stated seven step evidence based methodology with daily systematic literature surveillance, edited by a named clinical team under editor in chief Dr Peter Oettgen. Record scoped to DynaMed and its generative layer rather than to EBSCO, whose wider portfolio spans library and research databases with no clinical relevance, following the UpToDate and ModMed precedent. The AI is Dyna AI, introduced July 2024 as a retrieval augmented generation capability sold as an add on, extended in February 2026 into Dyna AI Mode, a dedicated interface inside DynaMed, DynaMedex and Dynamic Health that a clinician can toggle in and out of rather than being forced through. The company states the generative layer draws only on its own curated content sets and never on external unvetted sources, labels AI generated output, and links each answer to its origin. Dyna AI Mode also captures questions, responses, references and timestamps in copy ready form and allows a prior query to be re run, which is closer to an audit trail than anything else graded in this category. DynaMedex is a separate joint surface combining DynaMed disease content with Micromedex drug content from Merative, and was named top performing for clinical decision support point of care disease reference in the KLAS 2026 report; DynaMed itself was Best in KLAS in 2021, 2022, 2024 and 2025. A December 2025 announcement extends Dyna AI to generate structured drug monograph and dosing summaries from Micromedex data. EBSCO Clinical Decisions joined the Coalition for Health AI in September 2024 and publishes five principles for the responsible use of AI covering quality, security and patient privacy, transparency, governance and equity. Two scope statements are carried on the record because the company publishes them plainly and they bound what a buyer actually gets: Dyna AI is currently unavailable in the European Union, and DynaMed with Dyna AI for individual subscribers is currently available only in the United States.
|
Clinical Reference & Evidence | C | dynamed.com |
|
U
UpToDate
The reference clinical decision support product against which most point of care AI tools position themselves, published by Wolters Kluwer Health and in market for more than thirty years, with content curated by over 7,600 physician authors and editors and reported use by more than three million clinicians across thousands of hospitals worldwide. This record is product scoped to UpToDate and its generative layer rather than to Wolters Kluwer, which also publishes Lexidrug, Medi-Span, Ovid and a large portfolio outside healthcare. UpToDate Expert AI, launched September 2025, is a conversational generative assistant that draws exclusively on UpToDate's expert authored and peer reviewed content rather than the open web. Its distinguishing feature is not the answer but the scaffolding around it. Every response opens with a stated Assumptions section naming what the system took for granted about the patient, for example that the patient is not pregnant, not a child and carries no major comorbidities, and inline Nudges prompt the clinician to supply context the system lacks, such as comorbidities or ICU status. Answers carry inline citations tied to specific statements with single click access to the source topic, a side panel with rationale and supporting material, and drug information drawn from Lexidrug. Clinicians can accrue CME, CE and CPD credit while searching, redeemable in the platform, which the company states is not yet recognised by every accrediting authority. Wolters Kluwer has published an AI principles statement and a validation framework for evaluating clinical AI at the point of care, and named OpenAI as its enterprise model partner in June 2026. Expert AI is included in all United States personal subscriptions and in Pro Plus and trainee subscriptions in Canada, and reaches health systems through UpToDate Enterprise Edition. Chief Medical Officer Peter Bonis MD.
|
Clinical Reference & Evidence | C | wolterskluwer.com |
|
C
Curbside Health
Clinical pathways authoring and governance platform that converts a health system's guidelines, policies and protocols into structured visual decision trees delivered inside the EHR workflow. The product covers clinical pathways and what the company calls ClinApps, guidelines and protocols, policies and regulatory content, antimicrobial stewardship and antibiograms, and embedded clinical calculators, with all content searchable, versioned, governed and measurable. Authoring is visual and requires no code, and pathway logic stays under clinician control without information services involvement after the initial integration, which is the operational claim the company leads on. A community layer lets organisations share and copy each other's pathways across institutional boundaries and across different EHRs. Governance is presented as the core feature rather than a compliance wrapper: named clinical owners, defined review cycles, multidisciplinary review workflows, version history and audit trails, and visible status showing what is live, outdated or under review. The AI scope is deliberately narrow and the company states it plainly on a dedicated page: artificial intelligence is applied to structuring and drafting content from guidelines and PDFs, to supporting updates as evidence changes, and to scaling pathway volume without proportional staffing, under a stated principle of human in the loop at every stage, transparent logic and provenance, and no autonomous clinical decision making. The marketed position is explicitly against opacity, arguing that healthcare needs clarity, transparency and accountability rather than black boxes, and that decision logic should be explicit rather than implicit. Reported at more than one million patient lives impacted, with OSF HealthCare among named implementations and a concentration in paediatric and children's hospital settings. Founded by emergency medicine physicians Eric Leroux and Dan Imler.
|
Clinical Decision Support | C | curbsidehealth.online |
|
C
C8 Health
Clinical knowledge management platform anchored in anesthesiology and perioperative services, built on the premise that the problem is not missing evidence but the gap between documented protocol and actual practice. Hospitals hold their standards as scattered PDFs, unlisted videos and physical binders, and the company frames the resulting delay in adopting new evidence against the widely cited seventeen year evidence to practice lag. C8 unifies that material into one searchable corpus delivered by role, department and schedule, restructures uploaded documents into mobile navigable formats, and tracks adherence through dashboards for quality leadership. The AI layer is C8 Panda AI, a generative assistant that answers natural language questions sourced exclusively from the institution's own vetted knowledge base, returning inline citations that name both the source document and its author, so a clinician can trace an answer back to the colleague who wrote it. A Knowledge Network lets participating institutions and clinical societies share protocols across organisational boundaries. The platform is explicitly architected to operate without requiring PHI, which is an unusual and materially different privacy posture from most clinical AI. Founded 2019 at Geneva University Hospital by Dr Ido Zamberg, a physician and software engineer who spent fourteen years on enterprise knowledge management at HP and Autodesk, with Dr Olivier Windisch; incorporated in the United States in 2022 with CEO Galia Rosen Schwarz and co founder Tzach Klo. Anesthesia was the first vertical. Reported in use at more than one hundred US hospitals including Mount Sinai, UCSF Health, Brigham and Women's, MetroHealth, UTMB and Dartmouth Health, and named an official collaborator of the American Society of Anesthesiologists. Raised a 12 million dollar Series A in July 2025.
|
Clinical Reference & Evidence | B | c8health.com |
|
P
PrecisionOS
PrecisionOS builds immersive virtual reality surgical training for orthopaedics, and what separates it from a simulation studio is that it measures. Each module produces a composite Precision Score calculated from named parameters relevant to safe and successful implantation, which the company describes as proprietary and validated and which published work has correlated with real surgical performance. The platform is led by Danny Goel MD, a practising orthopaedic surgeon, and is based in Vancouver. The evidence base is unusually strong for training software. A block randomised, intervention controlled trial of senior orthopaedic residents published in JAMA Network Open compared immersive VR against technical video instruction and reported significant gains in knowledge and procedural metrics, a transfer effectiveness ratio of 0.79, and roughly 50 percent fewer critical surgical errors. A separate randomised controlled trial in the Journal of Bone and Joint Surgery addressed complex skill acquisition. The company reports meeting all five validation benchmarks that simulation researchers apply, covering face, content, construct, concurrent and transfer validity, through multiple randomised trials in major journals, and transfer validity has been demonstrated in blinded assessment of real operative performance. The published work discloses its own conflicts rather than burying them. The JAMA Network Open trial states that the chief executive held founder equity and drew salary during the study, that a co author held equity, and that PrecisionOS part funded the work alongside the Canadian Shoulder and Elbow Society, while recording that a third party research member observed each training session and that no PrecisionOS affiliate was present for the duration. Users span residency and fellowship programmes, professional societies and medical device companies across North America and Europe.
|
Workforce & Training | C | precisionostech.com |
|
M
MEDICAL IP
MEDICAL IP builds AI segmentation and quantification software for medical imaging, and everything else it sells derives from that one capability. MEDIP and MEDIP Pro convert CT and MRI into segmented 3D anatomical models; DeepCatch and the DeepCatch X modules extract quantitative measurements from a single chest X-ray across aorta, heart, torso, tuberculosis and emphysema indications; DeepFore predicts liver cancer occurrence and DeepFore Recur predicts recurrence; TiSepX performs lung volumetry. The same segmentation output feeds downstream products in surgical planning, 3D printed anatomical models (ANATDEL), and augmented and virtual reality anatomy education. Established in September 2015 as the first spin off company from Seoul National University Hospital, led by chief executive Sang Joon Park, with its laboratory inside the SNU clinical research institute and offices in Seoul, San Jose and Xi'an. Two things distinguish the record. The regulatory portfolio is among the broadest in this index, spanning US FDA Class II, European CE with ISO 13485, UK MHRA, China NMPA and Korean MFDS approvals up to Class III. And the evidence is genuinely published rather than asserted: DeepFore appeared in the Journal of Hepatology in May 2025, was featured on that June issue's cover and selected as a Selection of the Month by the editors, which is the strongest single publication credential on this sourcing list. Filed under imaging rather than as surgical decision support. Surgical planning and simulation are applications of the segmentation output, not the product. The anatomy education business is cross listed under workforce and training, where it has its own buyer in medical and dental schools.
|
Radiology & Imaging AI | A | medicalip.com |
|
O
Oxford Medical Simulation
Oxford Medical Simulation delivers virtual reality and screen based clinical simulation to nursing, medical and allied health learners, built around a large authored scenario library rather than a generative engine. A learner takes a case as they would in practice: seeing the patient, taking a history, examining, ordering investigations, speaking with colleagues, prescribing, treating and handing off, under time pressure. The stated focus is clinical decision making under pressure, crisis resource management, team interaction and patient engagement. Scenarios end in immediate automated feedback naming strengths and areas for improvement with evidence based rationale, and educators see individual and cohort level data to spot trends and target remediation, with a Competency Mapping and Tracking feature logging actions taken in a scenario and aligning them to the components of a competency framework. The library runs to more than 240 clinical scenarios across learner levels and specialties. The company sells to universities integrating simulation into curriculum and to health systems using it for onboarding, orientation, certification support and new to practice nurse development, with named users including Boston Children's Hospital, NYU Rory Meyers College of Nursing, the University of New England, Indiana University of Pennsylvania and the University of Northampton. Founded in 2017 with UK origins and now headquartered in Boston, it raised 12.6 million dollars in January 2024.
|
Workforce & Training | C | oxfordmedicalsimulation.com |
|
P
Proximie
Proximie began as a way for a surgeon to virtually scrub in to any operating room and has become an operating system for the OR built on the data that capability generates. The original product is augmented reality telepresence: a remote expert joins a live procedure with full audio and video, annotates the surgical field, and observes, advises or teaches in real time, with every case recorded and indexed into a secure library for debrief, coaching and structured video review. On top of that sits the Intelligence Suite, described by the company as an ambient AI infrastructure layer that continuously captures intraoperative video, workflow activity imagery and instrument data across hundreds of facilities. In April 2026 Proximie joined NVIDIA's Project Rheo, building its Smart OR platform on NVIDIA foundation models while contributing real world surgical data back to inform NVIDIA's next generation healthcare models. The company reports deployment in more than 500 hospitals across 50 countries and five continents, more than 20 peer reviewed publications, and platform users seeing operating room productivity improve by up to 24 percent, which it frames as up to 300 additional procedures per room per year through better workflow visibility and more accurate prediction of surgery duration. Proximie was founded in 2016 by Dr Nadine Hachach-Haram, a practising NHS consultant plastic surgeon, and raised an 80 million dollar Series C with SoftBank participation. It is also lead author of a report on patient safety in surgery and the case for reform in the NHS.
|
Health System AI Platforms | B | proximie.com |
|
C
Caresyntax
Caresyntax is a vendor neutral enterprise surgical data platform that instruments the operating room and analyzes what it captures. Proprietary software and AI process video, audio, images, connected device output, clinical records and operational data from before, during and after a procedure, feeding real time support to the team in theatre, a telehealth link for people outside it, and post procedure analytics afterwards. The company sells the same data asset to four different buyers, which is unusual and shapes how the platform should be read: hospitals use it for operating room efficiency and throughput, surgeons for benchmarking and technique review, medical device manufacturers for product development evidence, and insurance companies for surgical risk assessment and policy design. Scale is substantial, with software in more than 4,000 operating rooms worldwide supporting over 30,000 surgical professionals across more than two million procedures a year. Caresyntax is headquartered in Boston and raised a 180 million dollar Series C extension in August 2024, comprising 80 million in equity and a 100 million growth debt facility, from investors including Optum Ventures, BlackRock Innovation Capital, Intel, and the medical liability insurers ProAssurance and Relyens. It also partners with Google Cloud.
|
Health System AI Platforms | B | caresyntax.com |
|
T
Theator
Theator built the category it calls Surgical Intelligence: computer vision and large vision language models applied to intraoperative video from cameras already present in minimally invasive and robotic operating rooms, turning the procedure itself into structured data. The platform automatically records every case, identifies procedural steps, safety milestones and critical events, links that video to the patient record over HL7, and returns case and departmental analytics used for quality review, standardization, OR efficiency and surgical training. Its flagship product, Surgery-to-Text, generates a structured operative report in real time that the surgeon reviews and signs on leaving the theatre, replacing dictation and memory based reporting; the company anchors that product against published research finding memory written operative reports accurate only 72.8 percent of the time. In June 2026 Oracle Health formalized a US collaboration deploying Theator on Oracle Cloud Infrastructure and writing reports directly into the Oracle Health EHR. A validation study of the platform's computer vision measurement of warm ischemia time during partial nephrectomy, against expert reviewed video as ground truth, has been published in the peer reviewed literature. Theator was co founded by Tamir Wolf, a physician, and is headquartered in Palo Alto with research and development in Tel Aviv.
|
Workforce & Training | A | theator.io |
|
P
Patient Ready
Patient Ready is an AI native clinical simulation platform for nursing education and health system workforce training, delivering the same scenarios through both immersive VR and screen based formats. Its distinguishing claim is emotionally responsive AI patients that respond dynamically to a learner's decisions, emotional cues and the clinical context rather than following branching menu logic, which is aimed at practicing communication, trust building and de escalation alongside clinical reasoning. Learners converse with the patient while charting and acknowledging orders inside the simulation. Scenarios can be authored and reused across conditions, acuity levels, populations, languages and social contexts, with AI supported tools for authoring, assessment and debriefing, and the assessment model is aligned to the Clinical Judgment Model and the Next Generation NCLEX. The company sells into two markets, academic nursing programs and health systems, the latter for onboarding time reduction and communication and de escalation training. It was named the fifth most innovative company in education by Fast Company in 2026 and operates a UK arm, Patient Ready Ltd.
|
Workforce & Training | A | patientready.net |
|
L
Laudio
Laudio is a leader operations platform for frontline healthcare managers, built on the premise that the nurse manager is the lever that moves engagement and retention and that the job has become administratively impossible. It aggregates data from human resources information systems, time and attendance, scheduling, email, EHR admission and discharge feeds and the learning management system into a single workflow hub, then uses AI to recommend which specific, timely leader actions to take with which team members. Modules cover engagement and recognition, performance and professional development, overtime and attendance management, patient rounding and audits, with Performance Insights added in October 2025 to synthesize recognition, work patterns and peer input into views used in performance reviews. The platform is deployed at more than 150 hospital and health system sites covering over 300,000 frontline staff, with named customers including UNC Health, Northwell Health, Nebraska Medicine, Boston Medical Center, Memorial Hermann, MemorialCare, Novant Health, El Camino Health and North Mississippi Health Services. Implementation is stated at 12 weeks or less. Laudio was reported acquired by Ascend Learning in August 2025, which is corroborated by its website serving terms and privacy policy from a domain belonging to Kognito, an earlier Ascend Learning acquisition. Ascend Learning is a health education content, software and analytics group, so the acquisition places a frontline workforce analytics platform inside an education publisher rather than a health system technology vendor, and buyers should treat product roadmap direction and continuity as questions worth asking.
|
Workforce & Training | C | laudio.com |
|
C
C-SATS
C-SATS stands for Crowd Sourced Assessment of Technical Skills, and the name describes the mechanism accurately. Surgeons upload video of their own procedures, captured device agnostically from any minimally invasive surgery platform, to a private cloud library. Machine learning removes patient identifying data and segments the video into procedural steps, and the technical assessment itself is then performed by vetted expert surgeons and a crowd of trained reviewers scoring against validated instruments including GEARS, the Global Evaluative Assessment of Robotic Skills. Surgeons receive confidential, benchmarked feedback and performance trends through a personal dashboard and can earn continuing education credit. The platform was founded in 2014 as a University of Washington spinout, was acquired by Johnson and Johnson in April 2018, and now sits inside Johnson and Johnson MedTech alongside the Johnson and Johnson Institute's professional education offerings. Named deployments include Northwell Health, Providence St. Joseph Health, AdventHealth, Hackensack University Medical Center, Valley Health System, the University of Washington, UC Irvine Health urology and Severance Hospital at Yonsei University Health System.
|
Workforce & Training | C | csats.com |
|
V
Vivian Health
Vivian Health is a healthcare jobs marketplace connecting clinicians with employers and staffing agencies, which since October 2025 has layered an AI recruiting assistant over that marketplace. Vivian AI Assistant engages candidates around the clock, screens them against named role requirements including active licensure in the required state, board certification, recent clinical activity and DEA registration for advanced practice roles, prepares them for submission and hands them to a human recruiter. AI Proposals, added in June 2026, drafts personalized candidate outreach that a recruiter must review, edit and approve before it sends. The platform spans travel, permanent, per diem, local contract and advanced practice work across nursing, allied health, therapy and advanced practice provider roles, with more than 2.8 million registered healthcare professionals and over 250,000 job opportunities. Named employers and agencies include Trinity Health, Tenet Health, Adventist Health, Memorial Hermann, University of Miami Health, Sanford Health, HealthTrust, Ingenovis Health and Jackson Nursing Professionals. Vivian began as NurseFly, was acquired by IAC, and is now a subsidiary of People Incorporated, which adopted that name and the PPLI ticker in June 2026 as the parent refocused on its publishing business and a stake in MGM Resorts.
|
Workforce & Training | B | vivian.com |
|
A
Arena Analytics
Arena Analytics applies machine learning to healthcare hiring and workforce decisions. Rather than scoring generic candidate quality, its models predict a specific outcome for a specific role at a specific organization, most often whether a candidate will still be in that job after a set period. The suite spans Retention Prediction, Talent Rerouting, Talent Discovery, Flight Risk, Internal Mobility, a Workforce Dashboard and Workforce Development. The company began as Pegged Software and rebranded to Arena in 2016, having been spun out with a healthcare focus from Catalyte, which applies related methods to software engineering teams. Arena operates as a scoring and routing layer on top of existing ATS and HRIS systems including Workday, ADP, UKG, Paycom, iCiMS, TalentReef, Jobvite, Oracle and symplr rather than replacing them. Named healthcare deployments include Mount Sinai Health System, MultiCare Health System, Sunrise Senior Living, Benchmark Senior Living, Validus Senior Living and Curo Health Services. Arena publishes an adversarial fairness approach to bias mitigation and states that its recommended candidate groups clear the EEOC four fifths threshold. It has since extended beyond healthcare into hospitality and quick service roles.
|
Workforce & Training | A | arena.io |
|
L
Lyssn
AI that measures the quality of psychotherapy rather than documenting it, which makes it structurally different from every other behavioral health vendor in this index. The problem it addresses is real and well stated in the academic literature: health systems worldwide have spent enormous sums increasing access to evidence-based psychotherapies such as CBT, yet there has been no scalable way to evaluate whether those therapies are actually delivered competently, leaving quality and effectiveness largely unmeasured. Lyssn provides a HIPAA-compliant cloud platform for recording, sharing and reviewing therapy sessions with speech-to-text transcription, AI-generated fidelity and quality metrics, time-linked commenting inside audio and video playback for asynchronous supervision, and dashboards summarising performance across a caseload. Therapists can record in-person or telehealth sessions or upload sessions recorded elsewhere. The buyer is a training programme, supervisor, clinic or public health system rather than an individual clinician seeking time savings. Founded by PhD-level clinical researchers and data scientists out of the University of Washington, including David Atkins, Zac Imel, Michael Tanana and Shrikanth Narayanan. The evidence posture is unusual in this index: the underlying science is published in peer reviewed venues with the founders' equity stakes disclosed as competing interests in those papers, which is a higher standard of transparency than vendor-funded studies normally meet. Project AFFECT is an NIMH-funded research partnership with the Penn Collaborative for CBT and Implementation Science, registered as NCT05340738, evaluating AI-generated CBT fidelity feedback against usual care. Separate University of Washington work with King County's healthcare system evaluated detection of CBT for psychosis skills. Products extend to ClientBot, a patient-like conversational agent for training basic counselling skills.
|
Behavioral Health AI | A | lyssn.io |
|
V
Verifiable
Credentialing automation and provider network monitoring platform built around real time primary source verification across hundreds of sources, with continuous monitoring that flags expiring licenses, sanctions, and exclusion list changes. Distinguished by a Salesforce native architecture that lets organizations run credentialing inside their existing CRM rather than a separate system, and by offering both software and NCQA certified credentials verification organization services so customers can bring the function in house or outsource it.
|
Healthcare Administrative Automation | C | verifiable.com |
|
M
Medallion
Provider network operations platform automating credentialing, payer enrollment, state licensing, privileging, and ongoing compliance monitoring, positioned as an AI operations partner running a real time credentials verification organization. Integrates directly with primary sources including federation and federal databases to verify and monitor credentials, and pairs AI agents with credentialing specialists who review critical stages and handle exceptions. Serves health systems, digital health companies, payers, and provider groups.
|
Healthcare Administrative Automation | B | medallion.co |
|
I
Incredible Health
AI marketplace for permanent healthcare hiring that inverts the application model: employers apply to nurses rather than the reverse. A predictive matching engine screens credentials and preferences against algorithms recognizing more than 70 specialties and 250 skills, generative AI processes resumes and drafts tailored recruiter outreach, and two AI agents extend the platform, Gale as a career partner handling resume building and mock interviews, alongside Lyn. The vendor reports 1.5 million US healthcare workers and 1,500 healthcare employers on the platform, permanent roles filled in under 20 days against industry averages several times longer, a 20 percent increase in interview request acceptance after introducing generative outreach, and 15 percent higher retention for nurses hired through the platform. Free to nurses and paid by employers. Founded 2017 by Dr Iman Abuzeid; roughly $100 million raised at a reported $1.65 billion valuation.
|
Workforce & Training | B | incrediblehealth.com |
|
S
Stepful
AI powered healthcare workforce training platform operating as school as a service for health systems: employer sponsored, debt free training pathways for medical assistants, pharmacy technicians, practical nurses, dental assistants, and surgical technicians, expanding into registered nursing, respiratory therapy, and imaging. AI runs through instruction (personalized learning), avatar based clinical simulations, remote skills assessment, and workforce planning. Reports more than 32,000 graduates and 35+ health system clients including Mount Sinai, Ochsner, and Providence. Raised a $55 million Series C led by Oak HC/FT in June 2026, bringing total funding to $105 million.
|
Workforce & Training | B | stepful.com |
Citable summary
Self contained paragraphs, current as of August 31, 2026, free to quote with attribution.
How to choose a clinical workforce development platform
The AI Health Index grades 23 workforce and training vendors on the same fifteen capability axes it applies to clinical products, verified as of August 31, 2026, and the grades say the choice should turn on setting rather than on feature count. Setting and Specialty Coverage is the strongest axis in this category, with 7 of 23 vendors at an A and 22 at an A or a B, which means most vendors here are at least clear about who they built for. That clarity is the thing to use. A platform built for nursing competency in an acute setting and one built for physician onboarding across an ambulatory network look almost identical in a demo and solve different problems, and the published roster separates them before a sales call does.
Source: AI Health Index, August 31, 2026
What the AI Health Index finds missing across workforce and training vendors
Verified as of August 31, 2026, the AI Health Index grades 0 of 23 workforce and training vendors at an A on Commercial Transparency, 0 at an A on AI Governance and Bias Disclosure, and 0 at an A on AI Liability and Recourse. The governance figure is the one worth stopping on. A model that scores a clinician competency, ranks a job candidate or predicts who is about to resign is making a consequential judgement about a named person, and it does that outside the regulatory attention a clinical model attracts. The AI Health Index grades disclosure rather than product quality, so these are gaps in what a buyer can verify rather than accusations, and any vendor that publishes more is regraded.
Source: AI Health Index, August 31, 2026
Common questions
Which clinical workforce development platform should I choose?
Choose on the setting the platform was built for and on what it is allowed to do unattended, and work from a published roster rather than a shortlist assembled from vendor websites. The AI Health Index grades 23 workforce and training vendors on fifteen capability axes with a verification date on every record. Setting and Specialty Coverage is where this category is strongest, at 7 of 23 on an A, so the roster will usually tell you plainly whether a product was built for nursing competency, physician onboarding, scheduling or credentialing. Autonomy and Oversight Model is the second question, at 6 of 23 on an A, because a system that screens candidates or flags a competency gap with no human reviewer has changed a personnel process rather than supported one.
What clinical workforce development platform has the best customer service?
Support quality is not something the AI Health Index grades, because it cannot be verified from public sources and every vendor claims it. The closest verifiable proxies the index does publish describe how a vendor behaves after the contract is signed rather than during the sale: Deployment Model and Data Residency, where 0 of the 23 vendors in this category earn an A, and Commercial Transparency, where 0 do. For support specifically, the question worth putting to a reference customer is who resolved their last integration problem and how long it took. That answer separates vendors in a way a support page never will.
Which clinical workforce development platforms scale to a large health system?
Scale in this category is an integration problem rather than a capacity one. The AI Health Index grades 2 of 23 workforce and training vendors at an A on EHR and Interoperability Depth, with 11 at an A or a B, and that axis predicts whether a platform survives a rollout across many sites far better than any headcount a vendor quotes. The reason is that a large system runs several scheduling systems, more than one credentialing source of truth, and a human resources platform chosen without reference to either. Deployment Model and Data Residency is the second axis to read, at 0 of 23 on an A, because a vendor that cannot state where its system runs will not clear a large system security review quickly.
How does the AI Health Index grade workforce and training AI?
On the same fifteen capability axes it applies to clinical products, researched from public sources, with a verification date on every record and grades running A to D. A grade describes what an outside buyer can verify on that date rather than how good the product is, so a D records an absence far more often than a defect. No vendor pays for inclusion or for a grade. The index deliberately applies the clinical axis set here rather than a softer one, because a product that holds clinician performance data and makes automated judgements about people should answer the same questions a clinical product answers.
Do vendors pay to appear in the AI Health Index workforce & training category?
No. The AI Health Index is researched from public sources, no vendor pays for inclusion, for a grade or for placement, and every record carries the date it was last verified.
Workforce & Training comparisons
Comparisons are published only where the index assesses two vendors as direct competitors for the same buyer. Each carries a verdict, the buyer conditions that favor each side, and a graded side by side across all fifteen capability axes.