A composable equipment ontology turns any biomedical technician into the equivalent of a multi-year expert — recognising devices on sight, composing the correct procedure, and carrying that understanding from the training center into the field.
Genesis shows the steps. EON Universal understands the work.
IRVINE, CA. – July 2, 2026 – EON AI Ventures today introduced EON Universal for Healthcare, a new field-intelligence layer for safety-critical industry that understands medical devices at the level of process intelligence — not merely the steps of a procedure. Where conventional training and simulation tools must be rebuilt site by site, EON Universal learns a bounded library of medical devices once and composes any device on any ward from them. The result: a green worker performs like a seasoned one, and that competence travels from the classroom to the field.
EON Universal is offered by EON AI Ventures under Work Intelligence — the enterprise’s emerging system of record for how work is actually done. If ERP holds a company’s resources, CRM its customers, and PLM its products, Work Intelligence holds its work. EON Universal is the engine that makes that work executable: it turns a hospital’s device fleet into something a machine can recognize, reason about, and teach. . The technology, architecture, and enterprise vision behind this approach are detailed in the accompanying white paper, “EON Universal: Facility-Agnostic Training & Field Intelligence for Healthcare.”
THE PROBLEM: The expertise cliff
In hospitals, the senior clinical engineers who hold decades of judgment are retiring as device fleets grow and connect. The biomedical equipment technicians replacing them are green, in a domain where being wrong is a patient-safety and escalation problem, not an inconvenience. Industry has poured money into content: vendor courses tied to one make and model, of little help on the next device in the queue. The economics never close, because the work is treated as an infinite list of devices to memorize.
EON Universal starts from the opposite premise. A worker should be able to walk up to a device they have never seen and be guided to do the job correctly — to recognize the component on sight, be guided through the correct procedure step by step, and have the system escalate — stop and hand off to a human — the moment it is unsure. The worker is green. The guidance is not.
Click on the image below to access the EON Universal Healthcare Presentation.
THE CORE INSIGHT: Composition, not enumeration
A hospital isn’t a monolith to be memorized. Across every ward, biomedical work is performed on a finite library of known device classes — the same infusion pumps, ventilators, monitors, defibrillators and analyzers, arranged differently from one site to the next. The breakthrough is to model the vocabulary rather than the device estate.
Think of a language. You could try to memorize every full sentence you will ever need — endless and hopeless. Or you learn the words and build any sentence. EON Universal learns the components, then composes any device on any ward. You don’t model every hospital; you model the device classes every hospital is built from.
Enumeration scales with the number of hospitals and never ends. Composition scales with a bounded set of component classes — and every job performed makes the shared library smarter. One approach is a cost that recurs forever; the other is an asset that compounds.
THE BOUNDED LIBRARY: Fifty classes, not five hundred hospitals
In a hospital fleet, roughly 50 device classes cover the overwhelming majority of biomedical work. About 15 of them carry most of the daily value, and together the core library accounts for 80%+ of real work orders. The library is built on GMDN and UMDNS — the medical-device nomenclatures (ISO 15225) that clinical engineers already use — so when EON Universal recognizes a device, its output maps straight into the hospital’s CMMS / asset register and the device’s service history. It speaks their data language on day one.
| Tier | Scale |
What it covers |
|---|---|---|
| Tier 1 | ~50 classes | Core devices a biomed touches — 80%+ of work orders |
| Tier 2 | ~300 types | Makes & models — rarely surprised |
| Tier 3 | 1,000–2,000 | Maintainable items: sensors, batteries, valves, boards |
Click on the image below to access the EON Universal Work Intelligence Healthcare Library Presentation.
WHAT “KNOWING A COMPONENT” MEANS: A six-layer competence record
To “know” a component, EON Universal carries six layers of structured knowledge for every class:
- Identity — the GMDN/UMDNS class, make and model, and common aliases.
- Geometry — a 3D model plus multi-angle imagery.
- Anatomy — subcomponents and the boundary of the asset.
- Function — what it does and its operating envelope.
- Behavior — how it responds to upsets and abnormal conditions.
- Procedure — how to operate, inspect, isolate, and fix it.
Recognition keys on layers one and two; guidance composes from layers three through six. This is the difference between a label and an understanding.
THE DIFFERENCE: Genesis shows the steps. EON Universal understands the work.
EON Universal does not replace Genesis, EON’s production-ready engine that converts standard operating procedures and ordinary photographs into interactive, hands-on simulators. Genesis is the on-ramp — it captures how a task is done and renders it as a simulation. EON Universal is the understanding layer that sits on top: it brings the component library, the configurator, and live recognition, and it knows why each step exists. The two are complementary, and the boundary between them is exact:
|
GENESIS — the core engine |
EON UNIVERSAL — intelligence + library |
|---|---|
| Needs 3D models supplied to it | Brings the component library and the configurator |
| Runs sequential SOPs only — not conditional | Authors conditional SOPs that branch on live conditions |
| Knows what to show, but not why | Explains why each step matters |
| Cannot configure different capabilities | Generalizes to devices it has never seen |
| Does not recognize equipment in real life | Recognizes equipment on sight — feeds Field IQ + Holodeck |
This is the step nobody has taken — not even a simulator. That understanding is the entire product.
IN THE TRAINING CENTER: What EON Universal makes possible
Because the system understands the equipment, it unlocks capabilities that scripted simulators cannot:
- Talking components. Each part explains what it is and how it works — and lets the worker try it.
- Conditional procedures. Branching SOPs with safety gates — discharge the capacitor before opening.
- Fault diagnosis. Inject a fault and the trainee must recognise and respond, rather than follow a fixed script.
- Generative configurations. Produce unlimited, valid device configurations from one component library.
- Certification. Defensible, scored evidence that a worker is ready — measured against the standard.
- Compounding. Every session improves the shared library for the next worker.
Seven training use cases ship in the first library: talking components, guided & scored SOPs, conditional SOPs, fault injection, generative configurations, AR-only practice, and certification.
THE PROOF: Conditional SOPs: procedures that branch
A fixed SOP is a straight line. A conditional SOP is a decision tree with safety gates, where the next action depends on a live condition. Consider servicing a defibrillator: power down and isolate, remove the battery, then ask — is capacitor charge still present? If yes, discharge it safely and re-check; if no, proceed to service. Anything abnormal stops the job and escalates for human verification.
Why this is the proof. The ‘capacitor charge still present?’ branch only exists because EON Universal knows, from the device’s behavior layer, that a defibrillator’s high-voltage capacitor holds a lethal charge after power-off. Genesis has no concept of stored charge, so it cannot branch on it. Only a system that understands the device can author a procedure that adapts to it.
ONE SYSTEM, THREE SURFACES: Author once — deliver everywhere
The same understanding drives every delivery surface, so content is authored once and meets the worker wherever they are:
- Anywhere — phone or AR glasses. AR-only practice at 1:1 scale, off-shift, with no device on the bench.
- In the shop — tablet or AR glasses on the device. LiDAR overlays the digital twin onto the real device; every part is tappable.
- Immersive — the CAVE (Holodeck). LED walls and floor surround the trainee in a generated bay at full scale — a modern, reborn iCube, and the premium tier.
BEYOND HEALTHCARE: The same engine, every heavy industry
Because EON Universal understands devices rather than memorizing hospitals, the method transfers to any sector built from a finite parts vocabulary. Healthcare is this deck’s focus; oil and gas is the first library in active build; aerospace MRO and power and energy follow the same bounded-vocabulary approach. Learn the devices once; help every site built from them.
THE BUSINESS CASE: Own the work, not the weights
The architecture is deliberately simple: Genesis is the core engine that models, labels, and runs step-by-step SOPs; EON Universal adds the intelligence, the library, the configurator, and recognition; and Field IQ and the Holodeck deliver it — field recognition, on-the-spot guidance, and immersive scenarios. Every job performed makes the system smarter; it works on hospitals it has never seen; and it is a bounded library the enterprise owns, not a per-site modelling cost that recurs forever.
“For twenty-five years we helped enterprises see their equipment. EON Universal lets the machine understand it. General-purpose AI can learn everything on the public internet, but it cannot learn how your hospital actually runs — that knowledge has never left your sites. EON Universal turns it into an asset you own and that compounds with every shift,” said Dan Lejerskar, Founder & Chairman, EON AI Ventures
“Genesis shows the steps; EON Universal understands the work. That single sentence is the product. The moment the system knows that a defibrillator’s capacitor holds a lethal charge after power-off, training stops being a recording and becomes judgment a worker can carry into the field,” stated Mats Johansson, President & Co-Founder, EON AI Ventures.
Availability
The EON Universal method — proven first in oil and gas on ISO 14224 — applies directly to the hospital’s GMDN/UMDNS device vocabulary, delivered across phone and AR, tablet-on-the-device, and the CAVE. A detailed white paper and companion presentation are available on request. EON AI Ventures is engaging health systems and clinical-engineering teams now.
Find more information in the:
- Whitepaper: EON Universal: Facility-Agnostic Training & Field Intelligence for Healthcare
- Presentation – EON Universal Healthcare Presentation
- Presentation – EON Universal Work Intelligence Healthcare Library Presentation
Learn more by tuning to our podcast.
About EON AI Ventures
EON AI Ventures is the enterprise software company behind Work Intelligence – the captured, verified, and compounding knowledge of how expert work is actually done. Its Intelligence Flywheel platform (Genesis, Field IQ, Assess IQ) enables industrial enterprises to encode expert procedures into AI-guided simulations, deliver them to any worker on any device, and verify competency in the field. EON AI Ventures builds on more than twenty-five years of immersive, simulation, and AI technology developed across the EON group, whose platforms have served thousands of institutional customers in more than eighty countries. For more information, visit www.eonaiventures.com.