A composable equipment ontology turns any worker into the equivalent of a multi-year expert — recognizing components 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 1, 2026 – EON AI Ventures today introduced EON Universal for Oil & Gas, a new field-intelligence layer for safety-critical industry that understands industrial equipment at the level of process intelligence — not merely the steps of a procedure. Where conventional training and simulation tools must be rebuilt facility by facility, EON Universal learns a bounded library of equipment components once and composes any facility from them. The result: a green worker performs like a seasoned one, and that competence travels from the classroom to the rig.
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 refinery, platform, or processing train 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.”
THE PROBLEM: The expertise cliff
The people who hold thirty years of judgment are retiring. The people replacing them are green — often at remote sites where being wrong is a safety and escalation problem, not an inconvenience. Industry has poured money into content: thousands of bespoke simulators, each modelled by hand for one specific facility, each obsolete the moment the plant changes. The economics never close, because the work is treated as an infinite list of places to memorize.
EON Universal starts from the opposite premise. A worker should be able to walk up to equipment they have never seen and be guided to do the job correctly — to recognzse 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 Oil and Gas Presentation.
THE CORE INSIGHT: Composition, not enumeration
A facility is not a monolith to be memorized. It is assembled from a finite library of known components — the same pumps, compressors, valves, and vessels, arranged differently from one site to the next. The breakthrough is to model the vocabulary rather than the locations.
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 facility. You don’t program five thousand locations; you program the vocabulary they are built from.
Enumeration scales with the number of facilities 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 thousand locations
In oil and gas, roughly 50 equipment classes cover the overwhelming majority of frontline work. About 15 of them carry most of the daily value, and together the core library accounts for 80%+ of real field interactions. The library is built on ISO 14224, the petroleum industry’s own equipment taxonomy, so when EON Universal recognizes a component, its output maps straight into the customer’s reliability and maintenance data. It speaks their data language on day one.
| Tier | Scale | What it covers |
|---|---|---|
| Tier 1 | ~50 classes | Core gear a technician touches — 80%+ of all field interactions |
| Tier 2 | ~300 types | Variants and subtypes — the system is rarely surprised |
| Tier 3 | 1,000–2,000 | Maintainable items: seals, bearings, actuators, instruments |
Click on the image below to access the EON Universal Work Intelligence 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 — ISO class, aliases, and tag pattern.
- 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 | Generalises to skids it has never seen |
| Does not recognise equipment in real life | Recognises equipment on sight — feeds FieldIQ + 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 — for example, release pressure before opening.
- Fault diagnosis. Inject a fault and the trainee must recognise and respond, rather than follow a fixed script.
- Generative configurations. Unlimited, engineering-valid skids generated 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 skids, 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 isolating a pump: de-energise, verify zero energy, then ask — is pressure still present? If yes, bleed down and re-check; if no, proceed to open. Anything abnormal stops the job and escalates for human verification.
Why this is the proof. The ‘pressure still present?’ The branch only exists because EON Universal knows a pump stores pressure after power-off. Genesis has no concept of pressure, so it cannot branch on it. Only a system that understands the equipment 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, at home or in camp, with no physical hardware at all.
- On the rig — tablet or AR glasses on the skid. LiDAR overlays the digital twin onto the real equipment; every part is tappable.
- Immersive — the CAVE (Holodeck). LED walls and floor surround the trainee in a generated skid at full scale — a modern, reborn iCube, and the premium tier.
BEYOND OIL & GAS: The same engine, every heavy industry
Because EON Universal understands components rather than memorising facilities, the method transfers to any industry built from a finite parts vocabulary. Petrochemical is the proven, built library today; mining, aerospace and MRO, and power and energy follow the same bounded-vocabulary approach. Learn the parts 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 facilities 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 plant actually runs — that knowledge has never left your sites. EON Universal turns it into an asset you own and that compounds with every shift,” stated 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 pump stores pressure, or that a valve has a safe state, training stops being a recording and becomes a judgment a worker can carry into the field,” said Mats Johansson, President & Co-Founder, EON AI Ventures.
The first EON Universal library — oil and gas, built on ISO 14224 — is in active deployment with enterprise customers in 2026, delivered across phone and AR, tablet-on-the-skid, and the CAVE. EON AI Ventures is engaging additional flagship operators in energy and heavy industry now.
Find more information in the:
- White paper: EON Universal: Facility-Agnostic Training & Field Intelligence.
- Presentation – EON Universal Oil and Gas Presentation
- Presentation – EON Universal Work Intelligence 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.