Manage cookies

Cookie Settings

Cookies necessary for the correct operation of the site are always enabled.
Other cookies are configurable.

Essential cookies

Always On. These cookies are essential so that you can use the website and use its functions. They cannot be turned off. They're set in response to requests made by you, such as setting your privacy preferences, logging in or filling in forms.

Analytics cookies

Disabled

These cookies collect information to help us understand how our Websites are being used or how effective our marketing campaigns are, or to help us customise our Websites for you. See a list of the analytics cookies we use here.

Advertising cookies

Disabled

These cookies provide advertising companies with information about your online activity to help them deliver more relevant online advertising to you or to limit how many times you see an ad. This information may be shared with other advertising companies. See a list of the advertising cookies we use here.

Case study · Industrial maintenance · AI + AR

AI SmartAssistance: an expert in every technician's field of view

An AI-powered AR assistant that guides field technicians through complex maintenance tasks in real time, with Microsoft HoloLens 2, a custom-trained AI and the company's own knowledge base.

Product: AR assistant for field technicians
Device: Microsoft HoloLens 2, fully hands-free
Technology: Custom-trained AI + holographic overlay
Industry: Manufacturing, field service, complex equipment
Support: Remote expert, 24/7, from anywhere
Scope: AI training, AR development, HoloLens integration

3D and spatial mapping with our strategic partner

The challenge

Industrial maintenance was expensive, slow and uneven

When complex machinery breaks down, every hour of downtime has a direct cost. Dispatch a specialist, wait, fix, repeat: the traditional model was never built for the pace and scale of modern operations.

Cost & logisticsSending experts on-site doesn't scaleEvery service call meant travel, accommodation and coordination across time zones. A senior engineer can't be on three continents at once.

Knowledge gapSkill varies. Machines don't forgive itJunior technicians working from paper manuals or phone support made inconsistent decisions under pressure. One missed step could mean a failed repair or a safety incident.

Downtime costEvery hour waiting is revenue lostProduction lines don't pause while a technician waits for the right person or the right document. Slow, uncertain maintenance is a main driver of downtime.

The problem wasn't people. It was a system that hadn't caught up with the complexity of modern equipment.

The solution

Four capabilities, one headset

AI SmartAssistance — AR step-by-step guidance

AI SmartAssistance — Custom-trained AI assistant

AI SmartAssistance — Remote expert, live

AI SmartAssistance — Predictive maintenance & data loop

How a session works

From the fault to the fix, hands-free

Put on HoloLensThe technician starts the session at the machine.

Follow the stepsHolographic instructions appear on the component itself.

Ask the AIAnswers come from the company's own manuals and history.

Call an expertIf needed, a remote specialist sees the same view live.

Close the loopSession data improves guidance and predicts failures.

For operations

What this means in real terms

Every capability was designed around a specific operational cost or failure mode.

Lower dispatch costsWhen a technician guided by AI handles a repair that used to need a senior specialist on-site, the cost per service call drops.

Faster resolution, less downtimeNo time lost searching documentation or waiting on phone support. Repairs are done right the first time.

Junior staff perform at senior levelExpert knowledge at the point of work lets less experienced technicians handle complex tasks safely.

Predictive, not reactivePatterns that precede failure become visible early, so interventions can be planned before a breakdown.

24/7 support, no extra headcountThe AI is always on, across time zones and shifts. Support no longer depends on one person being available.

Expertise that staysWhen a senior engineer leaves, their knowledge stays, available to every technician in the network.

FAQ

Questions we often get

How long does it take to implement AI SmartAssistance?

A basic deployment, with AI training on existing documentation and HoloLens 2 integration, typically takes 8 to 12 weeks from kick-off to first production use, depending on the documentation and the complexity of the equipment.

What happens when the AI doesn't know the answer?

The system is designed for exactly this. When the AI reaches the edge of its confidence, it says so and connects the technician live with a remote expert, who sees the same view through HoloLens and can annotate it directly.

Can the AI be trained on our proprietary documentation?

Yes, and that's the point. It is trained on your own technical documentation, maintenance logs, repair records and operational data, so it becomes a specialist in your equipment and processes.

Do we need 3D models or technical drawings ready?

Not necessarily. If you have CAD files, schematics or maintenance manuals, we use them. If not, our partner Loto Studios handles 3D asset creation and spatial mapping from scratch.

Does it work in facilities with poor internet connectivity?

Core guidance works offline, which matters for remote sites and underground facilities. The live remote expert connection needs internet; the AI assistant and holographic overlays work without it.

What hardware does the technician need?

Microsoft HoloLens 2, a standalone mixed reality headset. For remote sessions the expert only needs a laptop or tablet. No special infrastructure is needed on site.