Station not covered
The system only knows whether the station is covered or not. It does not know who anyone is, or how long each person spends there. It alerts the supervisor so they can move someone.
Computer vision · Tailored
Computer vision in production: it watches the line and alerts you when something isn't right
Cameras over the production area and an AI that checks what they see, throughout the whole shift. They don't look at people: they look at the station, the machine, the conveyor and the material. When something isn't right, the alert reaches whoever can fix it.
Station 3Staffed
Station 4Unstaffed
Machine BStopped
Material intakeRunning low
Alert to the line manager: station 4 is not covered and the input material is running out.
Illustrative example
What it detects
Six things it can monitor on a line
Each area is drawn with you during the visit. The camera only looks at what we agree it should look at.
Machine stopped
It sees that the machine is not working and logs it with its time. If you already have the control room, we will look into making the downtime appear there too.
Material shortage before the line stops
It watches the material at the line input and alerts when it runs out, so it can be replenished before the line stops.
Line anomalies
Product stuck, fallen, piled up or out of place: whatever you show us is not normal.
Product build-up
It measures whether product builds up in front of a machine, a sign that the next one is running slower.
Shift summary
How long the line was running, stopped or without material in each shift. Numbers by line, with no people's names.
How the alert arrives
From the data to the person who can act
An alert that does not reach whoever can fix it is useless. That is why we design it from the end backwards.
- The camera sees
It watches a specific area: a station, a conveyor, the material input. Each area is drawn with you during the visit.
- Wait and alert
If what it sees is not normal for a period we agree with you, the alert reaches whoever can act, via the control room screen or the channel you choose. Waiting avoids alerting on every flicker.
- It is logged
A record is kept with the time and area: numbers and alerts, not video. It helps you see, by shift, where time is lost.
No hype
What works today and what is custom
Available today
- Control room with the status of each machine via sensors or the operator's tablet.
- Downtime with reason from the kiosk, and analysis by reason.
- Shift OEE with declared quality.
What already works is in production control.
Custom: we install and test it in your plant
- Real-time cameras over the line. Today the product does not analyse video.
- Whether a station is covered or not, without knowing who is covering it.
- Material at the input and line anomalies.
- GPU server in your plant or in Europe.
Before installing a camera
Cameras in the plant, with clear rules
A camera at work comes with rules. We explain how we approach it and what you need to do, so you can review it with your adviser from the outset.
How we approach it
- It detects the station, the conveyor or the area, not the person.
- No facial recognition: the system does not know who anyone is.
- No ranking or scoring of workers, and no comparing them with one another.
- No emotion inference: at work this is a practice prohibited by Article 5 of Regulation (EU) 2024/1689, except for medical or safety reasons.
- No sound and no cameras in changing rooms, toilets or canteens.
- Images are processed on your own server, in the plant or in Europe, and are stored only briefly. What is kept are alerts and numbers.
What you need to do, and we'll review it with you
- Inform in advance the workforce, expressly, clearly and concisely, and their representatives if any (art. 89 of Organic Law 3/2018).
- If there is a works council, its prior report on work organisation and control systems and the information on algorithms or AI systems that affect working conditions (art. 64 of the Workers' Statute).
- Carry out the impact assessment on data protection where applicable (art. 35 of the GDPR).
- Be careful with the purpose: an AI system for monitoring and evaluating people's performance and behaviour at work is considered high-risk (Annex III of the Regulation). That's why we don't set it up like that.
LOPDGDD art. 89ET art. 20.3 and 64GDPR art. 35Regulation (EU) 2024/1689 art. 5 and Annex III
We review it with you and with your employment and data protection adviser. This is not legal advice or a guarantee of compliance: every plant is different. We explain it in more detail in Cameras and AI in the factory: what the law allows in Spain.
How we test it
One line first, and then you decide
We choose a line and a problem
We look at the line together, decide what you want to monitor and where the cameras would go.
Cameras and server on that line
We set up the minimum and test it with your real production, with its lighting, dust and shifts.
We adjust and you decide
We remove false alarms, decide who gets notified for what and, if it works, we take it to another line.
Frequently asked questions
What we're usually asked
Do I need special cameras?
Normally not. Standard network cameras that are well placed are enough: position matters more than the model. During the visit we'll tell you how many and where.
Is video recorded?
Images are processed on the server. By default, alerts and numbers are stored. If you want to keep the image from an alert, we'll agree it with you with a short retention period.
Does it detect the person who is not at their workstation?
It detects whether the workstation is occupied or not, not who occupies it. It doesn't identify anyone, doesn't count each person's time and doesn't score anyone.
What about dust, steam or low light?
It matters a lot: a camera that doesn't see well is no use. That's why we test it on the real line, under its conditions, before expanding.
Read more
AI for factories
All use cases
The twenty-odd cases, by plant area and with their label.
ReadModule
Production control (MES)
The control room, the kiosk and the OEE that already work today.
ReadBlog
Cameras and AI in the factory: what the law allows in Spain
What the law says about cameras at work and about the AI that analyses them.
ReadLow budget, no commitment
Tell us about your line and we'll tell you what we'd set up
A short video call to understand what is stopping you, where and why. Then a written proposal with what we would do, where the AI would run and how much it would cost. No commitment.