When does a bad review get decided?
The review gets written afterwards. IRIS sees the queue while you can still fix it.
There are fifteen cameras here: eleven that raise an alert when something is going wrong and four that alert nobody, they just count. They are at reception, in the lounge, in the dining room, in the kitchen, at the door and in the back of house. None in a bedroom, a bathroom or a changing room.
Without IRIS these are fifteen screens nobody watches while the queue grows.
AI-generated image
What happens before the review
A whole coach pulls up and there is one person at the desk. Nineteen guests standing with their bags beside them. In the dining room four people are looking for a table while five tables have sat uncleared for eight minutes. A finished plate is going cold on the pass. The buffet tray is empty and the guest is already in front of it. None of this is a breakdown. It is a bad moment, and a bad moment costs you a star.
IRIS watches those cameras all the time and only interrupts when a rule you wrote is met: this many people waiting at reception, this many minutes with a table uncleared, a plate stuck on the pass, an empty tray. The alert reaches whoever is on shift with the camera, the time and the video. And alongside it, alerting nobody, other cameras count: how many people come down to breakfast and when, how long the queue lasts on a Thursday, how many people are in the room right now.
And now the limit, in full and up front, because in this business it is the first thing anyone needs to hear. Bedrooms, bathrooms, changing rooms and any private space are out: no camera, no detection, no alert. IRIS works at reception, in circulation areas, in food service, outside and in the back of house. Nowhere else. A hotel sells on how it treats people, and that starts with not looking where you do not look.
The real scale
Fifteen here. Two hundred in a real hotel.
This demo shows fifteen cameras because fifteen fit on a screen. A mid-sized hotel has hundreds: reception, shared corridors, lifts, lounges, meeting rooms, dining room, kitchen, pantry, car park, pool, loading dock and service door. And a group with fifteen hotels multiplies that by fifteen, with the same operations director watching. Nobody can keep an eye on that many screens; that is exactly the problem IRIS solves: it analyses however many there are, all at once, and only interrupts when it should. On the rest it counts, and at the end of the season you have the number.
Examples
These fifteen are just examples.
Each one shows a different kind of thing: a queue, a table, a plate, a suitcase, a flare-up. They are not the fifteen things IRIS can do: they are the ones that fit on a screen. Open any of them and you will see the image as it is, and then with what IRIS understands on top.
Simulation · how IRIS works
A camera looks. IRIS understands what it sees.
An extract of the real screen, no voice-over and hands-free. Each round poses another situation. What sits behind it is a good deal bigger than what you see.
- The rule gets built
- It goes to every camera
- Published, it watches alone
- And then it fires
Now think about yours
Imagine finding out while it can still be fixed.
The check-in queue at four on a Saturday afternoon. Breakfast packed at nine and half the room empty at eleven. The table left uncleared for ten minutes while people wait standing for a seat. The plate going cold on the pass. The empty buffet tray. The suitcase left on its own in the lounge. The person who has fallen in the lobby and is not getting up. The smoke in the kitchen. And how many people are in the room right now, without counting by eye.
All of that is happening in front of cameras your hotel already owns and already paid for. And here is the other limit, the one that matters twice as much in this business: IRIS does not measure an employee. The alert is there to open another desk or send somebody to the pass, not to point at a waiter or score a receptionist. It measures the situation, never the person. And in the bedrooms, the bathrooms and the changing rooms there is nothing to measure, because there is no camera there.
Next step
What does an airport see before the queue forms?
14 cases: 7 raise an alert when something happens and 7 only measure. You see each image as it is, and then with what IRIS understands on top.
What can a camera see without pointing at anyone?
13 cases: 9 raise an alert when something happens and 4 only measure. You see each image as it is, and then with what IRIS understands on top.
And the best part
Nothing changes on the wall.On the screen, everything changes.
Same brackets, same cabling, same cameras. The only difference is that those images are now understood as they come in, instead of waiting for someone to open them.
Tell us your problem and we will say whether IRIS understands it, or not yet.
We reply the same working day.