CAM-521
A bulky item comes in and stays put in the lobby
Mid-afternoon in a high-street branch. A customer is being served at the counter. Behind him, standing in the middle of the lobby, is someone carrying a large, rigid backpack the size of a box. They are not in the queue, they do not approach the counter and they do not move from the spot: it has been more than two minutes. IRIS does not know why anyone came in, does not infer it and has no business doing so. What it sees is a fact you can measure with a clock: a bulky item came through the door, stayed in the public area and is still there.

Turn on IRIS Vision
AI-generated image
What IRIS understands
What it recognises in this scene
- bulky item
- person standing in the lobby
- cap
- customer being served at the counter
- employee behind the counter
- counter
- indoor cash machine
- entrance door
What this camera measures
An alert says something is happening. The reading says how much.
- 2 min 20 sItem inside for
- 1 min 50 sStill in the same spot for
- 17:42:11Came through the door at
- 3People in the lobby
- 17:41:58Video saved from
The figures on this screen are an example from the illustration, not any client's measurement.
The rule
You decide once. IRIS applies it always.
If
a bulky item comes through the door and has stood still in the public area for more than two minutes
Then
- raise a silent alert on the branch screen
- note the time the item came in and where it is now
- save the clip of the entry and the clip of the exit, so they can be watched side by side
The instruction that set it up«Tell me if a bulky item comes into the branch and stays more than two minutes in the public area without going up to the counter.»
What changes
What changes for whoever answers for the branch network
In a branch with two employees and a customer in front of them, nobody is watching the lobby, and that is the whole story. The alert says nothing about who anyone is or what is going to happen: it says there is a bulky item standing where people walk, and it has been there two minutes. With that, an employee looks up and asks whether they need anything — which is what they would do with anybody standing about without joining the queue. And then there is the second thing, worth as much as the first: the time the item came in and the time it left, side by side, and if what left is not what came in, that is on the record too. Nobody has that record today.
What people usually ask
Does IRIS say anything about the person carrying the item?
No, and it is not going to. IRIS does not know why anyone came in, does not infer it and does not hint at it. A delivery, a house move, a parcel, a travel backpack or somebody on their way back from the gym are ordinary things in a high-street branch, and none of them says anything about anybody. The alert contains an object, a place and a clock: a bulky item came in at such a time, it is in the public area and it has been standing still for two minutes. Who is carrying it is not part of the data: it is not stored, not compared and not asked.
So what is the alert for?
So that somebody looks up. In a branch with two busy employees, a lobby can go twenty minutes without anyone raising their eyes, and that is what gets corrected. The vast majority of the time the employee asks whether they need help, the answer is yes, and that is the end of it — which is how it should end. What remains afterwards is a simple, factual record of what came in, how long it stayed and what went out, with the times. That record did not exist, and it is as useful for a complaint as for working out whether something at the counter needs changing.
What does this camera not see?
It sees the lobby and the door, and of an item it sees only the outside: size, shape and colour. It does not see what is inside, and it cannot. Nor can it tell two identical backpacks apart if they are the same colour and size; what it compares is objects, never people. And whatever falls outside the frame — behind the counter, inside the indoor cash machine, the street — it does not report: those are other cameras. An honest camera is one that says where it stops.
Other cameras
- CAM-510 · The queue tells you how many desks you need at that hour
- CAM-511 · Five people waiting and a desk set up with nobody at it
- CAM-512 · Two people through the door on a single opening
- CAM-513 · A restricted door standing open and someone waiting outside
- CAM-514 · An operation that takes two people, and there is one in the room
- CAM-515 · Someone has been in the ATM lobby for twenty-two minutes
Simulation · how IRIS works
No extra alarms here. Just what needs looking at.
Not a recorded video, not an explanatory drawing: a summary of the real screen, with a different case every time it starts. There is a lot more behind it.
- Checks the whole system
- Flags what is failing
- Puts it on one screen
Next step
Public transport
Who watches a whole station at rush hour?
17 cases: 11 raise an alert when something happens and 6 only measure. You see each image as it is, and then with what IRIS understands on top.
Retail
Who sees the sales that never reach the till?
10 cases: 4 raise an alert when something happens and 6 only measure. You see each image as it is, and then with what IRIS understands on top.
And the best part
Adding a camera costs what it costs;adding someone to watch it costs every single month.
Past a certain number, almost nobody is watching anything. IRIS watches them all at once and only calls you when something you said mattered happens in one of them.
Tell us your problem and we will say whether IRIS understands it, or not yet.
We reply the same working day.