How do I tell it what I need?
Tell IRIS what matters to you.
You write, in your own words, the situation you want watched, and you watch IRIS turn it into a rule.
How it works inside
From a sentence to an alert. Six steps, and you take none of them.
You write what you need the way you would say it to a colleague. From there you do nothing else.
What you write
«Tell me if someone leaves a suitcase on the platform for more than two minutes.»
You ask in your own words
In your own language, with nothing to learn. There are no menus with fifty checkboxes and no programmer to call to set it up.
IRIS turns it into a rule
It breaks the sentence into parts: what object, in which zone, for how long and what to do about it. It shows you the rule in writing so you can confirm it before anything starts running.
The rule is installed and starts running
It stops being a written sentence and becomes a task already running on a computer. If the deployment is on-site, that computer is in your own building: the sentence never leaves it and no internet is needed.
Every camera applies it at once
You do not repeat the request camera by camera. You choose where it applies: one camera, a whole platform, or every camera in the city. And it works at three in the morning the same as at noon.
The result comes back
An alert with the camera, the time and the clip, on screen or on the phone of whoever needs to see it. Or a number, if what you asked for was to measure rather than watch.
And you change it whenever you want
If it alerts too much or falls short, you change the sentence and it is published again. No code, no support ticket, no waiting for anyone to come out.
What you get back
Platform 2 · 03:14 · unattended suitcase, 2 min 40 s · clip attached
The shift supervisor knows exactly what they want watched. What they cannot do is set it up. Video analytics are tuned in a panel of thresholds, masks and parameters that only the installer understands, so every small change turns into an email, a ticket and a wait. In the end nobody changes anything, and the system carries on alerting about what mattered two years ago.
With IRIS you start from the sentence. You write what you want the way you would say it to a colleague: ‘Tell me if a lorry has been at the dock for more than twenty minutes with no loading activity.’ There is no need to translate it into technical language before you can try it, and no need to call anyone.
IRIS breaks that sentence into pieces and shows them to you before anything is switched on: which object to watch, in which zone, in what situation, for how long and what to do when it happens. You can correct any of them — raise the time, move the zone, change who gets alerted — and test it again against real footage. What gets saved is not a loose sentence: it is a specific rule that can be read, argued over and audited.
And a sentence does not create capabilities the camera does not have. If the framing cannot make out a helmet, writing ‘tell me if someone is not wearing a helmet’ will not fix it, and the test on real footage will say so straight away. Sometimes the result of that test is ‘this camera is not suited to this’ — and it is better to learn that on day one than on the day of the incident.
Who writes the rule?
The person who knows the operation writes it: the shift supervisor, the safety officer, the control room operator. Nobody has to open a ticket to raise a threshold by two minutes.
What do I see before it runs?
The sentence broken down into object, zone, condition, time and action, written on screen. If any piece is not what you meant, it is corrected right there, before anything starts alerting.
How do I know it works?
Because the rule is tested against real footage from that camera before it is put to work. You adjust the time or the zone until it alerts when it should and stays quiet when it should not.
And if it changes tomorrow?
You change the sentence and it is published again. Roadworks, a campaign or a new timetable do not mean waiting for the integrator's next visit. Decide once; IRIS applies it every time.
Do I need to know how to code to configure IRIS?
No. Rules are described in ordinary sentences — what to watch, where, for how long and what to do — and IRIS shows how it has read each part before switching it on. The technical team is still needed for commissioning and integrations, but not for changing a threshold.
Does IRIS detect anything I ask it to?
No. Some situations a given camera cannot resolve because of its position, image quality or lighting, and some details are too small or too far away for any camera at that framing. The way to find out is not to argue about it: it is to test the description on that camera's real footage and look at the result before counting on it.
Can I use natural language to search the recordings?
Yes. Besides defining rules for the future, you can describe something that already happened — ‘white van parked for more than ten minutes at dock 4’ — and IRIS returns the candidates with their camera, time and image. Stop looking for the minute; look for what happened.
Does it cost me anything to try phrasings until I get it right?
It costs nothing. IRIS does not charge per query: there is no meter on phrasings, searches or trials. Write a rule, test it against video from that camera, change it and test it again as many times as you need; one trial and a million trials cost the same. That is deliberate, because a sentence gets sharpened by trying it, and a system that charges per attempt ends up with rules written in one go and written badly.
Talking and drawing
Asking is how you search. Counting is how you measure.
To find something, you ask for it in words. “Show me yesterday afternoon's red motorbikes.” “Find someone without a helmet.” IRIS searches and shows you what it found. That is searching, and searching is done by talking.
Counting is a different thing. To know how many bicycles go down a street, you have to say where the counting happens: you draw a line on the image, and everything that crosses it adds up. To know how many people are in a square and how long they stay, you paint a zone and measure who is inside. A line cannot be described in a sentence. It has to be drawn.
This is not a limitation: it is what makes the number worth having. The line is always in the same place, so today's figure can be compared with last month's. If a slightly different sentence did the counting every day, the numbers would not match each other and no decision could rest on them.
And it can be shown. Anyone can see where the line is and why the figure came out that way; a number you cannot explain is a number you cannot defend in a council meeting or a board meeting. That is why our people counting is certified by Spain's Metrology Centre: what gets certified is a measurement, not a conversation. It is the guarantee that the attendance figure you show is the right one, because the one who checked it is a third party and not us. The certification covers that counting, not the whole product.
To search, talk
Describe in your own words what you are looking for, and IRIS takes you to the candidates. No odd query language to learn, nothing to set up first.
To count, draw
A line for what goes past. A zone for what stays. You draw it once on the camera image, and from then on it counts by itself.
Why the difference matters
Same place, same line, same criterion every day. That is how today's number can be compared with yesterday's, and how you can always show where it came from.
Both at once
One camera can have counters running all day and, on top of that, a rule written in words: “tell me if someone is not wearing a helmet”. You do not have to choose.
The real interface, step by step
You set the rule once. IRIS applies it every time.
You will see a summary of the interface, played step by step and hands-free. Each round starts with another case. The complete tool does not fit in a demo.
- The rule gets built
- It goes to every camera
- Published, it watches alone
- And then it fires
Next step
How long before somebody comes down that corridor at four in the morning?
13 cases: 12 raise an alert when something happens and 1 only measure. You see each image as it is, and then with what IRIS understands on top.
Who sees the child who has fallen at the far end of the playground?
13 cases: 12 raise an alert when something happens and 1 only measure. You see each image as it is, and then with what IRIS understands on top.
And the best part
Ten cameras or four thousand:not one of them goes unwatched.
The day IRIS starts, they all start: the ten in a school or the four thousand in a whole network. And it only raises its hand when the thing you asked for happens.
Tell us your problem and we will say whether IRIS understands it, or not yet.
We reply the same working day.