Use case · Security
Tailgating detection
Badge systems log one person per credential. Cameras can see when two walked through.
The problem
Why it keeps happening.
Every access-control system shares a blind spot: it authenticates credentials, not people. Tailgating quietly defeats the entire investment: one held door and the audit trail no longer reflects who is inside.
For data centres, pharma facilities, and controlled sites, an inaccurate presence record is itself a compliance finding, before anything goes wrong.
The rule
Written the way you'd say it.
“Alert security when two people pass an access point on a single credential.”Compile it in the Rule Playground
How it runs
- 01
Watch the entrances you already film
Doors, turnstiles, and vehicle gates with existing camera coverage connect directly: the same views your security team already reviews after incidents.
- 02
Count people per access event
Detection pairs each credential event with the number of people who actually passed, so two on one badge is flagged instantly. The room behind the door is a zone too: anyone inside outside permitted hours raises an alert.
- 03
Route by door criticality
A server-room door escalates to security immediately; a general office door may log and trend. Rules match the criticality your policy assigns.
- 04
Keep the record audit-ready
Every event carries a sealed clip tied to the access log: the evidence layer your presence records were missing.
Measure
What's measured.
- Tailgating events per door and hour
- People in and out per door and hour
- Out-of-hours presence per zone
What it’s worth
- Access-control investment made trustworthy end to end
- Presence records that survive an audit
- Insider-risk and theft reduction at controlled doors
- Fewer manual guard-hours watching entrances
Estimate your ROI for your own operation, in about two minutes.
Comply
The evidence.
- A clip and frame of the event, sealed with the device’s own key the moment it happens
- The rule that fired, the zone and camera, and the time
- The vision-language model’s verdict on the alert, with its reason
- Who saw it, who acted, and when, in the audit log

Where it applies
Related industries.
Common questions
Does it integrate with our badge system?
It works from the camera alone, and is more precise when paired with access events from your badge system.
Link to this questionWhat about legitimate escorted visitors?
The rule handles them: expected group entries can be allowed per door, per schedule or per visitor process, so alerts stay meaningful.
Link to this questionMore use cases
The use-case librarySecurity
Perimeter intrusion detection
Your fence line is already on camera. Make those cameras raise the alarm instead of just recording the break-in.
Safety
Forklift–pedestrian detection
The highest-severity risk in most warehouses and plants, watched continuously by the cameras already on the ceiling.
Safety
PPE detection
Helmets, vests, gloves, and eyewear verified continuously, not just when a supervisor happens to be looking.
See it on your own cameras.
A pilot on the cameras you already own, with success criteria agreed up front.
