VRTLST Edge v2 ships with on-device inference at 38 ms

Read more

VRTLST Guard

Every zone watched. Every rule enforced.

The rules you already have — PPE on the floor, nobody inside the robot envelope, fire lanes clear, no tailgating at the gate — enforced continuously instead of audited quarterly. Guard watches the boundary on every shift and can act on what it sees.

ZONE BREACH CELL 12 · ROBOT ENVELOPE e-stop sent
person in zone
09:41:02 Missing hi-vis · Dock 3 warning
09:38:55 Tailgate at Gate A warning
09:31:10 Fire lane obstructed cleared

What it does

Factory security & safety

01

Zones you draw yourself

Sketch a boundary directly on the camera feed and pick a rule. No integrator visit, no re-survey when the cell moves.

02

It acts, not just alerts

Trigger a hardware e-stop, lock a door, sound a local horn, or page the shift lead. The response is part of the rule.

03

Privacy by default

Faces are blurred at the point of capture. Guard has no identity matching and no biometric database — it produces evidence, not surveillance.

How it works

From a camera to a decision

Draw a boundary once. Guard enforces it on every shift, on every camera, without a human staring at a wall of screens.

  • PPE, exclusion zones, tailgating, fire-lane obstruction
  • Hardware e-stop and access-control integrations
  • Faces blurred on capture — evidence without surveillance
Book a demo
Draw the zone
Outline the robot envelope, the fire lane or the gate approach on the live feed.
Choose the rule
Exclusion, PPE compliance, tailgating, obstruction, or a dwell-time limit.
Pick the response
From a silent log entry through to an e-stop on the cell — graded by severity.
Review the event log
Every trigger keeps its clip, its zone and its outcome for the incident review.
24/7 enforcement, every shift
<1 s breach to alert
0 biometric records stored
6 rule types out of the box

Specifications

The technical detail

What your integrator will ask for on the first call.

Rules
exclusion · PPE · tailgating · obstruction · dwell
Breach to alert
<1 s
Responses
log · notify · horn · door lock · hardware e-stop
Privacy
faces blurred at capture, no biometric index
Evidence
clip + zone + outcome per trigger
Coverage
unlimited zones per camera

Getting started

How a Guard deployment goes

The same shape every time, whichever product you start with.

  1. Week 0

    One hour of footage

    Send us recorded video from a single line. We come back with what the model found in it — before anyone signs anything.

  2. Week 1–2

    One line, one model

    We stand up a pilot on the line that hurts most, using the cameras already mounted. Operators start correcting it on day one.

  3. Week 3–4

    Wired into the line

    The verdict moves from a dashboard to the PLC, the MES or the alerting channel your shift leads actually watch.

  4. Month 2

    Second line, second site

    The model and its thresholds travel. Command stages the rollout so a bad version never reaches more than one line.

  5. Ongoing

    It gets better

    Corrections accumulate, drift gets flagged, and new defect classes are a fine-tune rather than a project.

Questions

What people ask about Guard

Something not covered? Talk to an engineer.

Is this employee surveillance?

No, and it is built so it cannot become that. Faces are blurred before a frame is written anywhere and there is no identity matching, so Guard can tell you a person entered a zone but never which person.

Will it stop the line constantly?

Only if you configure it to. Responses are graded — most rules start as a silent log entry, and an e-stop is something you deliberately opt into for a specific zone.

Do the works council or unions need to be involved?

In most jurisdictions yes, and we would encourage it regardless. The privacy architecture is usually what makes that conversation straightforward.

What happens when the cell layout changes?

You redraw the zone on the feed. It takes a minute and needs no integrator visit or re-survey.

Keep exploring

The rest of the stack

See the whole platform
Watch

Know what's happening the moment it happens

Continuous monitoring across every line and every site, with alerts that reach the right person in seconds.

Explore Watch
Edge

The camera that thinks for itself

A sealed edge-AI device that runs the full VRTLST stack on-board. Single PoE cable in. Decisions out.

Explore Edge
Command

Every camera, every site, one screen

The control plane for your whole visual estate — deployments, model versions, alerts, access and audit.

Explore Command

Get started

Point it at a camera. See what it sees.

Send us one hour of footage from one line. We'll come back with what the model found in it.