Pilot
Vision picking on smart glasses
The glasses read a marker on the pick ticket, show what to pick and where, and the camera confirms the right item.
Cameras that check the work
A camera can check things a person is too busy to: the right item in the right tote, a label on a pallet, a set of product photos. We pilot vision systems on a small scale first and say honestly what’s ready for the whole warehouse floor.
What we’ve built
Pilot
Dock capture from wearables
Glasses photograph the paperwork and the loaded pallet, and the photos go straight into a live document-capture system, even when the network drops.
Demo
360° walk-arounds from photos
A set of still photos of a car, sorted, cleaned up and turned into a smooth walk-around video.
Demo
Product images with guard rails
Generated studio backgrounds for product photos, with a check that stops the model inventing a product that isn’t there.
Pilots and demos, honestly labelled
The smart-glasses picking and dock-capture apps are running as a pilot: in real use with a client, on a limited scale. The walk-around and product-image work are demos. A vision system across a whole warehouse floor needs the right lighting, testing and training time. We’ll scope that with you before you rely on it.
Pilot
Smart-glasses picking, in pilot
We built Android apps for display glasses and a picking server, and they’re now running as a pilot with a client, on a limited scale. The dock-loading app passed a 498-test gate first and sends its photos into a document-capture system.
How we’d test it on your floor
A pass mark agreed first
Before a pilot starts, we agree a set of your real examples and a pass mark. It has to meet it before it goes live.
One station before a roll-out
We start with a short pilot on one station, measure it, and only then talk about a roll-out.
Guard rails on generated images
A check stops the model inventing a product that isn’t there.
You choose where the AI runs
Tier 1
A hosted model, through a UK or EU endpoint
The best quality for the least effort. Before any of your data goes to a provider, we check that its business terms rule out training on it, and we tell you which region does the processing.
Tier 2
Inside your own cloud account
The model runs in your AWS or Azure account, under your access controls and your logs.
Tier 3
A private model on hardware in the UK
Open-weight models on your hardware or ours. Nothing goes to an outside AI provider. Our own research and document reading run this way.
Storage location and processing location aren’t the same thing. We’ll tell you both, in writing.
Questions
Can you put this in our warehouse?
Possibly. We start with a short pilot on one station, measure it, and only then talk about a roll-out.
Which glasses or cameras?
We pick hardware for the job and avoid locking you in. The software is ours to build; the hardware choice is yours.
Get in touch
Tell us what you’d like a camera to check.
One paragraph is enough. We’ll reply with honest thoughts on whether we can help, and what it would cost.