Industries Construction and infrastructure
Site photos that prove the work, checked the day they are taken.
Hold points, safety walks and defect inspections all end in photos. Sight checks them as they arrive, so a problem surfaces on the day, not at handover.
Hi-vis Hi-vis Hard hat Hard hat- Hard hat on every worker Pass · 2 of 2
- Hi-vis on every worker Pass · 2 of 2
- Edge protection in place Needs a person · Out of frame
- Check
- PPE on every worker
- Why
- 2 hard hats, 2 hi-vis found
A stock photo. The boxes are real labels drawn in Sight; the checks shown are an example.
What Sight checks in construction.
Each check is a rule written with you and trained on your own photos. Every answer comes back as pass, fail or needs a person, with the photo and the reason.
Safety gear on every worker
Hard hats and hi-vis are found on each person in each site photo, and a worker without them is flagged with the photo.
Defects found and traced
A model trained on your own photos of your own defects, such as cracks, honeycombing or damaged finishes, finds them in inspection photos and marks where they are.
Hold-point evidence complete
Each hold point lists the photos it needs and what must be visible in them. Sight checks they are all there before the pour, the cover-up or the sign-off.
What is on site
Plant, vehicles and people are picked out of drone and site photos, so the daily record does not depend on someone walking the site.
A hint while the crew is still there Rolling out
When a photo is missing or unclear, the person who took it is told what to retake before they leave, not after the job bounces.
The same eye, on every kind of photo.
Person Person People on a deck before a pour
CrackA crack, traced end to end
Vehicle Vehicle Plant on site
Sight runs in production on telecommunications install photos. On a construction project the first step is a trial model on your own site photos, scored on photos it has never seen.
- 01
Label
We label your photos, with your people confirming what counts as right.
- 02
Train
We train and tune a model on them, and score it on photos it has never seen.
- 03
Set up checks
We write each check with you: what must be in the photo, and what passes.
- 04
Connect
We connect Sight to the app your crews already use and the systems behind it.
- 05
Stay
We keep running it, and retrain it as your reviewers correct it.
You hire no machine learning team and buy no infrastructure. How we deliver
Bring the photos from one project.
Hold points, safety walks, defects: whatever your teams already photograph. An engineer will tell you what Sight can check in them.