Industries Utilities
Network assets inspected from the photos your crews already take.
Poles, lines, pits and substations are photographed on every job and every patrol. Sight finds the hardware in each photo and checks the work around it.
Hard hat Hard hat- Hard hat on every worker Pass · 2 of 2
- Truck in the photo Pass · Found
- Pole number readable Needs a person · Not in this photo
- Check
- Hard hat on every worker
- Why
- 2 workers, 2 hard hats found
A stock photo. The boxes are real labels drawn in Sight; the checks shown are an example.
What Sight checks in utilities.
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.
Hardware located, however small
Insulators, cross-arms, fuses and fittings are found in each photo, even when they are small and far away, ready for a condition check or a count.
Completed work verified
Each job type lists what its photos must show. Sight checks every job against that list, the same way for every crew and every contractor.
Asset numbers read
Pole and asset numbers are read from the photo and compared with the job, so work is recorded against the right asset.
Crew safety
Hard hats and hi-vis are checked on every worker in every job photo.
Wildlife on the network
Birds and nests on poles and lines are counted from patrol photos, with a model trained on your own network.
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.
Insulator Insulator Insulators on a pole
Insulator Insulator Fifteen insulators, small and far away
Bird Birds on the lines, counted
Sight runs in production on telecommunications install photos, which are close cousins of utility work: small hardware, outdoors, photographed by a crew in a hurry. A utility deployment starts with a trial model on your own photos.
- 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 · Where Sight’s AI runs
Bring a patrol’s worth of photos.
An engineer will tell you which hardware Sight can find in them, what it can check, and what it would need to learn.