Industries Local councils and government
Proof that public works were done right, without an inspector on every job.
Councils pay contractors for thousands of small jobs a year: footpaths, signs, parks, drains. Each one closes with a photo. Sight checks the photo.
Crack- Photo sharp enough to assess Pass · Yes
- Surface free of cracks Fail · 1 found
- Check
- Surface free of cracks
- Why
- One crack, traced end to end
- Then
- Raise a defect on this job
A stock photo. The boxes are real labels drawn in Sight; the checks shown are an example.
What Sight checks for councils and government.
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.
Contractor work verified before payment
Each job type lists what its completion photos must show. Sight checks every job against that list, so an invoice is paid on evidence.
Defects found in inspection photos
A model trained on your own photos of cracked paths, damaged signs or blocked drains finds them and marks where they are.
Counts from aerial photos
Vehicles, people and assets are counted in drone and aerial photos uploaded in bulk.
A record you can audit
Every answer keeps the photo it came from, the rule that was applied and the reason. Checks are versioned, so last year’s job can be explained by last year’s rule.
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.
Vehicle Vehicle Vehicles and people from the air
Person Person People on a works site
Sight runs in production on telecommunications install photos. For a council the first step is a trial model on your own works photos. Where each part of Sight runs is set out on the sovereign AI page.
- 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 the photos from one works program.
An engineer will tell you what Sight can check in them, and where its AI would run.