Entrusit case study · RestaurantsVision-based portion & quality control at the kitchen pass
A camera checks each plate against the reference dish before it leaves the kitchen.
The problem
Restaurant groups can't see whether plates match the spec — portion size and presentation drift between shifts and locations, and food cost drifts with them.
What we built
A proof of concept that scans each dish with a depth camera and a vision model, compares it with a reference plate and logs the result to a dashboard per restaurant and dish.
How it works
- 1Define the reference plate for each dish.
- 2A depth camera captures each plate at the pass.
- 3A vision model compares composition and portion against the reference.
- 4Results are logged per dish, shift and location.
Highlights
- Proof of concept stage
- Works per dish and per location
- Hardware + software, end to end
Stack & integrations
- Python / FastAPI
- Depth camera (OAK)
- OpenCV
- Claude vision
- SQLite
Security & your data
How we handle your data
- NDA before the first call
- Least privilege, read-only by default
- Humans approve sensitive actions
- You own the code and the data
- Your accounts and infrastructure
- GDPR and Macedonian data protection law
Entrusit · info@entrusit.com · +389 77 761 248 · entrusit.com
https://entrusit.com/work/vision-portion-control/
Related projects
- ProductSmart Scan — AI document processing into the ERPSupplier invoices, receipts and bank statements read, checked and posted — no re-keying.Read the case →
- ProductAsk Your Finances — an AI agent over your booksChat with your bank statements, purchases, expenses and sales — and get told what doesn't reconcile.Read the case →
- ProductSmart Product Import — messy supplier sheets to a clean catalogueAn Excel file and a folder of photos in; grouped, enriched, shop-ready products out.Read the case →
Project 16 of 16
Want something like this?
Tell us about your version. The first 30-minute process teardown is free, and we'll sign an NDA before it.