Pluginv0.0.70

Vosíme Pizza Checker

Client: Vosíme

📷

Custom PiPoeCam units

Hardware

🤖

Real-time ML quality check

Evaluation

🗺️

Multi-location dashboard

Coverage

🔁

Automated on failure

Claims

The challenge

Vosíme operates multiple delivery kitchen locations producing high pizza volume. Manual quality checks were inconsistent - pass/fail decisions depended on individual staff judgment and varied by shift. Failed pizzas that slipped through led to customer complaints and costly re-orders. There was no systematic record of quality events per order or per location.

Our solution

We designed and deployed a complete end-to-end system. Hardware: custom PiPoeCam units (Raspberry Pi + PoE camera) running PiPoeCam OS - a minimal custom Linux image with WiFi config and tools for stable reusable deployment - installed above each oven. Software: a Python backend (v0.0.70) that receives images, runs ML quality evaluation, stores results, and publishes events. A React/TypeScript admin dashboard (Vosíme Admin) gives the ops team a live view: order tracking with status columns, quality stats per location, AG Grid order tables with image zoom, Leaflet multi-location store map, and automated claim triggers for failed evaluations. CI/CD via GitHub Actions, deployed to Kubernetes via Helm charts.

Result

Quality checks are now fully automated and consistent across all shifts and locations. Every pizza has an attached quality record. Failed checks trigger automated claim workflows. The operations team has a unified dashboard across all locations for the first time. System reached v0.0.70 in active production.