Case Studies / Security
Security · Machine LearningA code format QR can't counterfeit — from patent filing to three production apps.
GoHexana's patented hexagonal secure codes, engineered into production: on-device ML decoding that works offline.
3
Production apps
Patented
Technology
Offline
Decoding
The ClientGoHexana, Saudi Arabia — inventor of a patented hexagonal-pattern alternative to QR and barcodes.
01
The Challenge
QR codes are easy to spoof and limited in capacity. The patented format needed production-grade engineering.
✕Frame drops and decoder failures in early builds
✕ML model too heavy for low-end phones
✕No scalable path to decoder-as-a-service
02
What We Built
The full encode/decode product line — mobile apps, web portal, and service APIs.
✓Mobile encoder/decoder apps with on-device TensorFlow models
✓Web portal encoder with code lifecycle management (enable/disable)
✓Optimized ML pipeline for low-end device support
✓Decoder-as-a-service architecture on Kubernetes
03
The Stack
TensorFlowOpenCVFlutterReactFastAPIMongoDBKubernetesJenkins CI/CD
04
The Results
Numbers from production operation — not projections.
70%
Decoder success rate in Phase 1
3
Production apps shipped
1
Patented innovation industrialized
I have obtained IP for the innovation that I applied for 4 years ago... Today I am happy that the work is achieving good results.Majid Badr AlqarniFounder, GoHexana
MORE
Related case studies
Automotive · Fortune 500
One bad test change can stop a production line. This supplier made that impossible.
Up to 50% Less downtime · 100+ Machines governedTelecom · SD-WAN & SASEEvery SD-WAN vendor built a walled garden. We gave one MSP a single gate.
40% Less training time · 20% Faster deploymentsInsurance · MainframeThe 6-hour mainframe job that now finishes in under two.
70% Faster processing · 40% Lower MIPSYour platform next
Building something this hard?
Tell us what you're building. A senior engineer — not a sales rep — replies within one business day.
Talk to the architects→