Architecture
Systems architecture, end to end
We design cyber-physical systems as a whole: devices on the assets, edge computing at the operation, a fog layer for the port, and cloud platforms above — with AI placed in every layer where a decision has to be made.
Layer 02
Edge
Compute where the work happens. Operators use HMI monitors that run models locally — querying thousands of containers and bulk trailers without waiting on the cloud.
Hardware & software
- Edge gateways
- HMI monitor devices
- Local language-model terminals
- Vision nodes
AI in this layer
- Real-time inference
- Local LLMs in the HMI
- Computer vision
Connected through IoT and industrial protocols
New devices and existing systems in one data flow — terminal operating systems, ERPs and document systems integrated through standard APIs.
Hardware we design for the system
The edge HMI monitor, BI dashboards, endpoint trackers and the platform behind them — each one a part of the architecture.

Edge layer
HMI monitor — Port twin
Touch monitor for the operation: live map, equipment health, dashboards and 3D view of the port.

Cloud layer
BI dashboards
Throughput, capacity, trends and forecasts for the strategic level — fed by every layer below.
Container Tracker
The endpoint device on each container: position and condition reported for years into the rest of the system.
- Layer
- Endpoint
- Power
- 12,000 mAh · 2 to 5 years
- Sensing
- Position, temperature, humidity, motion · IP67
- Network
- LTE / 4G / 2G · Bluetooth


Smart Container Tracker
The same endpoint with an AI model on board: it decides what happened to the cargo locally and sends only what matters up the architecture.
- Layer
- Endpoint · AI on the device
- Recognises
- Handling gestures, shocks, shipping quality
- Senses
- Air quality, temperature, humidity
- Sends
- Only meaningful events — to the edge and up
IoT platform & BI
End-to-end Internet of Things: the sensor board, the firmware, the network link and the Q-660 platform behind it — tracking, history, zones and an API to build on, delivered as SaaS or PaaS.
- Tracking
- Real-time position and condition
- History
- Track playback
- Zones
- Geofencing management
- Access
- Secured authentication
- Integration
- Complete API documentation
- Delivery
- SaaS or PaaS · custom hardware on request



From architecture to operation
- 01
Architecture
Assess the operation, define the layers, data flows and where AI belongs.
- 02
Design
Hardware, firmware, models and platforms designed together.
- 03
Build
Devices, edge software, twin and models built and tested on site.
- 04
Integrate
Connected to existing terminal, ERP and document systems through standard APIs.
- 05
Operate
Monitoring, retraining and support after go-live.