###Inspiration
The growing demand for ULD tracking and real-time intelligence in the air cargo industry inspired us to develop a purpose-built solution designed around the needs of our customers. While existing ULD tracking solutions remain prohibitively expensive, we took a different approach: designing and building our own hardware device from the ground up.
Our proprietary device integrates a comprehensive range of environmental sensors, including temperature, humidity, light intensity, and vibration, enabling continuous, end-to-end monitoring of cargo conditions. To ensure seamless connectivity and real-time data transmission, the device incorporates Bluetooth, Wi-Fi, and GPS, creating a fully connected intelligence ecosystem that delivers actionable insights throughout the entire shipment journey.
To bring this vision to life, we developed 3 MVPs, 1 POC, and 1R integration:
1>Cargo On Chip:** ULD Tracking Device 2>Cargo Neo Cortex:** Intelligence Platform 3>Cargo Perceptron:** In-house Language Model 4>Cargo Widget:** RAG-based BI Agent 5>ONE Record Connection:** Integration using the ONE Record IoT data model
What They Do
Cargo On Chip: Cargo On Chip is a compact, sensor-rich hardware device designed to continuously collect and store data every second throughout the shipment journey. Whenever it connects to a Wi-Fi or Bluetooth base station, the device automatically transmits its stored data in real time, providing complete end-to-end visibility from origin to destination.
Cargo Neo Cortex: Cargo Neo Cortex is a unified intelligence and analytics platform that brings essential customer information into a single view. In addition to ULD tracking and Cargo iQ milestone data, the platform provides visibility into commercial and operational activities, including offload events, claims, and shipment performance. It is also powered by Cargo Wizard, an embedded AI assistant that enables customers to easily navigate their data and retrieve relevant insights.
Cargo Perceptron: Cargo Perceptron is a proprietary large language model purpose-built around deep air cargo domain knowledge. It acts as the cognitive engine of our intelligent ecosystem, understanding industry-specific terminology, processes, and data to provide highly accurate and contextual responses.
Cargo Widget: Cargo Widget is an AI-powered BI agent built on the Cargo Perceptron model using a Retrieval-Augmented Generation (RAG) framework. Cargo Wizard can generate precise, context-aware responses to user queries in under 0.6 seconds, transforming the way customers interact with and understand their cargo data.
ONE Record Connection: We use the ONE Record IoT data model to store sensor readings in a standardized and structured format. This data powers the Cargo Neo Cortex dashboard, which also integrates the Cargo iQ route map to provide end-to-end shipment visibility.
When airline staff perform shipment acceptance through the Shipment Workspace, the system can trigger the Cargo iQ SAC milestone and publish the event to the agent system. If an issue is identified during acceptance, users can raise a Verification Request directly to the agent. With ONE Record publish-subscribe functionality enabled, subscribed GHAs are automatically notified whenever a Verification Request is pending.
How We Built It
Our solution is the result of a multidisciplinary engineering effort that combines hardware engineering, software development, AI, analytics, and industry-standard data integration.
Hardware Engineering
We designed and developed every layer of the physical device from the ground up, including circuit design, board layout, microcontroller programming, and sensor integration. The result is a compact, sensor-rich device supporting multiple communication protocols, including Bluetooth, Wi-Fi, and GPS, within a single purpose-built form factor.
Software Engineering
Our software ecosystem spans three operating systems—Windows, Linux, and macOS—providing cross-platform compatibility and flexibility. We leverage a diverse technology stack across multiple layers:
- C++ — Low-level microcontroller and embedded systems programming
- Python — Data processing, analytics, and AI/ML model development
- Java — Backend services and system integration
- HTML, CSS & JavaScript — Responsive and intuitive frontend interfaces and dashboards
This combination of hardware engineering and full-stack software development enables us to build, own, and operate the complete solution in-house. It reduces vendor dependency while allowing us to move faster and maintain greater control over innovation.
Challenges We Ran Into
Building an end-to-end hardware and software ecosystem required extensive iteration. Our code was rewritten and rerun hundreds of times, with each iteration presenting new obstacles, errors, and bugs.
One of our major challenges was transforming sensor- and device-generated data into the IATA ONE Record format. Successfully overcoming this challenge allowed us to connect our device-generated data with the broader digital cargo ecosystem.
Accomplishments We’re Proud Of
Our solution represents significant potential value for airlines seeking operational excellence and improved customer service, while being delivered at a fraction of the cost of existing alternatives.
We are addressing one of the industry's most recognized challenges: the lack of affordable and scalable ULD tracking. By designing and developing our own hardware device at significantly lower cost, we aim to remove the barriers that have traditionally prevented airlines from extending real-time monitoring to a broader range of shipments.
Most importantly, our solution helps democratize cargo visibility. Airlines can extend premium-grade monitoring capabilities to every customer shipment rather than limiting them to high-value or special cargo.
For the first time, passive pallets can be tracked and monitored with the same level of intelligence as active containers, helping close the existing visibility gap and establish a new standard for customer service in air cargo.
What We Learned
This project has been a transformative learning experience for our team. It pushed us beyond our usual areas of expertise and required us to work across hardware, software, AI, data standards, and industry-specific workflows.
Through the end-to-end development process, we gained hands-on experience in several areas:
- Multi-language software development — Building proficiency across C++, Python, Java, and web technologies to create a complete full-stack ecosystem
- Large Language Model (LLM) training — Learning how to build, fine-tune, and deploy a domain-specific language model from the ground up
- Hardware engineering — Developing practical expertise in circuit design, sensor integration, microcontroller programming, and embedded systems
- IATA ONE Record (1R) integration — Understanding and implementing the industry's next-generation data-sharing standard and connecting our solution to the wider digital cargo ecosystem
More than any individual technical skill, the project demonstrated the value of cross-disciplinary collaboration. It showed us that when curiosity, engineering, and determination come together, a small team can build solutions capable of competing with established industry technologies.
What Is Next
With a working prototype and a proven intelligence ecosystem in place, our next goal is to transition from innovation to real-world impact.
1. Pilot & Validate
Launch a controlled pilot program on selected routes to evaluate the device under real-world operating conditions. This will allow us to validate sensor accuracy, connectivity reliability, and data transmission throughout the complete shipment lifecycle.
2. Aviation Certification & Compliance
Pursue the necessary regulatory approvals and aviation safety certifications required to ensure that the device complies with aviation standards and can be deployed commercially at scale.
3. Scale Production
Transition the prototype into mass production by optimizing the hardware design for manufacturability, cost efficiency, and durability, enabling deployment across the entire ULD fleet.
4. Customer Integration & Onboarding
Open Cargo Neo Cortex to customers and provide self-service access to real-time tracking, analytics, and AI-powered insights through Cargo Wizard.
We also plan to introduce APIs or gateways within the Cargo Neo Cortex platform, allowing customers to retrieve data, upload their own data, build their own intelligence solutions, and integrate the platform with their existing data infrastructure.
5. Evolve the Intelligence Layer
Continue training and enhancing Cargo Perceptron with richer domain-specific data while expanding Cargo Wizard's capabilities.
Future capabilities will include:
- Predictive alerts
- Anomaly detection
- Automated exception handling
6. Industry Collaboration & Standardisation
Deepen our integration with IATA ONE Record and explore collaboration with airlines, ground handlers, and freight forwarders.
Our goal is to establish an open and interoperable platform that can elevate digital cargo operations across the industry.
7. Commercialisation
Explore opportunities to commercialize the platform by offering ULD tracking and intelligence as a value-added service to customers. We also plan to explore licensing the technology to other carriers seeking affordable, scalable, and intelligent cargo visibility.
Log in or sign up for Devpost to join the conversation.