Cargonaut

From a cloud solution to critical infrastructure in the logistics ecosystem

Cloud logistics automation at Schiphol Airport

In this second phase, Cargonaut and Incentro consolidated the platform as an operational standard within Schiphol’s logistics ecosystem. More automation without compromising accuracy, improved data quality at the source, and integration into critical processes. Today, the system optimizes shipment assignment and makes real-time decisions as part of the airport’s day-to-day operations.

After the initial implementation, the next challenge was no longer about further developing the technology, but about scaling the solution within a complex logistics ecosystem with multiple stakeholders and interconnected systems.

80% PLUS AUTOMATED ASSIGNMENT · 80% PLUS AUTOMATED ASSIGNMENT · 80% PLUS AUTOMATED ASSIGNMENT · 80% PLUS AUTOMATED ASSIGNMENT · 80% PLUS AUTOMATED ASSIGNMENT ·

Results

The evolution of the system has strengthened and expanded the initial outcomes:

80% plus with peaks of shipments assigned automatically
99% of ecosystem agents integrated into the platform
Significant reduction in errors and rework
Integration with key systems such as Secure Import

This level of adoption has turned the solution into an essential component of daily operations.

How has the solution evolved?

1. Data model improvement

Efforts focused on improving data quality to enhance system performance:

Correction of inconsistencies at the source
Increased data volume
Alignment across systems and stakeholders

Data quality makes the difference: it enables the model to automatically determine the correct agent and automate assignment.

The result: more accurate decisions without adding operational complexity.

2. Scaling the automation model

The system evolved by incorporating improvements in:

Data processing and cleansing
More advanced machine learning models
Identification of complex patterns and edge cases

The goal: exceed 90% automation while maintaining quality.
This is where the real shift happens: the system moves away from fixed rules and starts learning from data through machine learning models. Assignment is automatically adjusted in each case, even when information is variable or incomplete.

The system not only automates the process, but also learns and continuously improves assignment accuracy.

3. Ecosystem adoption

One of the main challenges was achieving adoption across all stakeholders:

Reducing friction in usage
Improving incident management
Aligning processes across participants

The solution evolved from an operational improvement into a system embedded in daily operations, capable of coordinating stakeholders and processes autonomously.

Automation alone was not enough.
The system had to be reliable enough for people to stop intervening.

Impact on the ecosystem

The solution has evolved into a key component within the airport’s technology landscape:

Anticipates assignment before shipments arrive
Reduces reliance on manual processes
Improves coordination between stakeholders
Serves as a foundation for other critical security and control systems

This has enabled Cargonaut to strengthen the overall efficiency of the logistics ecosystem.

All of this is supported by an infrastructure designed to work with real-time data and integrate AI models directly into daily operations.
It is part of the system itself, not an additional layer.

Assignment no longer depends on manual rules and is instead resolved automatically in each operation, improving the overall efficiency of the logistics ecosystem