A Dutch infrastructure enterprise receives dozens of weigh tickets daily, delivered both in paper format and digitally.
Paper slips were manually transcribed by site supervisors into the loading register and linked to the corresponding transport run within the fleet administration system.
Digital slips originate from various weighbridge systems. Site supervisors merged this data and exported it to both the loading register and fleet administration. Because these source systems provide data in inconsistent formats, exports frequently required manual formatting prior to processing.
This constituted low-value manual labor. Furthermore, errors occurred with regular frequency on both paper and digital slips, such as incomplete license plates, net weight exceeding gross weight, or exit timestamps recorded prior to entry timestamps. Due to the sheer volume of slips, these discrepancies often went unnoticed, compromising the accuracy and completeness of the loading register.
On paper
From different weighbridge source systems
| Reg. no. | Net (t) |
|---|---|
| 12-BXR-4 | 23,46 |
We developed an AI agent that consolidates, validates, and directly processes all weigh tickets into the loading register and the fleet administration system.
The AI agent ingests paper slips and digital data streams from the weighbridge systems, regardless of origin or layout.
All extracted information is converted into a uniform layout, ensuring consistent recording for every transaction.
Weight, transport run details, and material types are cross-checked against project expectations. The slip is then matched to the transport run in fleet administration and the loading register is updated.
Registration
Of weigh tickets are processed without human intervention, directly into the loading register and fleet administration.
One day as an example
48 weigh tickets
Site supervisors regain valuable time to operate on-site and actively guide project operations.
Every organisation works with AI, but everyone does it differently.
This case shows which phases of the Disruptiv framework another organisation went through. The assessment does the same for yours: you will not only see your score, but also which phase currently limits your progress and what needs to be done first.
Planning five years of soil logistics by hand was no longer manageable. An AI model now calculates every variant and picks the lowest-cost route.
Read case →Residents waited five working days for an answer. An AI assistant now drafts replies, but a staff member always checks and sends them.
Read case →Staff were already using AI widely, but without any agreements. In ten weeks all usage was mapped, a workable policy adopted and a secure environment put in place.
Read case →