Drivers send photos of CMR and declarations through Viber or Teams, and logistics checks them by eye and attaches them to the trip in CargoWise by hand. AI recognises the document, matches it against the trip in CargoWise and the Teltonika telematics data, flags mismatches for logistics and attaches clean documents.
Built for ISO 27001NIS2 DORA
A trip ends not when the cargo is unloaded but when the documents are back at the office. The driver photographs the signed CMR, delivery note or T1 declaration and sends it through Viber, Teams or email. The photos are tilted, part of the stamp is cut off, and dozens arrive on the same day. Logistics has to identify which trip in CargoWise the document belongs to, check that the consignee, weight and date match the order and that the consignee's signature and stamp are present, and only then attach it to the trip. Until that is done the invoice in SAP Business One is not issued, and if a mismatch is noticed a week later, the dispute with the customer has already started.
The solution takes photos from agreed channels, Teams, email or the drivers' app, and recognises each document: it determines the type and reads the sender, consignee, cargo description, weight, dates, and the signature and stamp fields. By order number, number plate or date the document is linked to a trip in CargoWise, and the unloading date and place are additionally checked against a Teltonika telematics record, if you have one. If everything matches, the document is attached to the trip in CargoWise and the trip is marked as ready for invoicing, which the accountant issues in SAP Business One in the usual way. If the weight, consignee or date differs, or a signature is missing, logistics gets a message in Teams with the specific mismatch and decides what to do. We recognise the text in the photos with Azure AI Document Intelligence in an EU region or with private AI in our GPU cloud in Lithuania (EU), Claude through Amazon Bedrock in an EU region matches the fields, and we integrate with CargoWise through an API, a file export or an email flow, depending on the version. The original documents stay in your CargoWise and SharePoint and are not used for model training.
Four steps from input to a record in your system, with human approval wherever there is risk.
The driver photographs the signed document and sends it through Teams, email or the drivers' app, the way they are used to. The solution takes the photo, straightens it, recognises the document type and, by order number or number plate, determines which trip in CargoWise it belongs to.
From the document the sender, consignee, cargo, weight, dates, and signature and stamp fields are read. Each field is matched against the order data in CargoWise, and the unloading date and place against a Teltonika telematics record. Differences are assessed as significant (consignee, weight, missing signature) or formal.
If there are no mismatches, the document is attached to the trip in CargoWise with the recognised fields and the trip is marked as ready for invoicing. Logistics sees a list of trips that became ready today, and the accountant issues the invoice in SAP Business One in the usual way.
When the weight, consignee or date differs or a stamp is missing, logistics gets a message in Teams with an image of the document and the mismatch highlighted. They contact the driver or customer and mark whether the mismatch is acceptable. We monitor recognition quality and tune templates for new document types.
Connecting the agreed channels (Teams, email, drivers' app) in your Microsoft 365 tenant so that drivers do not have to change their habits.
Integration with CargoWise through an API, a file export or an email flow, depending on the version, and an agreed rule set: which fields must match the trip, which may differ, and what counts as a blocking mismatch.
One window in Teams with all of today's mismatches, the document image, the trip data from CargoWise and the telematics record side by side, with the option to mark a decision.
Every recognised document is stored in a log with a confidence score and the logistician's decision, and we periodically review errors and tune recognition for new CMR and declaration templates.
Document recognition (OCR + LLM) + CargoWise integration + Teams channel for drivers. We choose the integration method with CargoWise after checking your version. Read more about this service and its limits on the service page.
Most phone photos are recognised without problems, even tilted or in shadow. When part of the text is unreadable, the solution does not guess: it marks the field as unread and logistics sees the original in Teams. The driver can be asked automatically to take the photo again.
Yes. We integrate with CargoWise through an API, a file export or an email flow, depending on the version, and we take Teltonika telematics data through its API if you have access. We choose the integration method after a check at the start of the implementation; telematics is not required, and without it the matching is done only against the order data in CargoWise.
Yes, and that is what we usually do. The first stage is CMR and delivery notes, because there are the most of them and they clear the way for the invoice in SAP Business One. Customs declarations, ferry tickets or weighing slips are added later as new document types with their own matching rules.
Drivers call the dispatcher with the same questions: how to fill in a CMR, what to do after an accident, when loading is.
A request from Outlook, Trans.eu or TimoCom waits while the sales rep calculates the distance, finds a similar trip in CargoWise and writes up the…
DKV and Eurowag statements and toll, ferry and subcontractor invoices arrive from Outlook and portals, and an accountant keys them into SAP…
Orders arrive in Outlook with a PDF, from the Trans.eu exchange and from Transporeon, and the dispatcher retypes them into CargoWise by hand.
This service is delivered by specialists with valid international certifications. Their expertise is confirmed by independent organisations, not by us.
AI systems are deployed with protection against data leakage and model abuse.
The AI security programme and its controls are managed following the ISACA methodology.
AI risks are identified and managed like any other IT risk.
We reply within 1 business day
