Document processing
Collect documents from agreed channels, identify the document type and shipment, read the relevant content and manage revised versions.
AI Operators · Use cases
Document automation
AI Operators process logistics documents, extract and validate shipment data, compare related files and enter approved information into your TMS under your SOPs.
Explore your workflowYour SOPs. Your systems. Your team in control.
- Starts with
- Shipment documents received through agreed operational channels.
- Works with
- Document types, shipment context, field mappings, comparison rules and your connected TMS.
- Completes with
- Approved data entered into the operational workflow, or a document exception ready for review.
The operational opportunity
Process the document. Validate the data. Complete the operational entry.
Document automation is broader than comparing two files. Logistics teams receive documents through email, portals and shared workflows, identify what each file is, extract the operational data, validate it against shipment context and then re-enter approved information into a transportation management system (TMS) or the next process.
Shipflow’s Document Operator connects those steps. It processes the document, classifies it, extracts the fields required by the workflow, applies document- and customer-specific checks, compares related documents or records when needed, and enters validated data into the permitted TMS fields. Missing, unclear or conflicting information goes to the responsible person with the source documents attached.
The workflow can support documents across the Ocean, Air and Road lifecycle. Representative Ocean documents include Master Bills of Lading (MBLs), House Bills of Lading (HBLs), Shipping Orders, Shipping Instructions, pre-alerts, commercial invoices, packing lists and arrival notices. Each document type has its own field mapping, validation rules and completion condition.
Receiving or extracting a document does not by itself make the data approved. Your workflow defines the authoritative source, required checks, permitted TMS fields and actions that need human review.
Workflow coverage
Process documents. Compare the right fields. Complete the data entry.
Configure the Document Operator around the job each document needs—not a single extraction template applied to every file.
Comparison and validation
Check required fields against related documents, TMS records and customer rules. Surface only the differences or omissions that require action.
TMS data entry and follow-through
Map approved values into permitted TMS fields, create or update the relevant record and route the workflow to its next operational step.
Representative document types
- Master Bill of Lading (MBL)
- House Bill of Lading (HBL)
- Shipping Order
- Shipping Instructions
- Pre-alert
- Commercial Invoice
- Packing List
- Arrival Notice
How it works
From incoming file to usable operational data.
Collect and identify the document
Bring files from the agreed inbox, portal or workflow into one process. Classify the document type, match it to the shipment and distinguish the current version from superseded or duplicate copies.
Extract and normalize the required data
Read the fields the operational workflow needs, such as parties, references, routing, cargo, equipment, dates and document-specific values. Normalize the information to the formats expected by your TMS and SOP.
Validate the document in context
Check required fields, formats and business rules against the shipment and available source records. A received document is treated as ready only after the checks configured for that document type pass.
Compare related documents when required
Apply relationship-aware checks across documents such as MBLs and HBLs, Shipping Orders and Shipping Instructions, or commercial invoices and packing lists. Define which values should correspond, which can legitimately differ and which discrepancies require action.
Enter approved data or route the exception
Write validated values to the permitted TMS fields and move the record to the agreed next step. Send missing, unclear or conflicting information to the responsible person with the source file, shipment context and exact fields requiring review.
Human control
Automate the routine. Keep judgment with your team.
Execute within agreed rules
- Collect, classify and match documents from the agreed sources.
- Extract and normalize the fields required by each document workflow.
- Run configured document, record and cross-document validation checks.
- Enter approved values into permitted TMS fields and advance the workflow.
Escalate when needed
- Required documents or fields are missing.
- Source information is unclear or does not pass validation.
- A discrepancy or revision falls outside the approved handling rules.
- The authoritative source is unclear or multiple documents conflict.
- A correction, submission or downstream action requires human approval.
Customer result
AI execution at Asia Shipping.
- Less time spent on document comparison
- 97%+
Asia Shipping uses Shipflow AI Operators to automate document comparison, including MBL and HBL checks. The deployment reduces time spent on this task by 97%+.
This result relates to the customer workflow described. Results depend on workflow scope, input quality and deployment configuration.
“Prior to Shipflow, our operators had to manually compare data fields between MBL and HBL three to four times per shipment, which was extremely time-consuming. With Shipflow, this process is now fully automated by AI.”
Getting started
Build around the way your operation works.
Choose the document workflow
Bring representative documents, including scans, attachments, revisions and difficult examples. Define whether the first workflow is processing, comparison, TMS data entry or a connected sequence, and agree what completed work means.
Map fields, relationships and sources of truth
Specify the data required from each document, how documents connect to shipments and one another, and which source takes precedence when values conflict. Identify the exact destination fields in the TMS.
Set validation and write controls
Define the checks, exception routes and approvals that apply before information is entered or an external action is taken. Confirm the supported input channels, file formats, system access and write-back permissions for the deployment.
Measure completed work, not just AI activity.
Measure the complete document workflow from receipt through validated data entry or exception handoff. Faster extraction alone does not establish that the shipment record is accurate and ready for the next operational step.
- Manual time per document or document set
- Time from receipt to validated TMS entry
- Fields entered without manual rekeying
- Document discrepancies requiring review
- Corrections and repeated processing
Common questions
Before you put an AI Operator to work.
How is this different from OCR or data extraction?
Optical character recognition (OCR) converts an image into readable text. Extraction identifies useful fields. Shipflow connects those steps with validation, cross-document checks and actions in the operational workflow, subject to your rules and system access.
Can Shipflow compare MBLs and HBLs?
Yes. MBL/HBL comparison is part of the document-comparison deployment at Asia Shipping. The fields, document relationships and exception rules for another implementation are configured around that operation’s requirements.
Can Shipflow process documents and enter data into our TMS?
Yes, when the document inputs, field mappings, validation rules, connected TMS and write permissions are included in the deployment. The operator enters approved values into the permitted fields and routes unclear or conflicting information for review.
Which logistics documents can be included?
Workflows can be configured around documents such as MBLs, HBLs, Shipping Orders, Shipping Instructions, pre-alerts, commercial invoices, packing lists and arrival notices. Supported file formats, fields and actions are confirmed for the selected workflow and systems.
Does every difference mean a document is wrong?
No. Different document roles can lead to legitimate differences. During setup, your team defines which fields should correspond, which differences are expected and which require investigation. The operator applies those rules rather than treating every difference as an error.
Do we have to automate every document type at once?
No. Start with one repeatable document workflow and a clear validation standard. Expand to additional types after the team has reviewed the results and agreed the relevant rules, exceptions and system connections.
Start with one workflow
Start with the document processing or data-entry workflow your team keeps repeating.
Map the inputs, decisions and systems with Shipflow. Define a useful first deployment with clear boundaries and measurable outcomes.
Book a working session