Give dispatch a shipment draft before the next load needs attention
For Freight brokers, dispatch teams, and shipment entry operators
Parse a shipper’s bill of lading into a consistent shipment entry shape. Keep freight rows, weights, and unit labels attached to the correct references so an operator can review the load details before they reach the transportation system.
25 free credits/month · No card needed
See the workflow and review checks{
"bill_of_lading_number": "DEMO-BOL-1048",
"shipment_date": "2026-08-17",
"shipper": "Example Packaging — Example Origin Warehouse",
"consignee": "Example Retail — Example Destination Warehouse",
"purchase_order_references": [
"DEMO-PO-2201"
],
"freight_rows": [
{
"description": "Boxed display stands",
"handling_units": 4,
"pieces": 80,
"weight": 960,
"weight_unit": "lb"
}
],
"special_instructions": "Appointment reference DEMO-APT-81"
}Synthetic data, not a live extraction. Real responses also include confidence, validation, and result status.
When this work lands on your desk
A broker or dispatch desk receives a bill of lading PDF and must prepare a shipment record while other loads are already moving.
The same document can carry a bill of lading number, purchase order number, carrier reference, and several addresses. Freight tables may separate handling units from pieces and show weight units only in a column heading. A flattened OCR transcript leaves the operator to reconstruct these relationships.
Start with the documents you already collect
- Shipper bill of lading PDFs
- Scanned freight bills of lading
- Phone images of printed shipment paperwork
PDF, JPEG, PNG, TIFF, or WEBP. Send one file per extraction call; create separate schemas when the document types need different fields.
Define the fields
Open the starter schema. Edit field descriptions, mark the values your process requires, and save it in your account.
Extract at intake
Send the document and saved schema slug to
POST /api/v1/extract, or collect the file through a branded upload site.Hand off reviewed data
Your operator verifies the shipment details, then maps accepted JSON into a TMS or dispatch worksheet through a customer-built integration. Location matching, service selection, and booking remain downstream steps.
A schema shaped around the next step.
Start with these fields, then adjust them to match your documents and destination system. The example above shows the data object you are asking Dokyumi to extract.
Download editable starter schemaStarter fields are optional until you choose which are required. Nested line items need a defined structure if you want validation of their individual values.
| Field | Type | What to capture |
|---|---|---|
bill_of_lading_number | string | Shipper’s BOL reference as printed. |
shipment_date | date | Document shipment date, distinct from delivery date. |
shipper | string | Origin party and address block. |
consignee | string | Destination party and address block. |
purchase_order_references | array | Preserve separate PO references when shown. |
freight_rows | array | Description, handling units, pieces, weight, and printed weight unit per row. |
special_instructions | string | Visible instructions; no inferred handling requirements. |
Give exceptions a clear path to review.
Dokyumi returns a model-reported confidence map, validation details, and a completed or review status for produced results. Check required fields and your business rules before passing data onward.
A completed extraction describes the extraction result. Your application and reviewers own matching, approvals, routing, and updates to other systems.
Read the response contractChecks for this process
- Distinguish shipper, consignee, and third-party bill-to addresses.
- Check handling-unit counts separately from individual pieces and preserve pounds versus kilograms.
- Review stamps or handwriting that obscure freight rows and identifiers.
Prove the fit on a representative batch.
Start with recurring shippers and include a multi-row BOL, a scanned copy, and a document with several reference numbers. Compare accepted field values and operator correction time against manual shipment entry.
Compare extracted values with a reviewer’s reference set. Record corrections, unresolved fields, review time, and credits used before connecting downstream actions.
The free plan’s credit limits apply. Assisted pilots are scoped with Dokyumi before work begins.
Expand when the next process is ready
Additional credits support recurring load volume. More schemas can cover shipper-specific field sets, delivery receipts, and freight invoices; additional branded sites can serve different customers or operating branches.
For a tailored implementation
Explore Enterprise for custom load-document volume, larger portal deployments, or requirements beyond self-serve document limits.
Talk through document mix and volumeStart small. Add capacity as intake grows.
All self-service plans include the REST API, upload-site webhooks, custom confidence thresholds, and schema inference. Choose by volume, schema count, and upload sites.
Each document uses one credit per 5 pages, rounded up. An 8-page file uses 2 credits. Self-service files can be up to 50 pages; larger files, custom-built schemas, and additional volume are quoted through Enterprise. Full pricing details
Questions about bill of lading shipment entry
Is this a native transportation management system integration?
Dokyumi provides an extraction API and configurable upload-site webhooks. Your team builds and maintains the mapping to its TMS, including reference resolution and write permissions.
Can it parse several freight rows?
Use an array field that describes the row columns you need. Evaluate representative tables and compare row counts and weight units with the source before accepting the result.
Will a BOL prove the shipment was delivered?
This workflow captures shipment information from the document supplied. Your operations process must review separate delivery records and determine the shipment’s status.
How do I test this workflow on my own documents?
Start free with 25 credits per month, 2 schemas, and 1 branded upload site. The starter schema opens in the schema builder after sign-up. Edit the fields, save it, and upload a representative file through your account or the extraction API. Account documents are stored according to Dokyumi’s privacy policy; contact hello@dokyumi.com for deletion requests and retention requirements.