Give brokerage document teams a clearer start to shipment intake
For Customs brokerage document teams and import operations coordinators
Turn a commercial invoice into a structured intake worksheet for the brokerage team. Preserve declared merchandise descriptions, quantities, currencies, and references as supplied, then hand the record to the people responsible for entry preparation and review.
25 free credits/month · No card needed
See the workflow and review checks{
"invoice_reference": "DEMO-CI-830",
"invoice_date": "2026-08-14",
"seller": "Example Export Manufacturing",
"buyer": "Example Import Supply",
"shipment_references": [
{
"label": "Purchase order",
"value": "DEMO-PO-337"
}
],
"currency": "USD",
"merchandise_rows": [
{
"description": "Unprinted paper storage boxes",
"quantity": 500,
"unit": "pieces",
"unit_value": 4,
"line_value": 2000,
"stated_origin": "Canada"
}
],
"invoice_total": 2000
}Synthetic data, not a live extraction. Real responses also include confidence, validation, and result status.
When this work lands on your desk
An importer sends shipment documents and the brokerage desk needs to organize the invoice data before preparing an entry.
Commercial invoices and packing lists describe related shipments using different units and reference labels. A document may show several country references, invoice and shipping addresses, and charges outside the merchandise table. Intake staff need those distinctions preserved before reviewing the shipment package.
Start with the documents you already collect
- Commercial invoice PDFs
- Packing list PDFs using a separate schema
- Scanned supplier shipment documents
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
The brokerage team reviews the extracted data against the supplied documents. Your systems handle cross-document comparisons and entry mapping; qualified staff own classification, valuation, admissibility review, and filing.
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 |
|---|---|---|
invoice_reference | string | Commercial invoice identifier. |
invoice_date | date | Issue date appearing on the invoice. |
seller | string | Seller name and address block as printed. |
buyer | string | Buyer name and address block as printed. |
shipment_references | array | Listed PO, container, or transport references with their labels. |
currency | string | Invoice currency, without conversion. |
merchandise_rows | array | Description, quantity, unit, value, and any explicitly stated origin per row. |
invoice_total | currency | Printed invoice total; no customs valuation determination. |
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
- Preserve the difference between seller location, shipment origin, and stated merchandise origin.
- Check invoice currency and quantity units before any downstream comparison.
- Review missing descriptions, ambiguous references, and totals that require additional document context.
Prove the fit on a representative batch.
Begin with invoices from recurring suppliers and a limited set of merchandise fields. Compare the extracted rows with your intake worksheet; evaluate packing lists separately before building customer-owned cross-document checks.
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
Paid tiers become useful for recurring shipment volume, separate commercial-invoice and packing-list schemas, and importer-branded upload channels. Expand only after the brokerage team has defined its acceptance and correction process.
For a tailored implementation
Discuss custom volume, long document requirements, or many importer portals when a broader brokerage rollout outgrows self-serve capacity.
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 customs document intake
Will it assign tariff codes or calculate duties?
No. This workflow extracts supplied document fields. Classification, customs value, duty calculations, regulatory review, and filing belong to your brokerage process.
Can the invoice and packing list be checked against each other?
You can extract each file with an appropriate schema. Your application must associate the shipment records and implement any quantity, reference, or description comparisons.
Does this send an entry to customs?
No. The API returns structured JSON for your intake workflow. There is no automatic customs filing or native brokerage-system connection in this example.
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.