Prepare sales order details when a customer emails a purchase order
For Order desk and sales operations teams
Turn a customer’s PO attachment into a consistent draft for your order desk. Capture what the buyer requested, then let your own process resolve products, addresses and commercial terms.
25 free credits/month · No card needed
See the workflow and review checks{
"buyer_name": "Example Customer Inc. — synthetic",
"purchase_order_number": "DEMO-PO-300",
"order_date": "2026-08-05",
"ship_to_address": "100 Example Way, Sample City, CA 00000",
"requested_delivery_date": "2026-08-20",
"line_items": [
{
"customer_item_reference": "DEMO-KIT",
"description": "Example service kit",
"quantity": 12,
"unit": "each",
"stated_price": 30
}
],
"order_total": 360
}Synthetic data, not a live extraction. Real responses also include confidence, validation, and result status.
When this work lands on your desk
A customer submits a PDF purchase order, and the order desk needs to create a sales order without missing a line or delivery instruction.
Customer item numbers may not match your catalog, delivery dates may apply to individual lines and a ship-to address may differ from the billing account. A structured draft helps the order desk see those details together. Extraction does not confirm inventory, accept the customer’s terms or create the sales order.
Start with the documents you already collect
- Customer purchase order PDFs
- Scanned purchase orders
- Revised PO files processed as separate submissions
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 order system resolves customer and catalog records. The order desk checks pricing, delivery commitments and revisions before creating an order and issuing any acknowledgement.
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 |
|---|---|---|
buyer_name | string | Customer organization named on the order. |
purchase_order_number | string | Customer PO reference, preserving revision text if included. |
order_date | date | Issue date printed on the PO. |
ship_to_address | string | Requested destination as printed. |
requested_delivery_date | date | Header-level requested date when explicitly stated. |
line_items | array | Customer item reference, description, quantity, unit and stated price. |
order_total | currency | Printed PO total; not a confirmed sales order value. |
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
- Customer SKU needs mapping to an internal product
- Revision supersedes a previously entered order
- Line-specific dates differ from the header date
- Unit prices or destination details require confirmation
Prove the fit on a representative batch.
Select repeat customers with distinct PO layouts, including one revision and one order with split delivery dates. Compare the draft with the order desk’s checked 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
Use paid capacity as recurring orders grow. Add schemas for quote requests or customer-specific line layouts when the order desk has validated the first process.
For a tailored implementation
Discuss custom volume and schema setup for large customer portfolios or several order-entry teams.
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 customer purchase order entry
Does parsing accept the customer’s order?
No. It captures requested details. Your commercial review and order acknowledgement process determine acceptance and delivery commitments.
Will customer SKUs map automatically?
Product mapping requires your catalog and rules. The extracted item reference and description give your integration the inputs for that lookup.
How should revised POs be handled?
Keep each submission linked to its source file. Your system compares references and revisions before changing an existing sales order.
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.