Give AP comparable invoice data before a PO exception review
For AP analysts investigating purchase order exceptions
Extract the purchase order reference and invoice lines into a structure your matching process can use. Keep document parsing distinct from your organization’s rules for quantities, tolerances and receiving.
25 free credits/month · No card needed
See the workflow and review checks{
"supplier_name": "Example Components Ltd. — synthetic",
"invoice_number": "DEMO-INV-021",
"purchase_order_number": "DEMO-PO-091",
"currency_code": "USD",
"line_items": [
{
"item_reference": "DEMO-BOLT",
"description": "Example bolt pack",
"quantity": 10,
"unit": "pack",
"unit_price": 20,
"line_amount": 200
}
],
"shipping_amount": 15,
"invoice_total": 215
}Synthetic data, not a live extraction. Real responses also include confidence, validation, and result status.
When this work lands on your desk
A PO-backed invoice reaches AP, and an analyst needs usable line data to compare with the purchase order and receipt records.
Invoice descriptions may differ from the buyer’s item names, and units can be expressed as cases, packs or individual pieces. An apparently matching total can hide a quantity or freight exception. Structured extraction prepares the visible values; the customer’s matching logic must decide which records correspond and whether differences are acceptable.
Start with the documents you already collect
- PO-referenced supplier invoices
- Purchase orders through a separate PO schema
- Receiving documents through a separate receipt schema
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 system looks up the PO, normalizes units and compares extracted lines with approved purchasing and receipt data. Your AP team owns tolerance settings, exception resolution and release for payment.
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 |
|---|---|---|
supplier_name | string | Invoice supplier for your vendor lookup. |
invoice_number | string | Reference used to identify this invoice. |
purchase_order_number | string | PO reference printed on the invoice. |
currency_code | string | Explicit currency for comparison with purchasing records. |
line_items | array | Item reference, description, quantity, unit, unit price and line amount. |
shipping_amount | currency | Separately printed freight or delivery charge. |
invoice_total | currency | Printed total, including charges shown on the document. |
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
- One invoice references multiple purchase orders
- Unit-of-measure mismatch between invoice and PO
- Freight or tax absent from the original order
- Partial shipment or substituted item needs confirmation
Prove the fit on a representative batch.
Evaluate ordinary matches alongside partial receipts, extra freight and a unit mismatch. Test parsing accuracy and your matching rules separately so the source of each exception is clear.
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
Add paid capacity for regular PO-backed invoice volume. Separate PO and receiving schemas can support richer customer-built matching once each extraction path is validated.
For a tailored implementation
Discuss schema assistance and custom volume for complex line tables or multiple purchasing entities.
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 invoice and po matching preparation
Is automatic three-way matching included?
No. Dokyumi extracts document data. Your system joins invoice, purchase order and receipt records and applies the matching rules.
Can it decide whether a price difference is acceptable?
Tolerance decisions belong to your purchasing and AP policies. Keep extracted prices available for the reviewer without treating them as an approval.
Can the same call read the invoice and PO?
Each call accepts one supported file and a selected schema. Prepare the documents separately and join results in your application.
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.