Set Up Packing Slip Fields and Run a Test Batch

What this guide helps you do

This guide shows how to configure a packing slip parser in PerfectParser, define receiving fields and item tables, run a test batch, and export warehouse data. Skip the AI prompt initially when you want the broadest field discovery on supplier-specific slip layouts.

Why packing slips are hard to parse

Packing slips sit between purchase orders and physical goods, so the same data appears under different labels — "Ship Qty", "Qty Shipped", or just "Qty". SKU columns may show part numbers while the adjacent column carries a long product description, and some suppliers omit the PO reference entirely while others print it in a barcode footer. Multi-line item tables often wrap descriptions across rows, which can split a single SKU into two parsed rows if the schema is not explicit. The qty ordered vs qty shipped distinction is critical for receiving: treating them as one field hides partial shipments. Dense warehouse printouts also use small fonts and thermal paper, so field descriptions in your schema should tell the AI which column is which.

Recommended Fields

We suggest configuring the following schema fields for your Packing Slip Parser to capture all essential warehouse receiving details.

AI Prompt (Optional)

Use this only when you want to guide auto-detect toward a specific set of fields.

If you want PerfectParser to discover additional fields on its own, leave the AI Prompt (Optional) box blank for the first pass, review the detected schema, then add a prompt only if you need tighter consistency.

When you do use a prompt, copy and paste the following instructions into the AI Prompt (Optional) field during setup:

Extract the packing slip number, associated purchase order reference, shipper name, recipient name, and ship date. Also extract the table of shipped items containing the item code/SKU, description, quantity ordered, and quantity shipped.

Set up this parser in the dashboard

Create a parser

Go to Parsers → New Parser in the dashboard. Give it a name like "Packing Slip Parser" and optionally select the document category.

Upload a sample document

Drag and drop a representative packing slip (PDF, PNG, or JPEG). Use a real file from a supplier whose format you process regularly — the AI uses it to learn column headers and table structure.

Detect fields or use standard fields

Paste the AI Prompt from the section above into the AI Prompt (Optional) box if you want tighter field mapping, then click Auto-Detect. To discover more fields automatically, leave the prompt blank and click Auto-Detect. Or skip auto-detect and add fields manually using the Recommended Fields table above.

Review and save your schema

Check that shipped_items is a Table with separate qty_ordered and qty_shipped columns. Confirm item_code is Text, not Number — SKUs often contain leading zeros or letters. Edit any field names or descriptions, then click Save.

Run a test batch

Navigate to Bulk Extraction, choose how your files are organised, upload a small test set of packing slips, and click Extract All Files. Review the results in Batch History and export to CSV or Excel.

Common mistakes

• Collapsing qty ordered and qty shipped into a single quantity column — you lose the ability to flag partial or over-shipments during receiving.
• Storing SKUs as Number, which strips leading zeros (e.g. 004521 becomes 4521).
• Using a delivery note without an item table as the sample when production slips always include line-level detail.
• Omitting po_reference from the schema when your 3-way match workflow depends on linking slips back to open purchase orders.

Next steps

• Create a Parser guide
• Bulk Extraction guide
• Export Results guide