Guide the AI with instructions, auto-detect data fields from your sample document, customize field names, and add missing columns manually.

After uploading your sample document, you configure the exact structure of the data you want to extract. The field editor uses a split-screen layout:

Left Panel (Sample Document Preview): Displays your uploaded sample file.
Right Panel (Configuration): Where you guide the AI, run auto-detection, and customize your fields.

Field configuration screen showing sample document preview and configuration panels

Step 1: Auto-Detect Fields

Instead of building your spreadsheet columns from scratch, let the AI analyze your sample document to detect them automatically.

Locate the AI Instructions (Prompt) box.
Enter a brief description of what you want the AI to do (e.g., Extract billing details and line items).
Click ✨ Auto-Detect Fields.
The AI will read your sample document and automatically generate a list of suggested columns in the Extraction Fields Schema editor below.

Your prompt tells the AI what to look for and how to structure its analysis. Here are some copy-pasteable examples for different document types:

Document Type	Example Prompt
Invoices	Extract the vendor details, invoice number, issue date, tax breakdown, and total. Identify the line items table and extract the description, quantity, and unit price.
Utility Bills	Extract the account number, billing period start/end dates, total charge, and usage details (like kilowatt-hours or gallons consumed).
Retail Receipts	Extract the store name, transaction date and time, payment method, total tax paid, and list of items purchased.
Delivery Notes	Extract the sender, recipient, carrier name, tracking number, shipment date, and list of packages with their weights and contents.

Step 2: Review and Refine the Fields

PerfectParser will display the auto-detected columns in a table. Go through each suggested field and decide:

Keep it: If the field name and description are correct, leave it as is.
Rename it: Click the field name to edit it.
Remove it: Click the trash icon to delete columns you do not need in your final export.

Each field has a description box. Write a clear, plain-English instruction to tell the AI exactly how to locate and extract that specific value.

❌ Too vague	✅ Clear and specific
Amount	Total invoice amount due, including VAT, in the invoice currency
Date	Invoice issue date in the format shown on the document
Name	Full legal name of the vendor (supplier) as printed on the invoice header
Ref	Customer purchase order reference number, usually labelled "PO Number" or "Your Ref"

If the AI missed a column, or if you want to define a new column manually, use the buttons at the bottom of the schema editor:

Add Text Field: Adds a simple, single-value column (e.g. tax_rate or due_date).
Add Table: Creates a table group for lists of items (e.g. line_items). You can define child fields inside this table (e.g. description, qty, price).
Add Section: Creates a nested group to keep related fields organized under one heading.

Once you are happy with the fields list:

To see the actual extracted data values of your documents, proceed to the Bulk Extraction tab.