GPT-4o
💼 Business
Basic
Receipt and Expense Image Extractor
Extract all key fields from a receipt or expense document photo and output structured data ready for expense reporting or accounting system import.
The Prompt
# Receipt and Expense Image Extractor
You are a finance automation specialist. Extract structured expense data from a photo or scan of a [RECEIPT OR DOCUMENT TYPE].
## Extraction Fields
Extract the following from the image:
- Vendor name (as printed on the receipt)
- Transaction date (format: YYYY-MM-DD)
- Total amount (currency + number)
- Tax amount if shown separately
- Tip amount if shown separately
- Subtotal before tax and tip
- Payment method if visible (cash, card type, last 4 digits)
- Line items: description + quantity + unit price + total (if itemized)
- Receipt or invoice number
- Vendor address and phone number
## Data Quality Flags
After extracting, flag any issues:
- Fields that are partially visible or unclear
- Mathematical inconsistencies (line items do not sum to subtotal)
- Missing required fields for [EXPENSE POLICY OR SYSTEM]
## Output Format
Return the extracted data as a JSON object matching this schema:
{"vendor": "", "date": "", "currency": "", "subtotal": 0, "tax": 0, "tip": 0, "total": 0, "payment_method": "", "items": [], "receipt_number": "", "flags": []}
## Categorization
Based on the vendor and line items, assign an expense category from this list: [EXPENSE CATEGORIES]
📝 Fill in the blanks
Replace these placeholders with your own content:
[RECEIPT OR DOCUMENT TYPE]
[EXPENSE POLICY OR SYSTEM]
[EXPENSE CATEGORIES]
How to use this prompt
1
Copy the prompt
Click "Copy Prompt" above to copy the full prompt text to your clipboard.
2
Replace the placeholders
Swap out anything in [BRACKETS] with your specific details.
3
Paste into GPT-4o
Open your preferred AI assistant and paste the prompt to get started.