Financial Document Parser

For Receipts:

• Merchant name and location
• Date and time
• Items purchased
• Individual prices
• Subtotal, tax, total
• Payment method
• Last 4 digits of card (if present)

For Bank/Credit Card Statements:

• Statement period
• Account number (last 4 digits)
• All transactions (date, description, amount, balance)
• Beginning and ending balance
• Total credits and debits
• Fees or interest charges

Output Format

# Financial Document Analysis

## Document Details
- **Type**: Invoice / Receipt / Statement
- **Date**: [Date]
- **Vendor/Merchant**: [Name]
- **Document Number**: [Number]
- **Total Amount**: $X,XXX.XX

## Line Items
| Description | Quantity | Unit Price | Total |
|-------------|----------|------------|-------|
| [Item] | X | $XX.XX | $XX.XX |

## Financial Summary
- **Subtotal**: $X,XXX.XX
- **Tax**: $XXX.XX
- **Total**: $X,XXX.XX
- **Payment Method**: [Method]

## Expense Categorization
| Category | Amount | Items |
|----------|--------|-------|
| Software | $XXX | Slack, GitHub |
| Office | $XX | Supplies |

## Insights
- ✓ Tax-deductible business expenses: $X,XXX
- ⚠ Recurring charges detected: 3 subscriptions ($XXX/month)
- ℹ Foreign transaction fees: $XX

## Flagged Items
- [ ] Large expense ($X,XXX) - verify approval
- [ ] Duplicate charge detected on [date]

## Export Data (CSV Format)
```csv
Date,Vendor,Description,Category,Amount,Tax Deductible
2025-01-15,Adobe,Creative Cloud,Software,52.99,Yes

Recommendations

• Track recurring $XXX/month for [subscription]
• Consider negotiating bulk discount with [vendor]
• Set up payment reminder for [invoice due date]

## Examples

**User**: "Extract data from this invoice PDF"
**Response**: Parse PDF → Extract vendor info, line items, totals → Categorize as business expense → Format as structured data → Generate CSV export

**User**: "Analyze my bank statement and categorize expenses"
**Response**: Extract all transactions → Categorize each (dining, software, travel) → Identify recurring charges → Calculate totals by category → Flag unusual transactions → Generate spending report

**User**: "Parse these 10 receipts and create an expense report"
**Response**: Process each receipt → Extract merchant, date, amount, items → Categorize expenses → Calculate totals → Generate consolidated report → Create CSV for expense submission

## Best Practices

- Preserve exact amounts (don't round)
- Maintain currency symbols and formats
- Note when data is unclear or illegible
- Flag suspicious or duplicate transactions
- Provide tax-relevant categorization
- Use standard expense categories
- Generate export-ready formats (CSV, JSON)
- Protect sensitive info (mask account numbers)
- Identify missing information (no date, unclear vendor)
- Calculate totals and verify against document
- Note discrepancies or calculation errors
- Include exchange rates for foreign currency