Invoice Organizer

Bulk-categorize a CSV of invoices or receipts, detect duplicates, and produce a tax-ready monthly summary.

---

Table of Contents

• Keywords
• Quick Start
• Core Workflows
• Tools
• Reference Guides
• Templates
• Best Practices
• Scope & Limitations

---

Keywords

invoice, invoices, receipt, receipts, expense, expenses, bookkeeping, accounting, tax, tax prep, categorization, vendor, reimbursement, monthly summary

---

Clarify First

Before categorizing, settle the inputs below. When one is missing or vague and would change the result, ask about it; when it wouldn't, use a sensible default and say which one you used.

• Receipt CSV fields: date, vendor, description, amount drive categorization and duplicate detection.
• Tax bucket scheme: US Schedule C vs UK self-employment vs generic sets which categories the summary maps to.
• Recurring-vendor rules: known vendor→category mappings to seed category_rules.json and cut the uncategorized bucket.

Ask about the two or three inputs that matter most for this request, not the whole list. If the user wants a result straight away, produce it and state your assumptions at the top.

---

Quick Start

Categorize 200 Receipts in 1 Minute

1. Export receipts from your bank or expense tool as a CSV with columns: date,vendor,description,amount, all in one currency (convert any foreign-currency rows first)
2. Run:

   python scripts/invoice_categorizer.py receipts.csv
   

3. Review the categorized output and override anything wrong via the rules file
4. Export the monthly summary for handoff to your accountant

---

Core Workflows

Workflow 1: Monthly Bookkeeping

Goal: Convert a month of unstructured receipts into a categorized, tax-ready summary in under 10 minutes.

Steps:

1. Export receipts as CSV from your bank, card, or expense tool
2. Run: python scripts/invoice_categorizer.py receipts.csv
3. Review the uncategorized bucket — these need rules added or manual override
4. Add rules to assets/category_rules.json for any recurring vendors
5. Re-run; uncategorized count should drop each month as the rules file grows
6. Drop the monthly summary into assets/monthly_summary_template.md

Expected Output: Categorized expense list + monthly totals by category + duplicate-suspect list.

Time Estimate: 10 minutes/month after initial rules are seeded.

Workflow 2: Duplicate Detection

Goal: Catch double-entered receipts before they reach the books.

Steps:

1. Run: python scripts/invoice_categorizer.py receipts.csv --json
2. Inspect the duplicates_suspected list
3. Confirm whether each is a true duplicate (same charge entered twice) or a coincidence (same amount on different days at different vendors)
4. Remove confirmed duplicates from the source CSV; re-run

Expected Output: Cleaned CSV with no duplicate rows.

Time Estimate: 2-3 minutes per month.

Workflow 3: Vendor Spend Review

Goal: Find spend creep — vendors whose monthly total grew significantly without you noticing.

Steps:

1. Run categorizer for the last 3-6 months separately
2. Compare per-vendor totals month-over-month
3. Flag any vendor where total grew > 25% with no obvious business reason
4. Either renegotiate, switch, or accept; revisit quarterly

Expected Output: Vendor-spend trend list with flagged growth.

Time Estimate: 15 minutes per quarter.

---

Tools

invoice_categorizer.py

Reads a CSV of receipts/invoices and:

• Categorizes each row by vendor + description against rules in assets/category_rules.json (extensible)
• Aggregates totals per category and per vendor
• Detects likely duplicates (same vendor + amount within 3 days)
• Flags uncategorized items for manual review

# Human-readable summary
python scripts/invoice_categorizer.py receipts.csv

# JSON for programmatic use
python scripts/invoice_categorizer.py receipts.csv --json

# Use a custom rules file
python scripts/invoice_categorizer.py receipts.csv --rules my-rules.json

Expected CSV columns: date, vendor, description, amount. Amounts are treated as one currency. A currency column is allowed but ignored: it is not read, shown in the output, or used to convert. Date formats accepted: YYYY-MM-DD, MM/DD/YYYY, DD/MM/YYYY

---

Reference Guides

• references/expense_categorization_guide.md — Standard expense categories, common tax buckets (US Schedule C, UK self-employment, generic), how to map vendors to categories

---

Templates

• assets/category_rules.json — Default rules; extend with your recurring vendors
• assets/monthly_summary_template.md — Format for handing the monthly summary to an accountant

---

Best Practices

• Categorize monthly, not annually. Annual catch-up bookkeeping always misses receipts and produces guess-categorization.
• Grow the rules file over time. First month: 30% uncategorized. Sixth month: < 5%. The compounding return on rule-writing is high.
• Keep evidence. Categorization is bookkeeping; receipts (PDFs, photos) are tax evidence. Store separately from this script's output.
• Don't trust auto-categorization for tax filing. Use it for prep; have a human (you or your accountant) sign off before filing.
• Currency consistency. The script sums every amount as if it were one currency. If you have multi-currency receipts, convert them at the month-end FX rate before the run; it does not handle FX.

---

Scope & Limitations

In Scope:

• Categorization of a receipts CSV by vendor and description against rules in assets/category_rules.json or a custom --rules file (invoice_categorizer.py).
• Totals per category and per vendor, and an uncategorized list for manual review.
• Duplicate suspects, defined as the same vendor and amount within 3 days.
• Expense categories mapped to tax buckets (US Schedule C by default, UK self-employment and generic) in references/expense_categorization_guide.md, plus a monthly summary template.

Out of Scope:

• Reading bank feeds, accounting software, or receipt PDFs and photos. Input is an exported CSV.
• Currency conversion. Multi-currency receipts are converted before the run.
• Tax filing, deductibility decisions, and VAT or sales-tax returns.
• Budgeting, forecasting and variance analysis (see finance/financial-analyst/), and SaaS seat and renewal savings (see business-operations/procurement-optimizer/).

Important Caveats:

• The output is not tax, accounting or legal advice. Bucket assignments need sign-off from the user or a licensed accountant before filing.
• Categorization is rule-based matching. New vendors land in the uncategorized bucket until rules are added.
• Duplicate detection is a heuristic. Flagged pairs can be legitimate repeat charges, and duplicates more than 3 days apart are not flagged.
• Tax line numbers and rules change by year and jurisdiction, so the reference mapping can go stale.

---

Integration Points

• Pairs with finance/ skills for budgeting and forecasting
• Feeds into c-level-advisor/cfo-advisor cash-flow workflows
• Used by solo-founder persona for monthly close