Categorize Leftover Expenses with AI After Bank Rules
What the source describes
This Brocent guide argues that QuickBooks and Xero bank rules should handle recurring transactions deterministically, and that ChatGPT is best used for the residue of unrecognised payees, split transactions and anomaly review. It recommends exporting uncategorised transactions to CSV with the real chart of accounts, asking for a suggested category with a confidence note and flags, and reviewing everything before posting. It stresses never auto-posting AI output, keeping an audit trail and leaving tax judgements to an accountant.
Result or outcome
According to the source, the residue that bank rules miss is often 10-20% of lines but a much larger share of the time, and each correction can become a new bank rule so the AI review pass shrinks month over month.
How to run it
- Set up QuickBooks Online or Xero bank rules for every recurring payee first, using recent history, so only the leftover lines need AI help.
- Export the uncategorized transactions to CSV, removing account numbers, and copy your actual chart of accounts so the AI cannot invent account names.
- Paste the prompt on this page into ChatGPT, Claude, Grok or Gemini with the business description, chart of accounts and CSV to get a suggested account, confidence and flags.
- Review every suggestion, starting with low-confidence and flagged lines, then code the confirmed transactions in the accounting platform yourself, never auto-posting.
- Turn repeat payees and your corrections into new bank rules, and save the export, suggestions and corrections as an audit trail.
Try it yourself
Copyable prompt
You are helping me categorize transactions my bank rules did not catch. Business: [one-line description]. Use ONLY these accounts from my chart of accounts: [paste account list]. For each transaction below, return: date, payee, amount, suggested account, confidence (high, medium, low) and a short reason. If a transaction might need splitting, might be personal, or you cannot place it, flag it instead of guessing. Do not make deductibility or tax treatment decisions. At the end, list any payees that appear more than once so I can create a new bank rule for them. Transactions (dates, payees, amounts only, account numbers removed): [paste CSV]
Replace the [bracketed] placeholders. Remove client names, account numbers, and personal data before pasting into any AI tool.
What to review
Confirm each suggested account exists in the client's chart of accounts and fits the receipt or invoice, not just the payee name. Split transactions, possible personal spend and anything touching deductibility or sales tax treatment should go to the client's tax professional. Check that receipts are attached for claimed expenses, and confirm your AI plan's data-handling terms before uploading bank data.
Related free download: 50 AI Prompts for Bookkeepers (Prompt pack (PDF))
Source: Brocent Blog
Not professional advice. This is general information, not accounting, tax, legal or financial advice. Check AI output yourself and consult a licensed professional for your situation. See our Terms of Use.
This entry summarizes a public source. Features, plans, and availability change, so confirm details with the vendor. Tool names are trademarks of their respective owners.
Related workflows
- Receipts and Expenses
Reclassify Miscoded Expenses in Excel with AI
In this Journal of Accountancy Tech Q&A, a CPA and accounting professor shows an accountant uploading a journal entry log where every expense was coded to Office Supplies. ChatGPT scans the Description column for keywords like laptop and monitor and builds a formula that adds a Reclassified Account column, for example moving those items to Computer Equipment. The author stresses checking the AI's work and never entering client or confidential information into ChatGPT.
Works in ChatGPT, Claude, Grok, Gemini
Microsoft Excel
Journal of Accountancy - Reconciliations
Triage Unmatched Bank Transactions and Miscoding with an AI Exception Review
This Workplace AI Institute article argues that bookkeepers should let accounting platforms do bulk bank matching and then hand only the exception list to a general-purpose model such as ChatGPT or Claude. It describes exporting unreconciled items as a CSV and asking the model, using its analysis tool, to find likely duplicates, flag GL coding inconsistent with the payee, and list large items to confirm with the client. The article warns that models can be confidently wrong about specific dollar amounts and that the review is a triage tool, not a posting tool.
Works in ChatGPT, Claude, Grok, Gemini
Xero, QuickBooks Online
Workplace AI Institute (blog) - Receipts and Expenses
Auto-Publish Receipts to Xero with Hubdoc Supplier Rules
Xero Central explains how to enter details for a document in Hubdoc and publish it to create a new transaction in Xero with a copy of the document attached. It also shows how to enable autosync for a supplier so Hubdoc automatically configures and publishes that supplier's documents to Xero as soon as they are uploaded. Documents detected as credit notes are not auto-published and must be reviewed manually.
Hubdoc, Xero
Xero Central - Receipts and Expenses
Chase Clients About Uncoded Transactions with an AI-Drafted Email
The Firm's guide to ChatGPT prompts for bookkeepers argues that bank feeds and ledger rules already handle matching, so chat assistants are most useful for the writing around the ledger, starting with the email asking a client to explain transactions the bookkeeper cannot code. It recommends grouping similar items, numbering questions, requesting receipts, and following up with a shorter, firmer second chase. The article also says to strip names, tax identifiers and account numbers before pasting, use a firm-approved tier, and never let the assistant decide tax treatment or code from memory.
Works in ChatGPT, Claude, Grok, Gemini
The Firm (accounting publication)
Some links on this page are affiliate links. If you sign up through one, we may earn a commission at no extra cost to you. It does not change what we recommend. See our affiliate disclosure.