- Home
- Receipts and Expenses
- Chase Clients About Uncoded Transactions with an AI-Drafted Email
Chase Clients About Uncoded Transactions with an AI-Drafted Email
What the source describes
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.
Result or outcome
According to the source, the unknown transactions email is the most disliked job in bookkeeping and the place where an assistant saves the most time per use, provided client data is anonymized first and the output is reviewed.
How to run it
- Leave matching and coding suggestions to the ledger, and list only the bank transactions you cannot code, with date, amount and description.
- Strip client names, tax identifiers, bank account numbers and addresses, replacing the client name with a placeholder such as Client A.
- Paste the prompt on this page and the list into a firm-approved business tier of ChatGPT, Claude, Grok or Gemini.
- Edit the draft so similar items are grouped, questions are numbered and receipts are requested, then send it from your usual email.
- If the client does not reply, send the shorter, firmer follow-up that the prompt also drafts.
Try it yourself
Copyable prompt
You are a bookkeeper writing to a small business client, [Client A]. Below is a list of bank transactions from [month] that I cannot categorize, with date, amount and bank description only (names and account numbers removed): [paste list]. Write a short, friendly email asking what each transaction was for. Group similar items together, number each question so the client can reply by number, and ask for a receipt or invoice where one would normally exist. Mention that we need answers by [date] to finish the month. Keep the email under 180 words plus the list. Then write a shorter, firmer follow-up to send if there is no reply after [7] days. Flag any transaction you think may be personal.
Replace the [bracketed] placeholders. Remove client names, account numbers, and personal data before pasting into any AI tool.
What to review
Check that every transaction in the email matches the bank feed exactly, with no amounts or dates altered by the AI. Do not let the assistant decide coding or tax treatment; code each item yourself from the client's answers and receipts. Confirm no names, account numbers or tax identifiers remained in what you pasted.
Related free download: 50 AI Prompts for Bookkeepers (Prompt pack (PDF))
Source: The Firm (accounting publication)
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
- Practice Operations
Speed Up Client Email Replies with Karbon AI Summaries and Quick Replies
Karbon's February 12, 2025 release notes announce two open beta Karbon AI features for accounting firms. Karbon says quick replies offer three suggested responses to common incoming emails, and that AI summaries cover the 10 most recent conversations on each work item. The summaries are meant to help users get up to speed before client meetings without sifting through emails and notes. Karbon positions the conversation summaries as especially useful for owners, managers and partners overseeing many client relationships.
Karbon, Karbon AI
Karbon Release Notes - Receipts and Expenses
Categorize Leftover Expenses with AI After Bank Rules
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.
Works in ChatGPT, Claude, Grok, Gemini
QuickBooks Online, Xero
Brocent Blog - Receipts and Expenses
Keep Each Client's Coding Rules in a Claude Project
Anthropic's help center describes Projects as self-contained workspaces with their own chat histories and knowledge bases. Anything uploaded to a project's knowledge base is used across all chats in that project, and project instructions tell Claude how to behave and respond in every chat there. Projects are available on free accounts, which can create up to five. Context is not shared across chats within a project unless it is added to the project knowledge, and on paid plans Claude automatically enables RAG mode when project knowledge approaches the context window limit.
Claude, Claude Projects
Claude Help Center (What are projects?) - 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