--- title: "AI for bank reconciliation: the finance-team process" url: https://usingaias.com/ai-for/bank-reconciliation/ summary: "Let your accounting software match first. Use AI on the leftovers, from descriptions only: likely explanations, queries, Excel comparison formulas and the checklist. A person approves and posts." published: 2026-10-01 updated: 2026-10-01 author: "Jack Stovell" publisher: "Adapt Progress Evolve Limited" language: en-GB --- # AI for bank reconciliation: the finance-team process Let your accounting software match first. Use AI on the leftovers, from descriptions only: likely explanations, queries, Excel comparison formulas and the checklist. A person approves and posts. ## At a glance - Difficulty: Beginner (Suits anyone who already reconciles a bank account in their accounting software. The Excel step is the only intermediate part.) - Time: About an hour to set up the first time, then less each period (our estimate, not a measured figure) - Tools: Xero or your accounting software, Microsoft Excel, ChatGPT, Claude or Copilot (an approved account) - You need: Bank statement lines imported into your accounting software; Every transaction for the period entered; Administrator access, to export uncoded statement lines in Xero; An AI tool your organisation has approved for work - Role hub: [AI for accountants and finance managers](https://usingaias.com/ai-for/accountants/) ## What you'll end up with A process you can run every week or month without reinventing it. Your accounting software does the matching it's good at. A general AI assistant helps with the leftovers, the queries and the spreadsheet. You approve, post and keep the evidence. By the end you'll have on file: the software's matches, a stripped list of leftovers, a comparison workbook, a completed checklist and a signed-off reconciliation. Nothing in that list needs bank data sitting in a chatbot. The steps use Xero, because that's where the menu names below come from. The process works the same in other accounting software; the buttons will be called something else. ## Before you start Three things need to be true first. Your bank feed or statements are imported. Every transaction for the period is entered, not just the ones you've got round to coding. And you have an AI tool your organisation has approved for this kind of work, because ICAEW's line is to keep client and confidential internal data off public AI tools and to review outputs with professional scepticism. Also check the opening balance, and check the statement balance in Xero matches the actual bank. Xero's own guidance puts both before you reconcile anything. If they're off, nothing downstream will be right, and no prompt will fix it. ## Steps ### 1. Let the software do the matching first Imported statement lines show on the left of the Reconcile tab. For each one you either match it to an existing transaction or create one. Xero suggests a match by comparing the statement line with the transactions in the account, and if several match it looks for the one with the closest due date. If the suggestion is right, accept it. Nothing suggested, but you know the transaction is there? Use find & match to search for it. Bank rules are for recurring or similar lines that you won't create a bill or invoice for. Set one up and Xero suggests the same coding each time. If a line relates to an existing transaction, don't use a rule: use find & match. If you're on the Grow plan or above, or you've added it to a smaller plan, there's automatic bank reconciliation too. A subscriber or administrator turns it on per bank account. JAX then reviews future statement lines (not historical ones) and reconciles the ones that meet its high-confidence criteria. Each gets a label: Rule, Match, Memory or Prediction. Hover over the label to see JAX's reasoning. Review them on the Reconciled transactions screen, and if one's wrong, fix it; JAX learns from the correction. **Checkpoint:** everything the software could match has been matched or accepted by you, and you've reviewed any automatic reconciliations. ### 2. Export the leftovers If you have the administrator role, you can list the unreconciled lines: in the Accounting menu, select Bank accounts, click the menu icon at the top right, then select Uncoded statement lines. Choose the bank account and dates, click Run, then Export and pick CSV (PDF works too, but you want the CSV). The export has a Your Comments column. Keep it. It's where you'll note what each line turned out to be. **Checkpoint:** one CSV covering the bank account and period you're reconciling, with a row count that matches what you saw on screen. ### 3. Strip it before AI sees anything This is the step people skip, and it's the one that matters most. Make a copy of the CSV. In the copy, keep the date, an amount band (say "under £100" or "£1,000 to £5,000") and the description text. Delete everything else. No account numbers, no sort codes, no names of customers, suppliers or staff. If a description has a person's name in it, replace it with [PERSON]. You don't need the exact figure for AI to say "that looks like a subscription". A band is enough. The exact numbers stay in your accounting software, where they belong. **Checkpoint:** read the stripped file top to bottom. Could anyone identify a person or an account from it? If so, strip it again. ### 4. Ask AI what each leftover might be Ask for questions, not answers. You want a list of what each line might be and what evidence would settle it. ```text Below are bank statement lines I can't yet identify. Each has a date, an amount band and the description text only. For each line, give me: (1) up to two things it might be, (2) the question I should ask or the document I should look for to confirm it, and (3) whether it looks related to another line in the list. Do not tell me how to code anything. Do not assume any suggestion is right. If a description is too vague, say so. [PASTE STRIPPED LINES HERE] ``` It may spot that several lines look like the same payee under slightly different reference text. That's a pattern to chase, not a coding decision. **Checkpoint:** every line has a next action (find the invoice, ask someone, check the contract). No line has been coded on the strength of the AI's guess. ### 5. Draft queries to budget holders Some lines you can't clear without the person who knows the spend. Let AI turn your rough notes into clear questions. ```text I'm reconciling a business bank account and need to ask budget holders about unexplained payments. Write a short, polite query for each item below. Each query should give the date, the amount band and the description text, ask what the payment was for and which cost centre or project it belongs to, and ask for any supporting document. Four sentences or fewer each. Plain UK English. Items: [DATE, AMOUNT BAND AND DESCRIPTION FOR EACH ITEM] ``` Add the exact amount when you send the email yourself, from your own work account. The AI saves you the wording, not the sending. **Checkpoint:** every query is sent, logged in the Your Comments column and has a chase date. You read each one before it went. ### 6. Build a bank CSV vs ledger comparison in Excel Export the ledger transactions for the bank account and period. Put the bank CSV on one sheet and the ledger export on another. Then give the AI the column headings, not the data. ```text I have two Excel sheets. Sheet "Bank" has columns: [BANK COLUMN HEADINGS]. Sheet "Ledger" has columns: [LEDGER COLUMN HEADINGS]. Dates are in [DATE FORMAT]. In "Bank", receipts are positive and payments negative; in "Ledger", [HOW AMOUNTS APPEAR]. Write formulas to add a "Status" column on the Bank sheet that: (1) uses XLOOKUP to find a ledger row with the same date and amount, (2) uses COUNTIFS to count how many ledger rows share that date and amount, and (3) shows "UNMATCHED" where there is no match and "CHECK" where there is more than one. Then add the same check on the Ledger sheet for rows with no bank match. Explain each formula in one sentence. Use cell references only, no typed numbers. ``` XLOOKUP returns the item for the first match it finds, which is why the COUNTIFS column matters: it tells you when there's more than one candidate. Test on a handful of rows you can check by eye before you trust it on the lot. **Checkpoint:** the workbook flags the unmatched rows on both sheets, and you've checked several matched and unmatched rows by hand. ### 7. Write the working-paper checklist with AI Checklists suit AI well: structure and words, no numbers. ```text Draft a one-page checklist for a monthly bank reconciliation working paper in a UK finance team using [ACCOUNTING SOFTWARE]. Include: statement balance agrees with the software; Bank Reconciliation Detail report run; every unreconciled item explained; no AI suggestion posted without evidence; queries to budget holders answered; bank rules reviewed; preparer and reviewer sign-off with names and dates. Add a tick box and a notes space for each. Short, plain wording. ``` Adjust it to your own standards, then keep it with the workings. **Checkpoint:** one checklist, completed for this reconciliation, not a template left blank. ### 8. Approve, post and keep the evidence This part is yours. AI has no role in it. Check each match and each coding decision against the evidence. Then run the Bank Reconciliation Detail report, which compares your actual bank balance with the balance of the bank account in Xero. If they don't agree, check for missing, deleted or duplicated transactions. Found a line reconciled to the wrong transaction? Unreconcile it, or use Remove & Redo, then reconcile it again correctly. Then file the pack: the exports, the comparison workbook, the completed checklist, the replies from budget holders and the report. The preparer signs and dates; the reviewer signs and dates. **Checkpoint:** the balances agree, every unreconciled item has an explanation, and both signatures are on the checklist. ## Common mistakes - **Pasting raw statements into a chatbot.** It's the obvious one, and it's why step 3 exists. - **Treating the AI's guess as the coding.** A suggestion is a lead. The evidence is the invoice, the contract or the budget holder's reply. - **Using a bank rule where an invoice exists.** If a payment is reconciled as a spend or receive money transaction instead of against the invoice or bill, the invoice still shows as awaiting payment and you can end up with a duplicate. Match it instead. - **Accepting automatic reconciliations without looking.** JAX shows its method and reasoning for each one so you can review it. Use that, and correct mistakes so it learns. - **Letting AI do the totals.** It writes formulas; the ledger and the bank supply the numbers. Never type in a total an AI gave you. ## When to keep AI out of it Approving a reconciliation. Posting a transaction. Making a payment. Anything with bank details or names in it. That's the short list. The AI isn't the decision-maker and it isn't a vault, so it gets descriptions, headings and drafts, and nothing else. The approval and the sign-off stay with you. ## Review checklist - [ ] Statement balance in the software agrees with the actual bank balance - [ ] Bank Reconciliation Detail report run and balances agree - [ ] Every unreconciled item has a written explanation - [ ] No AI suggestion posted without evidence (invoice, contract or a reply) - [ ] Every query to a budget holder answered or chased - [ ] Bank rules reviewed: none coding lines that have an invoice or bill - [ ] Automatic reconciliations reviewed, if switched on - [ ] No duplicate transactions from a wrong reconciliation - [ ] Comparison workbook uses formulas, not typed totals - [ ] Stripped file held no account numbers, sort codes or names - [ ] Preparer signed and dated - [ ] Reviewer signed and dated ## Before you paste anything: confidentiality and UK GDPR Before you paste anything, ask two questions: is there personal data in it, and is it confidential to my organisation or a client? If the answer to either is yes, use a tool your organisation has approved, under a business contract, and send only what the task needs. **For this task:** Never paste bank statements, account numbers, sort codes, or customer, supplier or staff names into a consumer AI tool. Give it description text, rough amount bands and column headings only. Never paste these into a personal (consumer) AI account: - Payroll reports, salaries by name, bank details or National Insurance numbers - Named employee records: health, absence, grievance or disciplinary details - Customer or supplier ledgers with names attached - Unpublished results, forecasts or board papers - Anything a client has given you - Passwords, API keys or bank logins (in any tool, ever) UK GDPR, in four lines: - **Send the minimum.** UK GDPR's data minimisation principle says personal data must be adequate, relevant and limited to what is necessary for the purpose. For most tasks on this site, the personal data the AI needs is none. ([ICO: The data minimisation principle](https://ico.org.uk/for-organisations/uk-gdpr-guidance-and-resources/data-protection-principles/a-guide-to-the-data-protection-principles/data-minimisation/)) - **Know who is controller and who is processor.** Under a business contract, the AI provider usually acts as your processor. On a personal consumer account, you are agreeing to the provider's own consumer terms instead. ([ICO: Controllers and processors](https://ico.org.uk/for-organisations/uk-gdpr-guidance-and-resources/controllers-and-processors/)) - **Check where the data goes.** Many AI services process data outside the UK. Restricted transfers need safeguards, which a business agreement usually addresses and a personal sign-up does not. ([ICO: International transfers](https://ico.org.uk/for-organisations/uk-gdpr-guidance-and-resources/international-transfers/)) - **The ICO has AI-specific guidance.** It covers accountability, transparency, accuracy and security when organisations use AI with personal data. ([ICO: Guidance on AI and data protection](https://ico.org.uk/for-organisations/uk-gdpr-guidance-and-resources/artificial-intelligence/guidance-on-ai-and-data-protection/)) Consumer plans vs business tiers (checked 2026-10-01; providers change their terms, so read the live page and your contract): - **OpenAI (ChatGPT).** Personal plans: conversations can be used to train models unless you turn off "Improve the model for everyone" in Settings > Data controls. ChatGPT Business, Enterprise, Edu and the API: not used to improve models by default. ([OpenAI Help Centre: How your data is used to improve model performance](https://help.openai.com/en/articles/5722486-how-your-data-is-used-to-improve-model-performance); [OpenAI: Enterprise privacy at OpenAI](https://openai.com/enterprise-privacy/)) - **Anthropic (Claude).** Free, Pro and Max: chats are used to train models only when the model-improvement setting is on. With it on, data is kept for up to five years; with it off, the standard is 30 days. Claude for Work and the API: inputs and outputs are not used to train models by default. ([Anthropic: Updates to Consumer Terms and Privacy Policy](https://www.anthropic.com/news/updates-to-our-consumer-terms); [Anthropic Privacy Center: Is my data used for model training? (consumer)](https://privacy.claude.com/en/articles/10023580-is-my-data-used-for-model-training); [Anthropic Privacy Center: Is my data used for model training? (commercial)](https://privacy.claude.com/en/articles/7996868-is-my-data-used-for-model-training)) - **Microsoft (Copilot).** Personal Microsoft accounts are covered by Microsoft's consumer terms, not your organisation's. Copilot and Copilot Chat used through an organisation: covered by Microsoft's Data Protection Addendum with Microsoft as processor; your data is not used to train foundation models. ([Microsoft Learn: Enterprise data protection in Microsoft Copilot and Copilot Chat](https://learn.microsoft.com/en-us/microsoft-365/copilot/enterprise-data-protection); [Microsoft Learn: Data, privacy and security for Microsoft Copilot](https://learn.microsoft.com/en-us/microsoft-365/copilot/microsoft-365-copilot-privacy)) > General information for UK readers. Not financial, legal, tax or HR advice. Example companies and figures are fictional unless a source says otherwise. Follow your organisation's policies and your professional body's rules. ## From the same studio Ours: made by the same studio that runs this site. - [How to get AI to](https://howtogetaito.com/make/a-spreadsheet/): A fuller walk-through of getting AI to build or fix a spreadsheet formula, with a small test on known answers before you trust it on real data. ## Related - [AI for accountants and finance managers](https://usingaias.com/ai-for/accountants/) - [AI cash-flow forecasting: a weekly forecast you can defend](https://usingaias.com/ai-for/cash-flow-forecasting/) - [ChatGPT and Xero: what connects and what to export](https://usingaias.com/ai-for/xero/) - [P&L with AI: build one from a trial balance](https://usingaias.com/ai-for/p-and-l/) ## Sources - [Xero Central: Reconcile your bank account](https://central.xero.com/0/article/Reconcile-your-bank-account) - [Xero Central: About bank rules](https://central.xero.com/0/article/About-bank-rules) - [Xero Central: How to use automatic bank reconciliation (UK)](https://central.xero.com/s/article/How-to-use-automatic-bank-reconciliation-UK) - [Xero Central: Export a list of uncoded bank statement lines](https://central.xero.com/0/article/Export-a-list-of-uncoded-bank-statement-lines) - [Xero Central: Bank Reconciliation Detail report](https://central.xero.com/s/article/Bank-Reconciliation-Detail-report) - [Xero Central: Fix an incorrectly reconciled bank statement line](https://central.xero.com/0/article/Fix-an-incorrectly-reconciled-bank-statement-line) - [Microsoft Support: XLOOKUP function](https://support.microsoft.com/en-gb/office/xlookup-function-b7fd680e-6d10-43e6-84f9-88eae8bf5929) - [Microsoft Support: COUNTIFS function](https://support.microsoft.com/en-gb/office/countifs-function-dda3dc6e-f74e-4aee-88bc-aa8c2a866842) - [ICAEW: Generative AI guide, do's and don'ts](https://www.icaew.com/technical/technology/artificial-intelligence/generative-ai-guide/dos-and-donts) ## Questions people ask ### Can AI do bank reconciliation? Your accounting software does the matching: bank rules, suggested matches and, in Xero, JAX's automatic reconciliation. A general AI assistant helps with the leftovers, from descriptions only, and with queries, Excel formulas and the checklist. A person approves and posts. ### How does Xero's automatic bank reconciliation work? Once switched on for a bank account, JAX reviews future statement lines (not historical ones) and reconciles those that meet high-confidence criteria. Each is labelled Rule, Match, Memory or Prediction, and you can hover the label to see its reasoning and fix any mistakes. ### What can I safely give ChatGPT for a bank reconciliation? The date, a rough amount band and the description text for each unmatched line, plus column headings when you want formulas. Never account numbers, sort codes or the names of customers, suppliers or staff. ### How do I compare a bank CSV with a ledger export in Excel? Put each on its own sheet and ask AI for formulas from the column headings only: XLOOKUP to find a ledger row with the same date and amount, and COUNTIFS to flag rows with no match or more than one. Test the formulas on rows you can check by eye. ### When should I use a bank rule rather than find and match? Use bank rules for recurring lines you won't raise a bill or invoice for. If a line relates to an existing invoice or bill, match it instead, or you can end up with duplicate transactions and the invoice still showing as awaiting payment.