Bank Reconciliation Extractor

Extract the bank and book balances, reconciled balance, variance, reconciling adjustments, and cleared transactions from a bank reconciliation PDF.

The full guide: Deposits in transit on a bank reconciliation

How should we start?

Build with Talonic

Need to scale? Create an API key, then run this from your own code or an agent.

Create an API key

Free account required

Start with a document

Upload a file or pick a sample, and see the fields come back.

No signup · nothing stored

Questions about Bank Reconciliation Extractor.

How is this different from a plain bank statement extractor?

A bank reconciliation compares the bank statement balance to the company's book (general ledger) balance and explains the difference — it is the worksheet, not the statement. The extractor reads the bank statement balance, the book balance, the reconciled balance, and the reconciliation variance to be explained, which a raw statement does not carry.

Which balances and period fields come out?

The opening balance, closing balance, the statement period start and end, the period end (as-of) date, the credit or debit indicator on the closing balance, and the total amount of transactions in the period, all in the account currency (ISO 4217).

What account and sign-off details are captured?

The bank account number, IBAN, BIC, bank name, and account holder name, plus the statement ID, who prepared and who reviewed the reconciliation, and the reconciliation status (in progress, reconciled, or variance pending).

Does it break out the transactions and reconciling items?

Yes. A bank transactions table returns each entry's reference, booking date, value date, amount, currency, credit or debit indicator, transaction code, payment reference, and running balance, and a reconciliation adjustments table lists each adjustment's type, amount, description, and date.

What are the file limits and privacy terms?

PDF only, up to 10MB and 100 pages. Processed via the Talonic API for extraction only, not retained for training, and not shared. Download as CSV, XLSX, or JSON.

Doing this to one file, or to ten thousand?

The tool reads a single document. The platform reads the whole estate once and keeps it queryable — the same engine, with a memory.

See invoice data extraction if you run this for finance and AP teams, or the extraction API if you are building it in.