Read bank statements – every entry with its source

Not every bank statement arrives as a file your accounting system can import: archived statements, statements from other banks and remittance advices for batch payments come as PDFs or scans. Excalitract reads account, period, balances and every single entry according to your schema. Matching against open items is then done by your accounting or reconciliation tool.

From bank statement to list of entries

From bank statement to list of entries
1 / 3Bank statements and remittances

Statements as PDFs or scans and remittance advices for batch payments – with many pages and lines.

One remittance, forty invoices

One batch payment, one remittance advice, dozens of invoice numbers with discounts and deductions. Excalitract captures every line separately – the basis for your tool to allocate the payment to open items.

Balances have to add up

Opening balance, entries and closing balance are captured separately, every value with its source. If the total does not add up in your reconciliation tool, you find the entry in question directly in the original.

Illegible stays open

If an amount on a scan cannot be read, the field stays empty and goes to review – instead of distorting the balance as a zero.

Explained briefly

Bank statements and remittances in one minute

From page to list of entries

Statement, entry, remittance line – every level as a list

A bank statement contains entries, and a batch payment points to a remittance advice listing many invoices. Excalitract maps both in the schema: header data and balances per statement, the entries below them, and the individual invoice references with deductions in the remittance advice. Your reconciliation tool gets clean rows instead of a PDF.

  • Entries as a list Every entry is a row – with date, amount, counterparty and source.
  • Remittances down to the invoice Every invoice reference in the remittance becomes its own row, with discount and deduction.
  • One sheet per level In the Excel® export, statements and entries sit on separate sheets, linked by IDs.
  • Bulk approval Approve many statements at once – open required fields block approval.
Bank statement becomes a list of entriesPeriod, closing balance and an entry with its payment reference are extracted with their sources from a bank statement and handed over as a list of entries. A batch payment is flagged because its invoice references are in the related remittance advice.Period1–30 Sep 2026Closing balance€48,215.37Entry of 14 Sep−€12,480.00Payment referenceBatch payment, 14 invoicesEntries · September 20262 Sep warehouse rent−€3,950.008 Sep Sample Ltd+€7,140.0014 Sep batch payment−€12,480.00Closing balance€48,215.37Batch payment – the invoice references are in the remittance advice.

Every entry with its source

Date, amount and payment reference stay linked to their line in the statement. You resolve questions from reconciliation with one click on the original.

Extracting a value with its source locationIn the original document, the location of a value is highlighted. A line connects the highlight to the extracted field “Consumption 2025: 48,210 kWh”, which carries the source location page 2, line 14.Page 2Field: Consumption 202548,210 kWhSource: p. 2, line 14From value to sourceHighlighted in the originalExtracting a value with its source locationIn the original document, the location of a value is highlighted. A line connects the highlight to the extracted field “Consumption 2025: 48,210 kWh”, which carries the source location page 2, line 14.Page 2Field: Consumption 202548,210 kWhSource: p. 2, line 14From value to sourceHighlighted in the original

Ready for matching

You export approved statements as Excel® or JSON, or hand them over via REST API to your accounting or reconciliation tool. Matching against open items happens there.

Export to your systemsApproved records flow from the result table into four targets: an Excel® file with one sheet per list level, JSON for further processing, the REST API for your business system and the MCP server through which AI agents work with Excalitract directly.Approved dataDocument · Field · Value · StatusXExcel®one sheet per list level{ }JSONincl. review statusREST APIfor your business appMCP serverfor AI agentsExport to your systemsApproved records flow from the result table into four targets: an Excel® file with one sheet per list level, JSON for further processing, the REST API for your business system and the MCP server through which AI agents work with Excalitract directly.Approved dataDocument · Field · Value · StatusXExcel®one sheet per list level{ }JSONincl. review statusREST APIfor your business appMCP serverfor AI agents
Typical fields

These are the values Excalitract extracts for you

Examples – you define exactly which fields are extracted in the schema.

  • Account holder, bank and account number
  • Statement number and period
  • Opening and closing balance with currency
  • Entries with date, amount and counterparty
  • Payment reference and remittance details
  • Remittance lines with invoice number, deduction and amount paid

Your result

  • Entries from PDF and paper statements as a structured list
  • Remittance lines with invoice numbers as a basis for matching open items
  • Handover to accounting and reconciliation tools as Excel® or via REST API
Demo

See Excalitract with your documents

No standard show: we prepare the demo for your documents and fields. Afterwards, you will know how Excalitract handles your document collection – and how you can measure it on a test set of your documents.