For lenders, brokers and credit platforms
The application file, read before review.
IDs, payslips, bank statements and tax forms arrive with every application. Parsevix reads each one and hands your underwriting system the figures as JSON, with names and account numbers masked before the AI model sees the text.
- IDs, payslips, statements and tax forms
- Pay, balances and transactions as numbers
- Decisions stay with your underwriters
No credit card · 20 free pages every month
- 1The applicant sends the documents
- 2Parsevix reads them, data masked
- 3Your underwriters see the figures
Payslips
Three payslips, one line of income.
Gross and net pay, deductions and the pay period come back from every payslip, whatever the payroll software that printed it. Put the months side by side and see the income at a glance.
There is no built-in payslip category: you define the fields once. Parsevix returns what the payslips state; checking them against your lending rules is your system's job.
Bank statements
Every transaction, for your rules to read.
With the built-in Bank Statement category every transaction comes back with its date, description and amount, next to the opening and closing balances. Your rules can then find the salary, the rent and the loan repayments.
The tags in the picture are your system's work: Parsevix returns the transactions as the statement prints them, it doesn't classify or score them.
Good to know
Before the first application.
- 01
Applicants' data
Names, ID numbers and IBANs are masked before any text reaches the AI model and put back in your result. Detection catches most personal data, not necessarily every item.
- 02
Authenticity
Parsevix reads what a document says. It doesn't check whether a payslip or statement is genuine or has been altered.
- 03
Long statements
A file can have up to 30 pages. A longer statement has to be split into files, and each part comes back as a result of its own.
Security & compliance
- PII maskedautomatically, before the AI step
- Encryptedin transit and at rest
- No AI trainingon your documents
- API files deletedafter processing
Priced per page, not per feature.
Every plan reads, sorts and masks documents the same way. Picking the category is included, and a document that fails costs nothing.
See pricing- credit per page
- 1
- free pages every month
- 20
- a month for 500 pages
- $39
Lending FAQ
Questions from
lenders and brokers.
What lenders, brokers and credit platforms ask before they send application documents.
No. It extracts what the documents state into fields. It doesn't score applicants, assess affordability or make or recommend credit decisions; those stay with your underwriters and your rules.
No. It reads the text of a document; it doesn't check whether a payslip, statement or ID is genuine or has been altered.
No. It reads the fields of an ID document, such as the name, number and dates. Verifying that the person is who the document says is not part of it.
By signed webhook, through Zapier or by calling the API. There is no ready-made connector for a particular loan origination or core banking system.
One credit per page read: a six-page bank statement uses six. Sorting documents by type is free, and a document that fails costs nothing.
Files uploaded in the dashboard or sent by e-mail stay in your project until you delete them. Files sent through the API are deleted after processing unless you keep them. Documents are never used to train AI.
Document pages