For insurers, claims teams and loss adjusters
The claim file, already summarised.
Claim forms, appraisals, repair invoices and police reports arrive as a pile of PDFs and scans. Parsevix sorts each document, reads it with names and plates masked for the AI model, and hands your claims system the figures as JSON.
- Every document of a claim sorted by type
- Personal data masked before the AI model
- Costs and dates as numbers for your system
No credit card · 20 free pages every month
- 1The claim file arrives
- 2Sorted and read, names masked
- 3Your claim summary fills in
Personal data
Masked on the way in, put back on the way out.
A claim is full of personal data. Before any text goes to the AI model, names, addresses, plates, policy numbers and bank details are replaced with placeholders. Your result comes back with the real values in place.
Detection catches most personal data, not necessarily every item. Health details in a medical report, such as diagnoses, do reach the AI model.
Appraisal and invoice
The estimate and the bill, line by line.
Labour, parts and paint come back as numbers from the appraisal and from the garage's invoice alike, so your system can set them side by side and see where the bill runs over.
Parsevix returns the figures each document states; comparing them, and deciding what to pay, stays with your system and your team.
Good to know
Before you send the first claim.
- 01
Photos stay photos
Pictures of the damage are not analysed. Text printed in or under them, such as captions, is read like any other text.
- 02
Garages and adjusters send directly
On paid plans each project gets an e-mail address; appraisals and invoices sent there are read like uploads, and you can limit it to the senders you allow.
- 03
Claims from abroad
The language is detected on every page, so a police report or invoice from another country is read in its own language.
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
Insurance FAQ
Questions from
claims teams.
What insurers, claims handlers and loss adjusters ask before they send claim files.
No. It reads what the documents state and returns it as fields. It doesn't judge the damage, check an appraiser's calculation, decide on cover or flag fraud.
One file is read as one document. Send each claim form, appraisal or invoice as its own file, up to 30 pages each, and each is sorted and read on its own.
Health data is a special category of personal data under the GDPR, and you need a legal basis to process it with a service like Parsevix. Names and numbers are masked where detection finds them, but diagnoses and treatments reach the AI model (Google's Gemini API, possibly in the USA). There is no HIPAA business associate agreement.
By signed webhook, through Zapier or by calling the API. There is no ready-made connector for a particular claims system.
One credit per page read: a fourteen-page appraisal uses fourteen. 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. Your documents are never used to train AI.
Document pages
The documents of a claim.
Damage report extraction
Claim, vehicle, damaged parts, repair costs and values from appraisals.
Invoice parser
Supplier, totals, VAT and every line item from invoices in any layout.
Medical record extraction
Patient, diagnoses, medications and lab results from medical records.