Damage report extraction
Appraisals in. Figures out.
Upload damage reports and appraisals as PDFs or scans, forward them by e-mail or send them to the API. Parsevix returns the claim, the vehicle, the damaged parts, the repair costs and the replacement and residual value as structured data, ready for your claims system.
- Claim, policy and vehicle as fields
- Repair costs, replacement and residual value as numbers
- Your own fields, defined once
No credit card · 20 free pages every month
The fields to define
Your damage report schema, set up once.
There is no ready-made Damage Report category: you create one in your project, with fields like these 34. Every report after that comes back in the same shape. Without a category, Parsevix can extract without a schema and use the report's own labels as keys.
Dates come back as ISO dates and amounts as plain numbers. A field the report doesn't contain, such as the vehicle on a property damage report, is left out, not guessed.
Report
- report_numberstring
- report_datedate
- report_typestring
- damage_descriptionstring
Appraiser
appraiser_infoobject
- appraiser_namestring
- appraiser_companystring
- appraiser_addressstring
Claim
claim_infoobject
- client_namestring
- insurer_namestring
- claim_numberstring
- policy_numberstring
- damage_datedate
- damage_locationstring
- damage_causestring
Vehicle
vehicle_infoobject
- makestring
- modelstring
- license_platestring
- vinstring
- first_registrationdate
- mileagenumber
Damaged parts
damaged_partsarray
- part_namestring
- repair_methodstring
Repair costs
cost_summaryobject
- labour_costnumber
- parts_costnumber
- paint_costnumber
- repair_cost_netnumber
- vat_amountnumber
- repair_cost_grossnumber
- currencystring
Values and finding
- diminished_valuenumber
- replacement_valuenumber
- residual_valuenumber
- total_lossstring
- repair_duration_daysnumber
Made for claims handling
Every appraisal, the same fields.
Appraisers, garages and loss adjusters each write their reports their own way, often over many pages with photos. This is what Parsevix does with them.
The figures behind the decision
Repair cost, replacement value and residual value come back as numbers, next to the report's own total loss finding. Your system can put them on one scale and apply the threshold you work with.
Parsevix returns the figures the report states. It doesn't decide whether a vehicle is a total loss or check the appraiser's calculation.
- 02
Costs broken down
Labour, parts and paint, the net and gross repair cost and the VAT come back as fields of their own, so estimates from different appraisers line up.
- 03
Damaged parts as a list
Each damaged part comes back with its repair method, such as replace, repair or paint, as the report lists them.
- 04
Vehicle and property damage
Vehicle appraisals, short reports and property damage reports can share one category; the vehicle fields stay empty when a report has no vehicle.
- 05
Names and numbers masked
Names, addresses, claim and policy numbers, number plates and vehicle identification numbers are masked automatically before any text goes to the AI model and put back in your result. Detection catches most personal data, not necessarily every item.
- 06
No category yet?
Extract without a schema: Parsevix returns every field it finds, named with the report's own labels. Turn it into a category once you know the fields you need.
- 07
Reports in any language
The language is detected on every page. A report in another language fills the same fields, with ISO dates and plain numbers.
How reports get in
Upload them, forward them or send them from your system.
Dashboard
Upload reports as PDFs or scans. Check each result next to its page, with every value marked where it was printed, and approve it.
E-mail address
Paid plansEvery project gets its own address. Have appraisers send their reports to it, and each attachment becomes a document.
API
Send reports from your claims system and get the JSON in the same response, or receive results by signed webhook or through Zapier.
Request
curl https://parsevix.com/api/v1/extract \ -H "X-API-Key: $PARSEVIX_API_KEY" \ -F file=@damage-report.pdf \ -F category="Damage Report"
The request stays open until the document is read and answers with the JSON.
- POST /documentsUpload without waiting; the result arrives by webhook or callback.
- POST /extract-autoNo category: every field Parsevix finds, named as in the document.
- POST /classifyOnly the document's category, for 1 credit.
Response · trimmed
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
Damage report FAQ
Damage reports,
answered.
What claims teams ask before they send their first reports.
PDF, Word (DOCX), PNG, JPG and TIFF, up to 10 MB and 30 pages each. A longer report has to be split into files, and each part comes back as a result of its own.
No. Create a category in your project with the fields you need, such as the ones on this page; it takes a few minutes and is used for every report after that. Or extract without a schema and get the report's own labels as keys.
No. It extracts what the report states into fields. It doesn't judge the damage, check the repair calculation or decide on a total loss.
Photos are not analysed. Text printed in or under them, such as captions, is read like any other text.
One credit per page: a fourteen-page appraisal uses fourteen, photo pages included. Choosing the category is included, and if a document fails, its credits are given back.
Reports 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 turn on keeping them for the project. Your documents are never used to train AI.
Related use cases
Documents that travel with this one.
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.
Contract data extraction
Parties, dates, value and the main clauses of a contract.