Subrogation demand intake
For Insurance recovery correspondence teams
Prepare claimant, incident, demanded amount and supporting references from a demand letter with fields you can edit. Liability decisions external.
25 free credits/month · No card needed
See the workflow and review checksInspect a document example.
Synthetic documents · Expected output- claimant name
- Example Claimant - synthetic
- respondent name
- Example Respondent - synthetic
- incident date
- 2026-09-30
- demand date
- 2026-09-30
- claim reference
- DEMO-CLAIM-0042
- demanded amount
- 1250
- demand basis text
- Demand basis text explicitly printed in the original synthetic source for reviewer context.
{
"claimant_name": "Example Claimant - synthetic",
"respondent_name": "Example Respondent - synthetic",
"incident_date": "2026-09-30",
"demand_date": "2026-09-30",
"claim_reference": "DEMO-CLAIM-0042",
"demanded_amount": 1250,
"demand_basis_text": "Demand basis text explicitly printed in the original synthetic source for reviewer context."
}A complete synthetic document with the visible values shown below. Real responses also include model-reported confidence, validation and result status. Test your own file with this schema.
When this work lands on your desk
A demand letter arrives for insurance recovery correspondence teams. The next step needs claimant, incident, demanded amount and supporting references, recorded under the correct document reference before the information enters your insurance operations register.
A demand includes an amount for repairs and another for loss of use. Keep the stated components without deciding liability or recoverability. This schema keeps the source labels and values explicit so the reviewer can resolve the issue before downstream use.
Start with the documents you already collect
- Demand letter PDFs
- Scanned or photographed demand letter pages
PDF, JPEG, PNG, TIFF, or WEBP. Send one file per extraction call; create separate schemas when the document types need different fields.
Define the fields
Open the starter schema. Edit field descriptions, mark the values your process requires, and save it in your account.
Extract at intake
Send the document and saved schema slug to
POST /api/v1/extract, or collect the file through a branded upload site.Hand off reviewed data
After checking claimant name, respondent name, incident date, your application maps the reviewed record into your insurance operations register. Keep the original document reference with the result. Liability decisions external. Dokyumi processes one file with a saved schema; your application owns record matching, business rules and updates to other systems.
A schema shaped around the next step.
Start with these fields, then adjust them to match your documents and destination system. The example above shows the data object you are asking Dokyumi to extract.
Download editable starter schemaChoose required fields for your process. The starter schema preserves any defined nested fields; refine line-item structures and test them on representative files.
| Field | Type | What to capture |
|---|---|---|
claimant_name | string | Claimant name exactly as printed in this demand letter. Preserve identifiers and qualifiers; do not look up or infer missing information. |
respondent_name | string | Respondent name exactly as printed in this demand letter. Preserve identifiers and qualifiers; do not look up or infer missing information. |
incident_date | date | Incident date explicitly printed in this demand letter. Keep it distinct from other dates; leave it empty if no calendar date is stated. |
demand_date | date | Demand date explicitly printed in this demand letter. Keep it distinct from other dates; leave it empty if no calendar date is stated. |
claim_reference | string | Claim reference exactly as printed in this demand letter. Preserve identifiers and qualifiers; do not look up or infer missing information. |
demanded_amount | currency | Amount requested by the sender, not an agreed debt, liability or settlement. |
demand_basis_text | string | Demand basis text exactly as printed in this demand letter. Preserve identifiers and qualifiers; do not look up or infer missing information. |
Give exceptions a clear path to review.
Dokyumi returns a model-reported confidence map, validation details, and a completed or review status for produced results. Check required fields and your business rules before passing data onward.
A completed extraction describes the extraction result. Your application and reviewers own matching, approvals, routing, and updates to other systems.
Read the response contractChecks for this process
- A demand includes an amount for repairs and another for loss of use. Keep the stated components without deciding liability or recoverability.
- Check incident date, demand date against their own printed labels; leave an unstated date empty instead of deriving it.
- Check demanded amount for signs, decimal placement and stated currency before any downstream calculation or posting.
Prove the fit on a representative batch.
Test demand letter examples from the layouts your team actually receives. Include the exception described here: A demand includes an amount for repairs and another for loss of use. Keep the stated components without deciding liability or recoverability. Compare the extracted claimant name, respondent name, incident date and any line rows with a reviewer's checked reference before enabling downstream actions.
Compare extracted values with a reviewer’s reference set. Record corrections, unresolved fields, review time, and credits used before connecting downstream actions.
The free plan’s credit limits apply. Assisted pilots are scoped with Dokyumi before work begins.
Expand when the next process is ready
Add recurring extraction capacity when demand letter intake becomes routine. Reuse this field contract for layouts that express the same information; create a separate schema when the next document has different fields or review requirements.
For a tailored implementation
Discuss document volume, page lengths and schema setup for insurance recovery correspondence teams. Bring difficult demand letter samples and the review requirements your implementation must preserve.
Talk through document mix and volumeStart small. Add capacity as intake grows.
All self-service plans include the REST API, upload-site webhooks, custom confidence thresholds, and schema inference. Choose by volume, schema count, and upload sites.
Each document uses one credit per 5 pages, rounded up. An 8-page file uses 2 credits. Self-service files can be up to 50 pages; larger files, custom-built schemas, and additional volume are quoted through Enterprise. Full pricing details
Questions about subrogation demand intake
Which fields can I capture from a demand letter?
The starter schema contains claimant name, respondent name, incident date, demand date, claim reference, demanded amount, demand basis text. Edit those definitions and choose your required fields before saving. Array fields include defined sub-fields so row values have a validation structure.
What needs review in subrogation demand intake?
A demand includes an amount for repairs and another for loss of use. Keep the stated components without deciding liability or recoverability. Check the original source alongside model-reported confidence and validation output; completion status describes the extraction result, not the business decision.
How does this data reach your insurance operations register?
Save the schema, then send one supported PDF or image to POST /api/v1/extract with its slug. The response contains the data, model-reported confidence, validation and result status. Your application maps reviewed values to the destination; upload-site submissions can use a configured webhook. Liability decisions external.
How do I test this workflow on my own documents?
Start free with 25 credits per month, 2 schemas, and 1 branded upload site. The starter schema opens in the schema builder after sign-up. Edit the fields, save it, and upload a representative file through your account or the extraction API. Account documents are stored according to Dokyumi’s privacy policy; contact hello@dokyumi.com for deletion requests and retention requirements.