Help claims coordinators start a file from the first loss notice
For Claims intake coordinators and insurance service teams
Extract the reported facts from a submitted loss notice into a consistent intake record. Preserve the distinction between what the reporter wrote and what the claims team later establishes, with dates, policy references, and incident text ready for review.
25 free credits/month · No card needed
See the workflow and review checks{
"reported_insured_name": "Example Workshop LLC",
"policy_reference": "DEMO-POL-018",
"reported_loss_date": "2026-08-11",
"report_date": "2026-08-12",
"incident_location": "Example premises, rear loading area",
"incident_description": "Reporter states that water was found near stored packaging after heavy rain.",
"reporter_role": "Site manager"
}Synthetic data, not a live extraction. Real responses also include confidence, validation, and result status.
When this work lands on your desk
A policyholder or service representative submits a scanned notice, and an intake coordinator needs to prepare the initial claim record.
The first report can mix a loss date with a reporting date, include an uncertain incident time, or repeat identifiers in several sections. Staff need enough structure to start intake without converting tentative descriptions into established facts. Handwriting and abbreviated locations also create avoidable follow-up work.
Start with the documents you already collect
- Completed first notice of loss forms
- Scanned incident intake forms
- PDF versions of customer-submitted loss notices
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
An intake coordinator reviews the extracted notice, confirms required information, and enters or maps accepted fields into the claims system. Coverage, liability, urgency rules, and policy matching belong to the customer’s claims process.
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 schemaStarter fields are optional until you choose which are required. Nested line items need a defined structure if you want validation of their individual values.
| Field | Type | What to capture |
|---|---|---|
reported_insured_name | string | Insured name as supplied on the notice. |
policy_reference | string | Reported policy reference, without asserting a policy match. |
reported_loss_date | date | Loss date stated on the form. |
report_date | date | Date the notice states it was reported or prepared. |
incident_location | string | Preserve location qualifiers and partial addresses. |
incident_description | string | Reported description; do not infer cause or responsibility. |
reporter_role | string | For example, insured representative, when explicitly supplied. |
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
- Keep reporting date separate from loss date and retain uncertainty stated by the reporter.
- Review handwriting, overwritten dates, and partial policy references against the source.
- Treat blank incident details as missing information to follow up, rather than filling them from assumptions.
Prove the fit on a representative batch.
Evaluate a narrow class of typed loss notices first, then include representative scans from the same intake channel. Record which fields trigger follow-up and whether structured output reduces initial record preparation time.
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
Paid expansion fits recurring notice volume, separate schemas for different intake forms, and branded sites for business units. Your developers can use the JSON response in a custom claims intake integration.
For a tailored implementation
Discuss custom volume and deployment requirements before broadening into additional claims lines or sensitive document categories.
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 first notice of loss intake
Does extraction create a claim with the carrier?
No. Dokyumi returns structured data. Your team owns claim submission and any connection to a carrier or claims platform.
Can it determine whether the incident is covered?
Coverage requires a separate claims review. This schema captures reported facts and identifiers; it does not interpret policy coverage, assign fault, or approve a claim.
What should happen to a review response?
Inspect validation errors and low-confidence fields, then compare important values with the notice. Model-reported confidence is one review signal, and a missing confidence entry is not approval.
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.