Give submission teams a usable loss history before renewal review
For Commercial insurance account managers and submission teams
Turn carrier loss run PDFs into consistent claim rows for the submission worksheet your account managers already maintain. Keep the report date, policy period, and printed financial labels together so the next reviewer can understand what each amount represents.
25 free credits/month · No card needed
See the workflow and review checks{
"named_insured": "Example Orchard Supply LLC",
"carrier_name": "Example Commercial Carrier",
"policy_number": "DEMO-LR-0042",
"policy_period": "2025-01-01 to 2026-01-01",
"valuation_date": "2026-08-15",
"claims": [
{
"claim_reference": "DEMO-C-019",
"loss_date": "2025-06-12",
"status": "Open",
"paid_loss": 4200,
"outstanding_reserve": 1800,
"total_incurred": 6000
}
],
"no_loss_statement": ""
}Synthetic data, not a live extraction. Real responses also include confidence, validation, and result status.
When this work lands on your desk
A commercial renewal reaches the submission stage, and the account manager receives loss runs from several carriers or policy years.
Loss history arrives in different table layouts. A report may put paid losses, expenses, reserves, and incurred amounts in adjacent columns, repeat policy information on continuation pages, or show a no-loss statement instead of claim rows. Copying only the totals strips away the context the submission reviewer needs.
Start with the documents you already collect
- Carrier loss run PDFs
- Scanned loss history reports
- Carrier no-loss statements
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 the source, your team maps approved rows into its submission worksheet or builds an API connection to its agency system. Customer-owned checks establish policy-year coverage and reconcile carrier labels.
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 |
|---|---|---|
named_insured | string | Name printed on this report; your team resolves account aliases. |
carrier_name | string | Reporting carrier as shown. |
policy_number | string | Preserve leading zeros and punctuation. |
policy_period | string | Printed period; do not substitute the report date. |
valuation_date | date | As-of date for the reported loss figures. |
claims | array | Rows with claim reference, loss date, status, and separately labeled amounts. |
no_loss_statement | string | Exact visible no-loss wording when present; absence is not a no-loss finding. |
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
- Check valuation dates before comparing reports from different carriers.
- Inspect wrapped claim rows and distinguish expenses from indemnity where the report separates them.
- Confirm whether an empty claim table reflects a printed no-loss statement, an incomplete report, or unreadable content.
Prove the fit on a representative batch.
Choose representative reports from a few carriers, including a continuation page and a no-loss example. Measure field correction time and missing-row frequency against your existing submission worksheet before expanding the schema.
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
Move to a paid tier when recurring renewals need more extraction credits, separate schemas for additional report structures, or branded upload sites for agency branches. Add declaration-page intake once loss-run review is stable.
For a tailored implementation
Discuss Enterprise when long histories, custom document volume, or a larger schema and portal rollout exceed the self-serve scope.
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 loss run submission intake
Will this calculate loss ratios or decide carrier appetite?
It extracts the values your schema requests. Your underwriting or submission process supplies premium data, calculations, interpretation, and carrier selection.
Can one report include multiple policy years?
A schema can request an array of policy sections and claim rows. Test the actual layout and preserve the period on each section; extraction does not establish that all requested years were supplied.
Can Dokyumi retrieve loss runs from carriers?
This workflow starts with documents you provide. Carrier retrieval and follow-up remain with your team or its systems; the extraction API accepts one supported PDF or image per request.
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.