Set Up Coverage Fields for Insurance Policies
Configure insurance policy fields in the dashboard — extract declarations, coverage tables, limits, and deductibles from policy documents.
Ready to set this up? Sign up for PerfectParser and get 20 free credits — no credit card required.
What this guide helps you do
This guide shows how to configure an insurance policy parser in PerfectParser, define declarations and coverage fields, run a test batch, and export policy data. After you upload a sample, field detection runs automatically. Compare the Schema tab with the recommended fields below and refine coverage field names.
Why insurance policies are hard to parse
Insurance policy packets stack declarations, endorsements, and coverage schedules in carrier-specific formats with no industry-standard layout. The declarations page holds policy number, insured party, and period — but limits and deductibles also appear per coverage line in a table that varies by line of business (commercial general liability vs property vs workers' comp). Per-occurrence limits are easily confused with aggregate limits when both appear in adjacent columns. Endorsement pages modify base declarations with rider language that does not repeat the full policy header. Premium, deductible, and coverage limit may use different formatting on the same page. Multi-carrier formats mean a schema tuned on one insurer's dec page will mislabel fields on another unless field descriptions name the exact label text (e.g. "Each Occurrence" vs "Per Claim").
Recommended Fields
We suggest configuring the following schema fields for your Insurance Policy Parser to capture all essential policy declarations.
| Field Name | Type | Description |
|---|---|---|
policy_number | Text | The unique policy number or identifier. |
insurer | Text | The insurance company name (e.g. Geico, Aetna, Allianz). |
insured_party | Text | The full name of the policyholder or insured business. |
policy_period | Text | The coverage dates range (e.g. June 1, 2026 to May 31, 2027). |
coverage_limit | Number | The overall maximum coverage limit of the policy. |
deductible | Number | The deductible or out-of-pocket amount. |
premium | Number | The total premium amount or cost of the policy. |
coverages | Table | Table containing coverage_type, limit_amount, and deductible details for each category. |
Set up this parser in the dashboard
Create a parser
Go to Parsers → New Parser in the dashboard. Give it a name like "Insurance Policy Parser". You can set the parser name while detection runs.
Upload a sample document
Drag and drop a representative declarations page (PDF, PNG, or JPEG). Use a dec page from a carrier you process regularly — the AI uses it to learn coverage table structure. Field detection and sample extraction start automatically.
Review detected fields
Field detection and sample extraction start as soon as the upload finishes. Open the Schema tab and compare detected fields with the Recommended Fields table above. Rename, remove, or add fields, and edit each field's instructions. Check sample values on the Results tab.
Review and save your schema
Check that coverages is a Table with separate limit_amount and deductible per row. Confirm coverage_limit reflects the correct limit type (per-occurrence vs aggregate) for your workflow. Click Save parser. You can edit fields later on the parser Fields tab.
Run a test batch
Open Run Extraction, choose how your files are organised, upload a small test set of policy documents, and click Start batch extraction. Review the run on the Results tab and export to CSV or Excel.
Common mistakes
- Using an endorsement rider as the sample when production files start with a declarations page — field placement differs completely.
- Mapping per-occurrence limits into coverage_limit when your workflow needs the aggregate cap (or vice versa).
- Omitting the coverages table and capturing only header-level premium and deductible — line-of-business detail lives in the table.
- Storing limit and deductible values as Text — use Number for comparison and reporting in certificate-of-insurance workflows.
Next steps
Test your first extraction free — sign up for PerfectParser, no credit card needed.
FAQs
Do I need a sample policy document to set up this parser?
Yes. Upload a declarations page from the carrier format you process most often. Policy packets combine declarations, endorsements, and schedules — start with the declarations page that contains policy number, insured party, and coverage summary.
Should I parse declarations separately from endorsement pages?
Configure your schema for the declarations page fields first — policy_number, insured_party, coverage limits, and the coverages table. Endorsement pages modify base coverage and use different layouts; handle them in a separate parser or batch if your workflow requires endorsement-level extraction.
How many credits does setup and a test extraction use?
Parser setup is free. Each policy page costs 1 credit. A declarations page alone is typically 1 credit; full policy packets with endorsements may use 5–20 credits depending on page count.
Looking for product features and use cases?