Extract declaration pages to structured JSON

Declaration pages summarize who is covered, what is covered, for how much, and for how long. Every carrier formats them differently, with unique layouts and field structures. Use Sensible to get structured dec page data for policy management, renewals, and coverage verification.

Why declaration pages resist template-based extraction

No two carriers format dec pages the same way. Multi-line schedules, endorsement riders, and combined personal/commercial layouts require extraction that adapts to each carrier while enforcing a consistent schema.

Carrier Format Variation

Travelers, Hartford, Chubb: each produces dec pages with unique field placement, terminology, and page structure. The hybrid engine reads each layout with LLM flexibility, then validates against your target schema with deterministic rules.

Coverage Schedule Parsing

Coverage tables list limits, deductibles, and premiums in structures that vary across carriers. Horizontal tables, vertical tables, nested tables: Sensible extracts each line with its coverage type and amounts intact.

Endorsement Lists

Each endorsement form number, description, and premium adjustment modifies the base policy in a specific way. The extraction captures every endorsement as a separate structured item, linked to the underlying policy data.

Fields we extract

Standard fields ship in the template library. Add or remove fields to match your policy admin system.

Policy information

Policy number, named insured, mailing address, effective date, expiration date, carrier name, producer/agency, policy form

Coverage details

Coverage type, limit per occurrence, aggregate limit, deductible, premium per coverage, total premium, retroactive date

Endorsements and conditions

Endorsement form numbers, endorsement descriptions, additional insureds, mortgagee/loss payee, vehicle/property schedules


{ /* SenseML: declaration page extraction */
"fields": [
{
"method": {
"id": "queryGroup",
"queries": [
{
// Policy number from the dec page header
"id": "policy_number",
"description": "policy number, policy #"
},
{
// Named insured
"id": "named_insured",
"description": "named insured, insured name, policyholder"
},
{
// Total annual premium
"id": "total_premium",
"description": "total premium, total annual premium, policy premium",
"type": { "id": "currency" }
},
{
// Policy expiration date
"id": "expiration_date",
"description": "expiration date, policy period to, policy end date",
"type": { "id": "date" }
}
// Additional fields for coverage limits, deductibles, endorsements, etc.
]
}
}
]
}
Umbrella Dec Page

Umbrella or excess liability declarations showing underlying policy schedule.

Workers Comp Dec Page

Workers compensation declarations with class codes, rates, and experience modification.

Commercial Property Dec Page

Commercial property declarations listing locations, building values, and coverage forms.

Homeowners Dec Page

Homeowners insurance declarations showing dwelling coverage, deductibles, and endorsements.

Auto Dec Page

Personal or commercial auto declarations with vehicle schedules and coverage limits.

Supported declaration pages

Sensible's insurance template library includes dec page configurations across all major lines of business. New carrier formats can be added using SenseML without starting from scratch.

By line of business

Personal auto, homeowners, commercial property, general liability, workers compensation, umbrella/excess, professional liability

By carrier

All major carriers including Hartford, Travelers, Liberty Mutual, Chubb, AIG, Zurich, Nationwide, State Farm, and any specialty carrier

Trusted by operations and engineering teams at

Common Questions

Answers about dec page extraction across carriers and lines of business.

Does Sensible handle dec pages from any carrier?

Yes. Every carrier formats dec pages differently. Sensible's hybrid extraction adapts to each carrier's layout while outputting a consistent schema.

Can Sensible extract endorsement schedules from dec pages?

Yes. Sensible identifies endorsement sections and extracts endorsement form numbers, descriptions, and any premium charges associated with each endorsement.

Does Sensible handle multi-line dec pages?

Yes. Package policies with property, liability, auto, and umbrella on separate dec pages are each extracted with line-specific field configurations.

What coverage details does Sensible extract from dec pages?

Sensible extracts coverage types, limits, deductibles, premium per coverage, endorsement list, named insureds, and additional insureds from the declarations page.

Do you support webhooks?

Yes. Sensible sends extraction results to your webhook endpoint when processing completes. You can also poll the API for status.

Does Sensible support human review?

Yes. Sensible flags extractions with low confidence for human review. You can configure review thresholds and workflows.

What security certifications does Sensible have?

Sensible is SOC 2 Type II certified and HIPAA compliant. Data is encrypted in transit and at rest.

How long is document data retained?

Document data is stored indefinitely by default. Custom retention policies are available and can be configured for same-day deletion if needed.

Is there a free trial?

Yes. Sensible offers a 14-day free trial on the Growth plan. No credit card required to start.

How is pricing structured?

Sensible uses per-document pricing for predictable costs. No token-based billing or usage surprises. Volume discounts are available for higher throughput.

How do I integrate with Sensible?

Sensible provides REST APIs and SDKs for Python and Node.js. Most integrations take a few hours. Webhooks, Zapier, and direct API calls are all supported.

What file formats does Sensible support?

Sensible processes PDFs (native or scanned), Microsoft Word (DOC, DOCX), spreadsheets (XLSX, XLS, CSV), single-page images (JPEG, PNG), multi-page images (TIFF), and email bodies with attachments.

How accurate is the extraction?

Accuracy depends on document quality and configuration. Most production deployments achieve 95%+ accuracy with proper validation rules and confidence signals.

How fast is document processing?

Processing speed depends on document size, page count, OCR requirements, and which extraction methods are used. Simple single-page documents process in seconds. Larger or more complex documents that use LLM-based extraction take longer.