The 2026 Buyer's Guide to Intelligent Document ProcessingDownload →

Document extraction built for insurance engineering and operations teams.

Loss runs, ACORD forms, dec pages, and every insurance doc your pipeline handles. We've seen it all. Every field is validated, typed, and traced to its source.

50%+
of Sensible's customers in the insurance space
JSON
Validated against your schema
Minutes
To configure a new configuration
SOC 2
Type II · HIPAA on Enterprise
insurance_auto_dec_pages/farmers
Live in DevPublish configurationDocumentation ↗
MW
farmers_edited⤓⤒⊘▾ 100%▾ 1/2‹›
ExtractionValidations 0Errors 0
▤{ }▾
Auto Insurance Declaration Page
F
FARMERS
INSURANCE
Premiums / Fees
Effective8/13/2020 12:01 AM
Expiration2/13/2021 12:01 AM
Policy Premium$1,295.00
Fees$0.88
▶ Policy Premium and Fees$1,295.88
Vehicle Information
Veh. · Year/Make/Model/VINCoverageLimit / Deductible
1 · 2020 Kia Telluride 4D 4WD
5XYP5DHC0LG071111Comprehensive
Collision
Add’l Equipment$500
$500
$1,000
Coverage Information
CoverageLimitsPremium
Bodily Injury Liability$500K / $1M$439.70
Property Damage Liability$500K each accident$275.50
Medical Coverage$5,000 each person$24.70
Uninsured Motorist BI$500K / $1M$171.90
Comprehensive$71.60
Collision$233.80
1{
2"policy_number": "19221-09-11",
3"carrier": "Farmers Insurance",
4"policy_premium": {
5"value": 1295.00,
6"unit": "$"
7},
8"fees": [
9{
10"name": "Anti-Fraud Fee",
11"value": 0.88
12}
13],
14"total": {
15"source": "$1,295.88",
16"value": 1295.88,
17"validated": true
18},
19"effective_date": "2020-08-13",
20"expiration_date": "2021-02-13",
21"vehicles": [
22{
23"year": 2020,
24"make": "Kia",
25"model": "Telluride",
26"vin": "5XYP5DHC0LG071111"
27}
28],
29"coverage": {
30"bi_limit": "$500K/$1M"
31}
32}

Trusted by teams turning documents into production data

The platform

Sensible turns insurance documents into your data layer.

An API call sends a loss run, ACORD form, or dec page to Sensible. A SenseML config (yours, ours, or built together) defines what to extract. The platform returns structured JSON validated against your schema, with source coordinates per field. Engineers ship extraction in days instead of months. Operations teams stop re-keying. Compliance gets a clean trail.

API & SDKs

REST API with Python and Node SDKs, plus webhook support for async processing.

View the docs →

Off-the-shelf configs

get started in minutes using configs our team has already built for the most common doc types

Browse insurance configs →

Schema & provenance

Type validation, cross-field reconciliation, and source-coordinate trace per field. Every output is auditable.

Managed services

Don't want to own the configs? Sensible's team builds, tests, and maintains extractions for you.

Learn about managed services →
How it works

From document to structured data, in four steps.

The same pipeline whether you're running a 10-page ACORD or a 300-page loss run. Sync or async. Same auth, same schema contract.

Step 01

Send the document

POST a PDF, scan, or image to the extraction endpoint with the SenseML config that matches the carrier format.

POST /v0/extract
config: loss-run-v3
Step 02

Hybrid pipeline runs

Layout-based rules locate fields. LLM parsing handles ambiguous sections, tables, and prose. SenseML constrains both halves to your schema.

OCR → layout → LLM → type cast
Step 03

Validate every field

Schema enforcement, type checks, cross-field reconciliation, and confidence scoring. Low-confidence fields surface for human review.

schema → types → cross-ref → confidence
Step 04

Deliver to your stack

Validated JSON returns sync or via webhook. Plug into your underwriting workbench, claims system, rating engine, or warehouse.

{ fields: {…}, source_coords: {…} }
Insurance documents we extract

Deep expertise in the insurance space.

Click below to learn more about the most common use cases that we support. Don't see your specific use case? No worries, we can build configs for any document type

Loss run — sample extracted by Sensible

Loss runs

Multi-policy claim summaries, any carrier

View document type →

ACORD form — sample extracted by Sensible

ACORD forms

125, 126, 130, 140 across carrier revisions

View document type →

Declaration page — sample extracted by Sensible

Declaration pages

Limits, deductibles, premium breakdowns

View document type →

Policy endorsement — sample extracted by Sensible

Policies & endorsements

Coverage terms, with diff annotations

View document type →

Insurance quote — sample extracted by Sensible

Insurance quotes

Premiums, terms, comparable across carriers

View document type →

Commission statement — sample extracted by Sensible

Commission statements

Splits, schedules, agency hierarchies

View document type →

Summary of benefits — sample extracted by Sensible

Summary of benefits

Plan grids, coverage tiers, line by line

View document type →

Explanation of benefits — sample extracted by Sensible

EOBs

Benefits, payments, denials

View document type →

Browse the full insurance config library →
Partner with us

We build the extraction layer. You ship product.

Plenty of teams would rather not write document parsers, monitor model drift, or maintain configs across format changes. Sensible's services team can handle all of it.

What you give usSample documents · target schema · target throughput
What you get backA working extraction endpoint, configs in your environment, downstream integrations wired up
PricingSame per-document rate as self-serve. No separate build fees.
01

Custom configs

SenseML for any layout your team handles. Loss runs, dec pages, niche carrier forms, ad-hoc broker submissions. Versioned in your environment

02

Integration delivery

Webhooks, batch jobs, email-driven intake, downstream mappings into your underwriting workbench, claims platform, rating engine, or warehouse.

03

Drift & format maintenance

When a carrier changes a layout or a model's behavior shifts, we update the configs. Your pipeline keeps shipping. Engineering team stays on product work.

04

White-glove onboarding

High-volume teams get a dedicated solutions engineer through go-live. Schema design, test coverage on real documents, monitoring and alerting.

Talk to managed services →Schedule a call
Customer story

How Shepherd automated loss run extraction to increase underwriter productivity by 10x.

“Most solutions try to be a silver bullet for document parsing, and it works for easy documents, but they fail very quickly when you throw something complex, like loss runs, at them.”

Read the case study →
10xUnderwriter productivity
100%Accuracy on supported loss run formats
300+Page loss runs processed in under a minute
Insurance resources

How insurance teams build with Sensible.

Blog · Technical

Automating data extraction from loss runs

Multi-carrier loss run patterns and edge cases.

Blog · Tutorial

Extract data from declaration pages

Walk-through of dec page extraction with SenseML.

Blog · Customer

Ledgebrook transformed E&S underwriting

Speed of submission triage as the wedge.

Blog · Customer

Apollo Insurance: real-time renters price matching

From manual review to seconds of API calls.

Blog · Technical

Extracting data from certificates of insurance

COI parsing patterns and field validation.

Blog · Industry

Cyber insurance quote extraction

Quote-to-comparison automation.

SOC 2 Type II

Audited annually

HIPAA-ready

Available on Enterprise

Field-level provenance

Every extraction traceable

Per-document pricing

Predictable, no surprises

FAQ

Questions insurance teams ask.

What insurance document types does Sensible support?
Loss runs, ACORD forms (125, 126, 130, 140), declaration pages, policies and endorsements, insurance quotes, commission statements, claims forms, EOBs, and summary of benefits. Each ships as a starter config in the insurance library.
How does Sensible handle different carrier formats?
Each carrier layout is its own SenseML config. Configs are versioned, testable, and deployable through CI/CD. New carrier formats become new configs without changing your API integration.
Why not just prompt an LLM directly?
LLMs with structured outputs return syntactically valid JSON, but they don't enforce policy-period reconciliation, claim totals, or that a dollar amount actually appears on a specific page. Sensible runs deterministic validation on top of the model output and traces every field back to its source coordinates, so a downstream system never gets a hallucinated value.
How does this compare to building extraction in-house?
First version of an in-house build usually works. The cost shows up later: model deprecations, carrier format drift, prompt regressions, the audit trail you didn't build, the human-review queue you didn't design. Sensible runs that infrastructure so engineering time stays on your product. SenseML is open and MIT-licensed, so the configs are yours to fork if you ever want to take it back in-house.
Does Sensible meet insurance compliance requirements?
SOC 2 Type II certified. HIPAA on Enterprise plans. Field-level source coordinates per extraction support audits, regulatory compliance, and E&O defense.
How is pricing structured for insurance volumes?
Per-document pricing regardless of page count or complexity. Trials start on the Growth plan for 14 days. View pricing →
Get started

Start extracting insurance documents today.

14-day free trial on the Growth plan. Pre-built insurance configs included. No credit card required.

Start extracting free →Schedule a demo