An auto underwriting file holds the application, licenses, registrations, motor vehicle reports and loss runs, plus fleet schedules for commercial accounts. Each value is traced to its source page.
LandingAI transforms documents into highly accurate, verifiable, structured data so teams can reliably automate document-intensive workflows.
The ACORD 127 holds 13 drivers and four vehicles, so a larger fleet adds vehicle and driver schedules, then a loss run from each prior carrier.1
Motor vehicle reports, violation descriptions and point systems differ by state, and so do registration cards. Each prior carrier prints its loss run in its own columns as well.
Listed drivers, garaging and mileage are checked against licenses, registrations and driving records. Unlisted drivers cause the most mispriced premium.2
The same Parse call reads an auto insurance application, a commercial auto declarations and a motor vehicle report. Every document type uses one set of APIs, with zero templates to build and zero models to train or fine-tune.
A new form, issuer or document type works on its first call, with nothing to configure.
If an issuer redesigns a form or a new version arrives, no pipeline changes are needed.
Upload a sample in the Playground; agentic reasoning will immediately understand it.
Parse reads application forms, vehicle schedules, motor vehicle reports and multi-page loss runs into structured Markdown, with their tables and checkboxes intact.
Parse API →Split takes the Parse output and separates the submission into its application, each schedule, each driver's report and each carrier's loss run, with the page range of each.
Split API →Extract returns drivers, VINs, garaging, violations and loss totals as JSON that matches the schema for each document type.
Extract API →Ground maps each extracted value to the block, page and bounding box it came from, so an underwriter checks a violation or an open reserve on the original page before rating the risk.
Ground docs →Trusted, high-volume processing of the documents involved in auto insurance underwriting requires handling diverse document types and layouts. A driver's license is very different from an auto insurance application, which is different from an auto loss run. The pipeline must provide high accuracy and consistent outputs across all of them.
Our agentic approach is able to reason over each document type and return structured hierarchical Markdown and JSON outputs that downstream systems can rely on.
Each document below links to a worked example. The documents and schemas are available in full on GitHub and you are welcome to use them for your own testing.
| Field | Source document | Used for |
|---|---|---|
| Driver name, date of birth and relationship to the insured | Auto Insurance Application | Driver reports ordered and household drivers checked |
| VIN, garaging ZIP, primary use and annual miles | Auto Insurance Application | Rating territory, use and mileage class |
| Prior insurance and driving history incidents | Auto Insurance Application | Answers compared with the driving record and loss history |
| Year, make, VIN and stated value | Vehicle Schedule | Fleet rating and physical damage values |
| License number, issuing state, date of birth and expiration | Driver's License | Driving record order and driver age rating |
| VIN, model year and make | Vehicle Registration | Vehicle rating and VIN match with the application |
| Registrant, address and expiration date | Vehicle Registration | Ownership and garaging territory |
| Scheduled vehicle, VIN, coverage limit and vehicle premium | Commercial Auto Declarations | Expiring fleet terms compared with the new schedule |
| License class, status and expiration | Motor Vehicle Report | Driver eligibility |
| Violation, conviction date and points | Motor Vehicle Report | Violation surcharges and driver rating |
| Suspension reason and effective date | Motor Vehicle Report | Driver acceptability |
| Crash date | Motor Vehicle Report | Accident surcharge review |
| Policy period, claim count and total incurred | Auto Loss Run | Loss frequency and severity |
| Loss date, cause of loss, claim status and outstanding reserve | Auto Loss Run | Open-claim exposure and loss patterns |
| Carrier, line of coverage and run date | Auto Loss Run | Prior coverage and how current the run is |
| Business name, entity type and jurisdiction | Business Registration | Named insured matches the legal entity |
| Listed name, sanctions list and programs | Sanctions Screening | Sanctions clearance before binding |
Auto underwriting leaders measure document work in three places: how fast a quote goes out, how much underwriter time goes to rekeying and how well each rate matches the evidence.
Brokers often market a commercial auto submission to several carriers at once, and a slow quote can lose the account. When schedules, driving records and loss runs are read in minutes, more submissions reach an underwriter and get a quote.
Drivers, VINs and loss totals are typed from schedules and reports into the rating system, often more than once. Extracted, grounded fields let underwriters start from the values and open the page only where one needs a closer look.
Unlisted drivers, misstated garaging and undisclosed violations leave a policy priced below its risk. Grounded values let rules and underwriters compare each application answer with the license, registration and driving record behind it.2
The best accuracy on the difficult documents other tools get wrong, such as messy scans, complicated tables, checkboxes and handwriting.
Every answer cites its sources. Values come back with an audit trail (page, bounding box, character range) so a human can review them.
Applies multi-step reasoning, and plans before it acts. Handles documents it has never seen before and adapts to variations.
Composable APIs that drop into any tech stack and can be called from anywhere. Easy to build on and embed in your pipelines and products.
Cost-competitive rates with complete price transparency. Spend controls before you run, and every job reports its exact cost.
Built for production and scale from day one. Fully observable and monitored, running securely in our cloud or yours.
Available on Team and Enterprise plans. VPC and on-prem deployment require an Enterprise plan.
