Trusted by teams turning documents into production data
Insurance
Traffic citations record who was stopped, what they were charged with, the fine, and when they have to answer for it. Every state, county, and municipality prints the ticket differently, and many arrive handwritten or scanned. Sensible converts citations into structured JSON for fleet safety, claims triage, and violation tracking.
Validated JSON
Schema-enforced output; every field matches your contract
Source coordinates
Every value links back to page + bounding box for audit
Per-document pricing
Predictable cost. No token-volatility surprises
Trusted by teams turning documents into production data
Citations look simple and parse badly. Layouts change at every jurisdiction line, the form is often filled by hand at the roadside, and the data that matters most, the violation code and the fine, hides in dense, abbreviated fields. Hybrid extraction reads the messy inputs; SenseML rules map every result to one schema.
01
A citation from Phoenix looks nothing like one from a New Jersey township. Field order, statute references, and form numbers change by state, county, and court. Some states list prior violations alongside the current offense. Each layout gets its own extraction config, and SenseML makes each one repeatable.
02
Most citations start as a carbon copy filled out by hand at the side of the road, then get faxed, photographed, or scanned before they reach you. Hybrid extraction combines LLM parsing for handwriting and degraded scans with deterministic rules that hold the output consistent, and flags low-confidence fields for review rather than guessing.
03
A single stop can carry several charges, each tied to its own statute code, description, and fine. Sensible reads the charges as structured rows, keeping each violation code bound to its fine and description instead of flattening the ticket into loose text.
Managed services
Solutions engineers handle plan, build, deploy, and adjust on your behalf. You see clean JSON in your API response. Same engine as self-serve, just with the configuration work outsourced.
What's included
01Plan.Engineers review your samples and pick the right method
02Build.SenseML configs written from your samples
03Deploy.Same engine as self-serve, ready for production
04Adjust.We update configs when formats shift or new edge cases appear
05Integrate.Help with custom integration into your downstream systems
Every fleet and claims pipeline maps citations to its own schema, so we build the config around your fields rather than a fixed list. These are the fields teams pull most often; we map whatever else your violation-tracking or underwriting workflow needs.
01
Citation & issuing
Citation/ticket number, issuing agency, officer name and badge, date, time, and location of the violation, court name and appearance date
02
Driver & vehicle
Driver name, license number and state, date of birth, address, plate number, VIN, vehicle year, make, and model
03
Violation & penalty
Violation code(s) and statute, charge description, speed and posted limit, fine per charge, total fine due, and response deadline
config.json
SenseML
{ /* SenseML: traffic citation extraction */
"fields": [
{
"method": {
"id": "queryGroup",
"queries": [
{ "id": "citation_number", "description": "citation number, ticket number, complaint no" },
{ "id": "violation_code", "description": "violation code, statute, ARS/VC section" },
{ "id": "fine_amount", "description": "fine amount, bail, total due" },
{ "id": "court_date", "description": "appearance date, court date, respond by date" }
// + driver, vehicle, and officer fields, mapped to your schema
]
}
}
]
}Sensible processes citations from any agency and any submission channel. New jurisdiction layouts can be configured in hours, and the extraction logic stays explicit in SenseML rather than buried in prompt tuning.
State police and DMV citations, county sheriff tickets, municipal and township courts, photo-enforcement and red-light notices, and multi-violation states like New York and New Jersey
Handwritten carbon copies, e-citation printouts, faxed and scanned tickets, phone photos, and PDF mailers from court systems
Answers about jurisdiction coverage, handwritten and scanned tickets, and multi-violation citation handling.
A single stop can carry several charges, each tied to its own statute code, description, and fine. Sensible reads the charges as structured rows, keeping each violation code bound to its fine and description instead of flattening the ticket into loose text.
Yes. Most citations start as a carbon copy filled out by hand at the roadside, then get faxed, photographed, or scanned before they reach you. Hybrid extraction combines LLM parsing for handwriting and degraded scans with deterministic rules that hold the output consistent, and flags low-confidence fields for review.
Citation number, issuing agency, officer, date, time, and location, court and appearance date, driver and vehicle details, and the violation codes, charge descriptions, and fines are all extracted. Custom fields can be added in SenseML to match your violation-tracking or underwriting schema.
Sensible processes citations from state police and DMV, county sheriffs, municipal and township courts, photo-enforcement and red-light notices, and multi-violation states like New York and New Jersey. Each layout gets its own extraction config, and new jurisdiction layouts can be configured in SenseML.
Start free
Free 14-day trial. No credit card required. Start extracting in minutes.