Trusted by teams turning documents into production data
Real Estate
The URLA (Form 1003) is the standard residential loan application — but borrower-completed forms arrive as scanned uploads, e-signed PDFs, and faxed bank copies. Income, asset, and property data sit across multiple pages and revision versions. Sensible converts any 1003 into structured JSON for LOS automation and underwriting.
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
Revision detection, multi-borrower handling, and validation against credit and asset documents demand more than pattern matching. Sensible reads the form, validates the fields, and ships clean JSON to your LOS.
01
The 2021 URLA redesigned the entire form. Legacy 1003s and the new URLA both circulate. Sensible detects revision year automatically and extracts using the right schema, so your LOS receives consistent JSON regardless of form version.
02
Joint applications with co-borrowers, non-occupant co-borrowers, and multiple borrower pairs need to be split into discrete borrower records. Sensible preserves the relationship between borrowers and their respective income, assets, and credit data.
03
Income totals must match line-item sums. DTI ratios must be consistent with declared income and debts. JsonLogic validations catch internal inconsistencies before the application moves to processing.
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 1003 is different, so we build the config around your exact schema rather than a fixed list. These are the fields mortgage teams request most; we map whatever else your LOS or underwriting pipeline needs.
01
Borrower identity
Borrower name, SSN, date of birth, citizenship, marital status, current address, mailing address, contact info
02
Loan and property
Loan amount, loan purpose, property address, property type, occupancy, estimated value, sales price, term, amortization
03
Income, assets, liabilities
Employment, base income, bonus/commission income, other income, asset accounts, liabilities, monthly obligations, REO schedule
config.json
SenseML
{ /* SenseML: Form 1003 / URLA extraction */
"fields": [
{
"method": {
"id": "queryGroup",
"queries": [
{ "id": "loan_amount", "description": "loan amount, amount requested" },
{ "id": "property_address", "description": "subject property address" },
{ "id": "annual_income", "description": "annual income, gross monthly income" },
{ "id": "loan_purpose", "description": "loan purpose, purchase or refinance" }
// + more fields, mapped to your schema
]
}
}
]
}Sensible processes every revision of Form 1003 / URLA, from the 2009 legacy version to the current 2021 redesign.
The Fannie Mae / Freddie Mac redesigned URLA: borrower information, financial information, real estate, declarations, and demographic information sections.
The pre-2021 Form 1003 still circulates in some portfolios. Version detection extracts using the legacy schema and maps to the URLA 2021 output shape.
Answers about URLA revisions, multi-borrower handling, and income validation.
Borrower identity, loan and property details, employment, income, assets, liabilities, REO schedule, and declarations are all extracted. Custom fields can be added in SenseML to match your LOS schema exactly.
Yes. JsonLogic validations check that income totals match line-item sums and that declared DTI is consistent with income and liabilities. Internal inconsistencies get flagged before the application moves to processing.
Joint applications, non-occupant co-borrowers, and additional borrower pairs are split into discrete borrower records. Income, assets, and credit data stay linked to the correct borrower.
Sensible supports the current 2021 URLA redesign and the legacy 2009 Form 1003. Version detection happens automatically; the legacy schema gets mapped to the URLA 2021 output shape so downstream systems receive consistent JSON.
Yes. Sensible sends extraction results to your webhook endpoint when processing completes. You can also poll the API for status.
Yes. Sensible flags extractions with low confidence for human review. You can configure review thresholds and workflows.
Sensible is SOC 2 Type II certified and HIPAA compliant. Data is encrypted in transit and at rest.
Document data is stored indefinitely by default. Custom retention policies are available and can be configured for same-day deletion if needed.
Yes. Sensible offers a 14-day free trial on the Growth plan. No credit card required to start.
Sensible uses per-document pricing for predictable costs. No token-based billing or usage surprises. Volume discounts are available for higher throughput.
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.
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.
Accuracy depends on document quality and configuration. Most production deployments achieve 95%+ accuracy with proper validation rules and confidence signals.
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.
Start free
Free 14-day trial. No credit card required. Start extracting in minutes.