AI-Process Mortgage Document in Make
AI-Process Mortgage Document is a PDF4me AI module for Make that extracts structured data from a mortgage document PDF or image. It returns the lender, borrower and co-borrower, property address, loan amount, interest rate, term, appraised value, closing costs, and an ISO 8601 closing date, ready for loan processing and compliance workflows.
What this module does
PDF4me AI-Process Mortgage Document extracts structured data from mortgage document PDFs or images inside your Make scenario using AI. Supply a Deed of Trust, Promissory Note, or loan application and the module returns lender, borrower and co-borrower, property address, loan amount, interest rate, term, appraised value, closing costs, closing date, and projected payments as individually mappable fields, ready for loan processing, risk assessment, portfolio management, and compliance tracking. No template setup required.
Authenticating Your API Request
Every PDF4me module in Make requires a valid Connection. Create or select one that holds your PDF4me API key so the scenario can authenticate AI mortgage extraction requests securely.
Important Facts You Should Not Miss
Choose an Input Data Type, map the mortgage document, and optionally set Document Type. Output exposes lender, borrower, property, and loan fields for downstream processing.
What parameters does AI-Process Mortgage Document use in Make?
Required: Connection, Input Data Type, and Mortgage Document Name. The matching input field (Input Binary Field, Base64 Content, or Document URL) is conditional on the chosen Input Data Type. Document Type and Custom Field Keys are optional.
| Parameter | Required | What it does | Example |
|---|---|---|---|
| Connection | Required | PDF4me API connection. Click Add and paste your API key the first time. Reused automatically across all PDF4me modules. | My PDF4me connection |
| Input Data Type | Required | How the mortgage document is supplied. Binary Data reads from a previous module (most common). Base64 String accepts an encoded payload. URL downloads from a public link. | Binary Data |
| Input Binary Field | Conditional | Binary content of the mortgage document. Required when Input Data Type is Binary Data. Map from Dropbox, Google Drive, or an HTTP request Data field. | 1. Data |
| Base64 Mortgage Document Content | Conditional | Base64-encoded mortgage document. Required when Input Data Type is Base64 String. Supports .pdf, .png, .jpg, and .jpeg. | JVBERi0xLjQK... |
| Mortgage Document URL | Conditional | Public URL to the mortgage document. Required when Input Data Type is URL. The link must not require authentication. | https://example.com/mortgage.pdf |
| Mortgage Document Name | Required | Filename with the correct extension (.pdf, .png, .jpg, .jpeg). Used for format detection and AI processing optimization. | mortgage_2026.pdf |
| Document Type | No | Optional document type to improve parsing accuracy, for example Deed of Trust, Promissory Note, Mortgage Agreement, or Loan Application. | Deed of Trust |
| Custom Field Keys | No | Optional array of extra field keys to extract beyond the standard mortgage schema. | ["escrowAmount"] |
Output Fields
| Field | Type | What it contains |
|---|---|---|
documentType | String | Type of mortgage document detected, for example Deed of Trust. |
lenderName | String | Name of the lender or financial institution. |
propertyAddress | String | Complete address of the property being mortgaged. |
loanAmount | Number | Principal amount of the mortgage loan. |
interestRate | Number | Annual interest rate as a percentage. |
loanTerm | Number | Term or duration of the loan in months or years. |
loanType | String | Type of loan, for example Fixed Rate, Adjustable Rate, FHA, or VA. |
borrowerName | String | Name of the primary borrower. |
coBorrowerName | String | Name of the co-borrower, if present. |
appraisedValue | Number | Appraised value of the property. |
closingCosts | Number | Total closing costs associated with the mortgage. |
closingDate | String | Closing date of the mortgage in ISO 8601 format. |
projectedPayments | Array | Array of projected payment objects with principal, interest, and estimated total monthly payment. |
success | Boolean | True if the AI extraction completed successfully; false if it failed. |
message | String | Human-readable status message confirming success or describing the error. |
How do I set up AI-Process Mortgage Document in Make?
- Add PDF4me and select AI-Process Mortgage Document.
- Select Connection (or click Add to create one with your PDF4me API key).
- Choose Input Data Type: Binary Data, Base64 String, or URL.
- Provide the matching input field and set Mortgage Document Name with the correct extension.
- Optionally set Document Type (for example Deed of Trust) and Custom Field Keys to sharpen extraction.
- Click Save and run. The output exposes lender, borrower, property, and loan fields: wire them into a loan origination system, risk model, database, or compliance report.
Workflow Examples
Workflow ExamplesCommon Make scenario patterns using AI-Process Mortgage Document.
- A mortgage document is uploaded to a watched Google Drive folder.
- AI-Process Mortgage Document extracts lenderName, borrowerName, loanAmount, interestRate, and closingDate.
- A validation step checks loan amount and rate against expected ranges.
- A new loan record is created in the loan origination system and the loan officer is emailed a summary.
- A new mortgage application arrives with its closing package attached.
- AI-Process Mortgage Document extracts loanAmount, appraisedValue, and borrower details.
- A Make formula calculates loan-to-value and debt-to-income ratios.
- High-risk loans are routed to a manual review queue; the rest continue to approval.
- A scheduled scenario retrieves all mortgage documents due for review.
- An Iterator passes each file to AI-Process Mortgage Document.
- Extracted fields are checked against regulatory requirements.
- Non-compliant loans are flagged and a compliance report is emailed to the team.