Industry field guide
Real estate lender payoff records for AI evaluation
A principal balance and a payoff quote are different records.
- Sector
- Finance and insurance
- 2022 NAICS
- 522292
- Practice pack
- Example and answer key (JSON)
- Updated
What this guide tests
Which amounts are documented for L-A, and does the packet provide a current day-12 payoff quote for that loan?
See the specimen and fields · Work through the fictional records
Task and source context
A principal balance and a payoff quote are different records. CFPB explains that a payoff amount can depend on when the obligation is paid and the items included in the quote. A real estate lender can test whether an assistant recognizes the stated quote window without producing new payoff instructions. CFPB payoff amount explanation
Invent a loan ID, a period-end statement, and a payoff quote with an explicit good-through date. Add a later quote for a similar loan. Ask which document is relevant on the exercise date, which amounts are documented, and whether staff must obtain a fresh quote. An expired quotation should remain visible with its actual status. Score dates and record type separately.
Omit borrower identities, property addresses, settlement information, confidential pricing, payment instructions, and account records. Have an authorized reviewer verify the fictional timeline.
Industry research
The U.S. Census Bureau’s industry definitions establish which activities these codes cover. The workflow sources in this guide describe the task or record type. Fiund’s pilot below uses fictional material to test a specific decision within that scope.
522292 · Real Estate Credit
This U.S. industry comprises establishments primarily engaged in lending funds with real estate as collateral.
Build a pilot sample
Set up this pilot
Create fictional loan balance and payoff records with distinct expiry dates. Query after one quote expires and grade the need for a current verified quote.
Prepare the test packets
- Start with the worked case. Use the fictional record types below as a guide to the source files you need. Give each packet a stable ID and save its source versions with it.
- Change one fact. Make one packet with enough evidence to answer the question and one where the evidence points to a different answer. Keep the other fields fixed so a reviewer can tell what changed.
- Remove the decisive evidence. Give the reviewer a third packet with a plausible near-match in its place. Have them write what can still be established and what evidence would resolve the rest.
Fields the reviewer needs
- Loan alias and record class
- Distinguishes balance from quote.
- Quote amount and good-through date
- Defines the stated validity window.
- Exercise date and renewal evidence
- Supports the current-status finding.
Use How to prepare a financial workflow data sample for AI to turn the specimen into a brief with a defined task, source and review owner.
Fictional exercise
A balance statement is not a payoff quote and an expired quote remains expired
An invented loan fixture contains arbitrary practice amounts without a property, borrower, usable account reference or payment instruction.
| Record ID | Source | What it records |
|---|---|---|
| PQ1 | Period statement | Loan L-A, day 1 principal balance 500 practice units. Record class balance statement. |
| PQ2 | Quote Q-A | L-A payoff quote 512 units, expressly good through day 10. No extension or later L-A quote supplied. |
| PQ3 | Review date and other quote | Requested date day 12. Quote Q-A2 for distinct loan L-A2 is 515 units, good through day 15. |
Question for the model. Which amounts are documented for L-A, and does the packet provide a current day-12 payoff quote for that loan?
Show the reference answer
PQ1 documents L-A's day-1 principal balance of 500 practice units. PQ2 documents a separate 512-unit payoff quote valid through day 10, so it is expired for PQ3's day-12 review. Q-A2 belongs to another loan and cannot extend L-A's quote. The supplied packet therefore lacks a current L-A payoff quote; request fresh authorized evidence rather than treating the principal balance or similar-loan figure as a replacement.
How to check the result
Ask for the answer, the record IDs that support it and any fact the evidence leaves unresolved. Have a reviewer compare the response against the reference before deciding whether the sample is ready to expand.
Errors to flag in this case
- Substituting principal balance for a date-specific payoff amount.
- Extending an expired quote by using another loan's later good-through date.
Change the inputs and run it again
Move the requested date to day 9. Require Q-A to be identified as within its stated window without generating payment instructions.
Score the decision and the evidence separately
Save the reviewer’s expected answer, supporting record IDs and unresolved fields in a separate answer key. Score the model on the decision, its citations and its handling of the deliberate gap. A correct answer citing a different case counts as an evidence error.
Before expanding collection, have a second reviewer run the same checks on the held-out packet. Keep related versions, views and exports of the same case together so they stay on one side of the training and evaluation split.
Check permission and scope
Use original fictional statements. Exclude settlements, private pricing, actual account data and all money-movement instructions.
Exclude real personal and financial data, credentials, underwriting decisions and individual eligibility conclusions.
Describe an authorized archive through Fiund’s existing-data assessment, or describe a new capture capability through the collection brief. The contributor agreement covers the terms for participation.
Sources and further reading
Resources for this workflow
Includes worksheet
How to prepare a financial workflow data sample for AI
Build a fictional or authorized finance example with the reporting unit and time cutoff intact.
Includes worksheet
Plan a sample of business data for AI
Describe the evidence without transmitting private account or customer information.
Company and program reviews
Use these reviews to compare sourcing, capture or evaluation approaches. Confirm the applicable program, accepted sources and terms with the provider.
Compare the approach
Scale AI review: data partnerships, Outlier and buyer services
Read the public financial-services partnership criteria and scope controls.
Compare the approach
Invisible Technologies review for expert-led AI training
Compare expert calibration and reviewer agreement for narrow financial document exercises.
Related industry examples
Industry guide · NAICS 522210
Credit card dispute status records for AI review
A credit appearing on a statement can be temporary.
Industry guide · NAICS 522299
Secondary-market loan tape revisions for AI testing
Two loan tapes may represent different dates or corrections to the same date.
Industry guide · NAICS 522220
Dealer-arranged finance contract data for AI testing
A dealership worksheet may describe a proposed deal while a finance company’s acceptance refers to a later contract.