Use caseMortgage lending

Mortgage application processing

A couple sends twelve documents through their broker on Friday night. An auto loan hides in the third statement, and Monday goes into retyping.

Incomes and debits are read on arrival, with their source lineThe undisclosed loan is found before the broker promises an answerThe analyst decides, within his lending authority

The assistantIncome extracted

Emily: $2,650 a month, stable over three months. Ryan: $2,180 base pay, the October $1,500 bonus set aside as non-recurring.

source · 6 pay stubs, tax return 2025
Actions on this loan file
The verdict on the file

A figure needs a person · the AI says which, with its line

01

The friction

At a glance

Emily and Ryan Parker's bank statements show the same debit three times, $212 to a consumer credit company on the 5th of each month, and their mortgage application lists no current loan. It may well be an oversight. The analyst simply reaches that line after retyping six pay stubs into a spreadsheet, by which time the broker has promised the couple an answer.

Now the documents are read on arrival. The AI extracts incomes and regular debits the moment the file lands, sets them against your lending policy and names what does not match. The analyst starts from figures and their sources, and keeps the credit decision.

Bank statement Sep 2026.pdfViewer
The line nobody disclosed. A monthly debit to Finauto on the statement, and what the reading pulled from the twelve documents.
Mortgage queueCase management
Nathan's Monday list. Four files in the mortgage queue, the Parkers' flagged by its AI verdict like any other column.

An analyst knows statements, figures and queues by heart. The Parkers' loan goes through because they reach him in the right order: the documents are read on Friday night, the missing schedule is asked for on Monday morning, and the decision is taken on verified figures. The acts below stay on LN-26-20417 until the decision reaches the lending system.

02

The reading

The broker submits on Friday evening. By Monday the incomes and the commitments are extracted and checked.

Step 1Intake

The broker's submission arrives through the API

Emily and Ryan Parker are buying a two-bedroom condo in Charlotte for $310,000. Their broker submits the application and twelve documents through the portal on Nov 6. The portal calls the repository API: a loan case is created, and each document is filed under its type and its borrower.

6 pay stubs2 tax returns3 bank statementsPurchase agreement
Loan LN-26-20417 · DocumentsCase management
Each document is tied to a borrower, so each income is read against the right person.
The file is in one place from minute oneNo zip file to unpack, no attachment to rename. The application and its papers land typed, in the right queue.
Step 2AI check

The pay stubs and the tax return are read

The AI extracts net pay, employer, employment type and start date from each pay stub, then checks the household income against the 2025 tax return. Ryan's October pay stub carries a one-time bonus of $1,500.

Your lending policy counts only recurring income, so the extracted figure for Ryan is his base pay of $2,180, and the bonus is set aside with the line it comes from.

Pay stub Oct 2026, Ryan.pdfViewer
Each extracted figure points to the pay stub line it was read on.
Nobody retypes a pay stubSix pay stubs become four fields on the case, each with its source. Nathan checks them instead of copying them.
Step 3AI check

The statements show a loan nobody disclosed

The AI reads three months of statements for regular debits, rejected payments and overdrafts, and compares the debits that look like a loan with the debts disclosed in the application.

A debit of $212 goes to a consumer credit company on the 5th of each month. The application lists no current loan, so the status written on the case is Attention required, with the three statement lines as evidence.

Bank statementsCase management
The debits are grouped and labeled. The one that matters is highlighted.
The gap is found while the broker can still answerThe undisclosed loan surfaces on Friday night, not on the analyst's third pass through the statements.
03

The gap

Nathan Cole picks up the file on Monday. One repayment schedule is all that stands between him and a decision.

Step 4Assistant

A summary before the details

Nathan asks the assistant to summarize the application. It gives the purchase, the qualifying income, the disclosed and found debts, and the scoring result your lending system returned through its API, each line with its source.

Loan LN-26-20417AI console
The ratios come from your scoring engine. The summary cites where each figure came from.
Add up one analyst's week. How many hours go into reading documents before the first credit judgment, and how many of those reads could have been checks?
The analyst knows the one open question at onceNathan does not read twelve documents to find it. The summary tells him what is settled and what is not.
Step 5Assistant

The request goes to the broker, drafted from the file

Nathan asks the assistant for a request to the broker. The draft names the Finauto debit, asks for the repayment schedule and the outstanding balance, and says why the end date matters. He sends it, and the case moves to Waiting for documents.

Loan LN-26-20417Case management
The request is filed in the case history, with its date.
The broker hears about it on Monday morningOne precise question, with the lines behind it. The couple is not left waiting for a denial they could have avoided.
Step 6AI check

The schedule arrives and the file is checked again

The broker uploads the schedule the next day: an auto loan of $10,500 signed in 2023, outstanding balance $3,220, last payment on Mar 5, 2028. It is filed on the same case. The AI checks it against the statements and updates the commitments, and the scoring engine is called again.

Disclosed and verifiedCase management
Nathan sees the application as disclosed and as verified, side by side.
The figures the decision rests on are verifiedThe gap between the application and the documents is written down, so the committee or the auditor can read it later.
04

The decision

The file is complete, and the credit decision belongs to the analyst.

Step 7Viewer

Check the schedule in the document itself

Before deciding, Nathan opens the schedule in the viewer next to the case. He asks the assistant how many payments are left, and the answer points to the line on page 2. He drops a note on it for the committee file.

Finauto schedule.pdfViewer
The note stays on the document, visible to everyone who opens it afterwards.
The doubt is settled in the documentNo download, no second application. The schedule opens beside the case, and the answer comes with its line.
Step 8Workflow

Nathan decides within his lending authority

Nathan approves the loan at a 34.6 percent debt-to-income ratio and records his reason: the auto loan ends in 2028 and the household saves $400 a month. The routing rule checks his lending authority. Above the 36 percent ceiling, the process would have opened a credit committee review as a child case, with every document and field.

Ceiling: 36%This file: 34.6%Authority: analyst level 2
Loan LN-26-20417Case management
The AI prepared the figures. The decision and its reason are Nathan's.
The lending authority is enforced by the processNathan does not have to remember his limit. The process routes on it, and the exception would carry the whole file.
Step 9History

The decision goes to your lending system, with its trail

On approval, the workflow passes the decision to your lending system through its API, where the commitment letter is produced. The loan case keeps its history: every figure the AI extracted, every change Nathan made, every document version, dated and attributed.

Loan LN-26-20417 · HistoryCase management
The trail is part of the file, readable for the life of the loan.
Audit questions are answered from the fileWhich income was counted, which loan was found, who decided and why: an examiner finds it all on the loan case.
05

Where each file lands

Credit stays a human call. What the AI returns is the file read against your lending policy, in one of three states Nathan can act on.

Complete

Every rule passes

Incomes consistent, debts disclosed, documents current. The case keeps one sourced line per check.

After that: the analyst checks the figures and decides.
Attention required

A figure needs a person

An undisclosed debit, a bonus counted as salary. The analysis says which, with the lines behind it.

After that: the analyst asks the broker; the check runs again when the document arrives.
Outside policy

A lending rule fails, and you know which

A ratio above the ceiling, a job still in its probation period. The AI lists what passes, then names the rule that fails.

After that: the file goes to the credit committee as a child case, whole.
The limits we set

It grants nothing. It denies nobody. It computes no score of its own. Across the nine steps on this page, the credit decision is taken by the analyst, within his lending authority and with his own trace.

The AI reads, checks, drafts and summarizes. The control is in how the process is written, with its authority levels and its committee path.

06

In numbers

Counted on the Parkers' file, twelve documents and one hidden auto loan. Your policy and your brokers will produce other counts.

0 pay stubsretyped into a spreadsheet. Six pay stubs become four fields with their sources.
Day 1when the undisclosed loan is found, before the analyst opens the file.
1 requestto the broker, with the three statement lines behind it.

Where these numbers come from. They are counted on the scenario described on this page, with example data. They are not a customer result.

What makes these gains possible

Zero wasted readingProductivityThe documents are read before the analyst starts. He begins from figures and their sources.
Zero hidden commitmentsCredit qualityDebits that look like a loan are set against the application on arrival.
Decision supportA person decidesSummaries and answers cite their sources. The decision and its reason stay with the analyst.
07

Who it helps

The analyst signs, the credit manager answers for the portfolio, the CIO wires the systems. Each of them weighs this differently.

Business operations

Credit analysts

Reading documents takes the week, and judging risk gets Friday afternoon.

  • Incomes and debits arrive extracted, each with its line.
  • Undisclosed commitments are flagged before you open the file.
  • The request to the broker is drafted with the evidence.
  • The summary lists every figure with its source.
Risk and credit

Credit managers

A figure in a credit decision is hard to defend when nobody can say where it came from.

  • The AI decides nothing. The decision is the analyst's, with its reason.
  • Lending authorities are enforced by the routing rule.
  • Exceptions go to committee with the whole file.
  • Disclosed and verified figures stay side by side.
IT and architecture

CIOs and architects

Broker portal, scoring engine, lending system: three integrations before anything works.

  • Applications come in through the API, from any broker portal.
  • Your scoring engine and lending system are called by API.
  • Reading and checking run as steps of the loan process.
  • Deployed on your premises or in your cloud, as your regulator expects.

Start small

With one document type. Take the bank statements, where undisclosed loans hide, and read them on arrival. A month of applications will show how many loans you were missing.

Your broker portal, your scoring engine and your lending system stay in charge of what they do today. The loan case connects them.

See it live

See it on your own applications

Bring a few anonymized loan files and your lending policy. We will read one with you on arrival and leave the credit call to your analyst.

The screens on this page are drawn to show one step at a time, with example data.

Uxopian Software helps organizations put AI to work across the systems they already run, without giving up control of their data, their infrastructure or their critical processes.