Use caseHomeowners insurance

Document inconsistencies and fraud

An invoice $500 above its own lines. A photo already paid on a claim from 2025. In a queue of forty claims a day, such things get caught by luck.

The AI flags what does not line up, and shows whereThe referral travels with every document and noteThe adjuster and the investigator decide, never the AI

What comes backDocument checks

The invoice lines add up to $6,350, and the total says $6,850. The plumber's visit is dated two days before the leak was discovered.

source · the invoice and the loss notice
Actions on this case file
The state of the documents

Something does not line up · the AI shows where, an adjuster reviews

01

The friction

The core idea

$500. That is how far the total on Gary Chandler's plumbing invoice sits above its own three lines, and it looks like any other invoice. One of his four photos was already filed on a claim paid in March 2025, which only surfaces if the same adjuster happens to remember it. When a doubt does come up, the referral is a pile of screenshots for the investigator to rebuild.

On every claim, the documents are checked the day they arrive. The AI flags what does not line up and points to the page, and a nightly pass over the repository finds files that already sit on another claim. The adjuster clears or refers each signal with a reason, and the investigator decides on the evidence.

Invoice DVP-2026-0418.pdfViewer
$500 too many. The invoice in the viewer, the gap highlighted on the page, the checks in front.
Compare documents · REF-26-0193Viewer
Two copies, one total apart. The policyholder's invoice next to the copy Desert Valley Plumbing sent the investigator.

Adjusters and investigators already use every one of these screens. What protects the honest customer is the order: the signal is raised on arrival with its evidence, the adjuster looks for a plain explanation first, and only what stays unexplained goes to the investigators. The acts below stay on CL-26-27731, one Phoenix condo and three signals.

02

The signals

The claim looks routine. The checks have run before Kyle Foster, the adjuster, opens it.

Step 1AI check

The invoice does not add up

Gary Chandler reports water damage in his condo in Phoenix and uploads an invoice from Desert Valley Plumbing for $6,850. The AI extracts the lines and the total, and checks that they agree. The three lines add up to $6,350.

Do the lines match the total?Is the invoice addressed to the insured home?Do the dates agree across documents?
Claim CL-26-27731 · Document checksAI console
A signal says what was found and where. It makes no judgment about the person.
The gap is found before the paymentNobody has to add up an invoice by hand. The $500 is named on the page where it sits.
Step 2AI check

The dates do not line up

The loss notice gives Sep 16 as the day the leak was discovered. The invoice says the plumber came on Sep 14. The AI reads the dates printed in each document and places them in order on the claim, so Kyle sees the sequence at a glance.

Claim CL-26-27731Case management
Dates can differ for honest reasons. The sequence helps the adjuster ask the right question.
The question to ask is readyKyle knows what to ask before he picks up the phone, and why.
Step 3Operations

A photo already filed on another claim

Every night, the operations engine runs a check across the claims repository and lists files that appear on more than one claim. This morning it lists one of the four photos: Bathroom floor.jpg is the same image file as one filed in March 2025 on claim CL-25-08214, under another policy.

The other claim belongs to another team. Kyle sees that the match exists and its reference. Opening that claim stays with the special investigations unit.

Duplicate files, Sep 19Operations engine
The check analyzes content in place. Nothing moves, and the report becomes the work list.
A reused photo is caught by the checkNobody has to remember a claim from eighteen months ago. The repository is read every night, within everyone's rights.
03

The adjuster's review

Three signals sit on the claim. Kyle looks for a plain explanation before anything else, and one call settles a third of it.

Step 4Case management

The signal with an explanation is cleared

Kyle calls Mr. Chandler with a neutral question about the dates. The leak started on Sep 14, the plumber came the same day, and he only reported it once the neighbor downstairs wrote about the stain. That matches the neighbor's letter. Kyle clears the date signal and writes the reason.

Signals on CL-26-27731Case management
The call note is filed on the claim, next to the signal it answers.
Ask your adjusters how many signals turn out to have an honest answer, and where they get to write that answer down today.
Most doubts end with a phone callClearing a signal is a normal outcome. The reason stays on the claim, and the honest customer is never referred.
Step 5Workflow

The rest is referred with the evidence attached

The invoice gap and the reused photo have no explanation yet. At the end of his step, Kyle launches an investigation from the processes he is allowed to start. The child case receives the claim's data and documents, the highlights and his call note. He holds the invoice payment, as your procedure asks, and releases the other lines of the claim.

Referral REF-26-0193Case management
Documents are transferred to the referral, not copied into an email.
The referral is built in one actionNo afternoon of screenshots. The investigator receives the claim as it stands, with every note in place.
04

The investigation

Diane Rollins, an investigator, picks up the referral the next morning and checks each signal at its source. Four steps, and a monthly tune-up.

Step 6Assistant

The referral is read in one summary

Diane opens REF-26-0193 and asks the assistant for a summary. Her role lets her open claim CL-25-08214 too: it was paid in March 2025, at another address.

Referral summaryAI console
The summary repeats the evidence, with its sources. The finding is Diane's to write.
The investigator starts at the sourceHer morning goes to checking the evidence, rather than rebuilding it.
Step 7Viewer

The invoice is compared with the supplier's copy

Diane asks Desert Valley Plumbing for their own copy of invoice DVP-2026-0418. It comes back the same day and is filed on the referral. She opens both copies side by side in the viewer: everything matches except the total.

Compare documentsViewer
The difference shows in the layout as well as in the text.
One comparison settles the invoiceThe supplier's copy is the evidence, filed with the email it came with.
Step 8Workflow

The finding is recorded, and the next decisions go to people

Diane records her finding for each signal. The claim is settled on the supplier's figures for the work that is proven, and the decision on the policy goes to the fraud committee as an approval task. Kyle gets the claim back with the finding.

Referral REF-26-0193Case management
Every decision here is signed by a person and dated in the history.
The customer's file is decided by peopleThe AI raised two signals. The finding, the settlement and the decision on the policy are three human signatures.
Step 9Reporting

The checks are tuned on what the signals became

Once a month, Sarah Bennett reviews the document checks. Her report counts, per check, the signals raised, cleared by adjusters and confirmed by investigators. The date check is often cleared, so she rewrites its instruction in the console: a gap under three days is now shown as information. The change needs no release.

Document checks, SeptemberCase management
Figures are sample values. Every call to the AI keeps its question, answer, model and date.
The noisy check gets quieterAdjusters stop clearing the same signal eighty times a month, and the useful checks keep their weight.
05

Where each file lands

A signal is a question about a document. Each claim ends up in one of three places, and the investigators only see one of them.

No signal

The documents line up

Amounts, dates and files agree. The checks leave no trace on the adjuster's path.

What follows: the claim follows its usual process.
Signal cleared

Something did not line up, and there is a reason

A late report, a typo on a date. The adjuster writes the reason on the claim.

What follows: the claim goes on, and the reason feeds the monthly review.
Referred

No explanation was found

The signal and its evidence go to the special investigations unit as a case of its own.

What follows: the investigator checks at the source; the committee decides on the policy.
What stays with people

It accuses nobody, refuses nobody and blocks no payment. Across the nine steps on this page, every decision is signed by an adjuster, an investigator or the committee, with their own rights and their own trace.

The AI extracts, compares and summarizes, and the operations engine lists duplicate files. The control is in how the procedure is written, so honest customers are never treated as suspects.

06

What it is worth

Counted on Gary Chandler's claim and its referral. A batch of auto claims or a stricter procedure would count differently.

3 signalsraised before the adjuster's review, two on arrival and one overnight, each pointing at the page or the file it came from.
0 screenshotsto build the referral. The documents and notes travel with the child case.
1 comparisonto settle the invoice: the supplier's copy against the policyholder's, side by side.

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

The three principles behind those numbers

Checked on every claimProductivityThe checks run on arrival and every night, so nothing depends on an adjuster's memory.
Evidence that travelsProcess reliabilitySignals, highlights, notes and copies live on the claim and its referral. Nothing waits in an inbox.
Decision supportA person decidesSignals and summaries cite their sources. Clearing, referring and deciding stay with people.
07

The people involved

An adjuster, an investigator and an architect all have to be comfortable with a fraud check before it touches real claims.

Business operations

Claims adjusters

Forty claims a day, and somewhere in them a doctored invoice you are expected to spot.

  • Signals arrive with the page and the amount they concern.
  • Dates from every document are laid out in order.
  • Clearing a signal takes a reason, and it stays on the claim.
  • A referral is one action, with everything attached.
Risk and compliance

Investigators and fraud managers

Referrals land as screenshots, and the first hour goes into rebuilding them.

  • The referral is a case with every document and note.
  • Two copies of a document compare side by side.
  • Every finding and decision is signed and dated.
  • Each check is counted on what its signals became.
IT and architecture

CIOs and architects

Every fraud tool you have seen wanted another platform and another copy of your claims.

  • The checks run inside the claims process, called by API.
  • The duplicate check reads the repository in place.
  • Rights apply before any document is read.
  • Your claims stay on your infrastructure, on site or in your cloud.

Start small

With one check. Take the invoice your adjusters add up by hand, and move the check to the door. Run it first on claims your investigators already closed, so the results can be judged against known answers.

Your claims system, your repository and your investigation procedure stay in place. The checks run inside them.

Next step

Test the checks on your own claims

Bring a batch of anonymized claims your investigators have already closed. We will show which signals the checks raise and how your team would review them.

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.