Use caseRetail banking

Identity and address proofs on upload

Claire applies from her phone on Sunday. On Monday an agent sees her bill is four months old, and the account waits days for a new one.

Each proof is typed and read on uploadDates and names are checked against the bank's rulesThe agent clears every gap before the account opens

The capture resultIdentity check

Driver's license, valid until June 2031. Last name, first name and date of birth match what Claire declared in the app.

source · Driver's license, front and back
Actions on this onboarding file
The verdict on the proofs

One point needs a person · the check says which, with its source

01

What gets in the way

In a nutshell

How long does it take a bank to notice that a utility bill is four months old? For a Sunday application, about a day, plus however long the customer takes to answer. What fills the queue is proofs that are slightly off: a maiden name on the bill and a married name on the license, a street number that differs by one. Each one sends the file back and forth for a week.

The bank moves that check to the minute of upload. The AI recognizes each proof, extracts its dates and names, and runs the rules compliance wrote: which proofs count, how old they may be, what must match. Karim starts from a verdict with its reasons, clears what he can, and decides before the account opens.

Electric bill.pdfViewer
Sunday, 19:43. The bill is read a minute after upload, and the two points that stop it are marked on the page.
Onboarding OB-26-31207Case management
Under fifteen hours. Claire's whole file on one line of time, with a single request to her in the middle.

None of these screens is new to an onboarding team. The gain sits in their order: the proofs are checked when they arrive, the gaps reach the agent with their reason, and the account opens on a file a person has cleared. We follow Claire's application below, one proof at a time.

02

The identity proof

Claire uploads her proofs on Sunday evening. The license is read and checked within the minute.

Step 1Intake

The app sends the proofs through the API

Claire photographs the front and back of her driver's license, then uploads a PDF electric bill. The bank's app calls the repository API: an onboarding file is created, and each document lands in its slot.

Driver's license, frontDriver's license, backProof of address
Onboarding OB-26-31207Case management
Each proof lands in its named slot, so the checks know what to look for.
The file exists from the first uploadNo email with attachments, no folder on a share. The proofs and the declaration sit together, in one onboarding file.
Step 2AI check

The card is recognized and its fields extracted

The AI recognizes a state driver's license and extracts the fields the checks need: last name, first and middle names, date of birth, license number, issue date and expiration date. Each field comes with its confidence and its place on the image.

Driver's license, frontViewer
Each field points to its zone on the photo, so the agent checks it on the image.
Nobody keys in a license numberThe fields come off the image with their source. The agent reads them on screen and checks the photo only when a rule asks.
Step 3AI check

The identity rules run before anyone looks

The checks are the bank's own, written by compliance in plain language: is this an accepted identity document, is it valid today, do the name and date of birth match the declaration.

Is the document on the accepted list?Is the expiration date after today?Do name and date of birth match the declaration?
Identity checksAI console
Each check writes its reason in a sentence the agent can verify.
A valid license goes no furtherMost identity proofs pass on upload. The agent does not open them, and the check stays on the file for compliance.
03

The proof of address

An address proof has its own rules: who issued it, how old it is, and whether it matches the declaration. This one fails two of them.

Step 4AI check

The bill is read and its date checked

The AI recognizes an electric bill and extracts the account holder, the service address and the issue date. The bill is dated July 8, 2026, four months ago. The bank accepts proofs up to three months old.

Electric bill.pdfViewer
The date and the holder are highlighted where they were read.
The old bill is caught on Sunday nightThe problem is known the evening it arrives. The request can go out first thing Monday.
Step 5AI check

The last name gap comes with what may explain it

Lowell on the license, Garner on the bill. The check looks across the documents on the file and finds the middle name on the license: Garner. It writes that the bill is likely in Claire's maiden name, points to the field, and leaves the check open.

Name comparisonAI console
The AI proposes a reading. The agent confirms it on the image.
The gap arrives with a leadThe agent does not start from a bare mismatch. She starts from the line that may settle it, and checks it.
Step 6Workflow

The weekend's files wait sorted by verdict

On Monday at nine, Karim opens his onboarding queue. Files marked Complete have already moved to the account opening step. He filters on Attention required, sorted by the age of the application.

Complete: 146Attention required: 61Not eligible: 7
Onboarding queueCase management
The verdict and its reason are columns, so Karim knows what to look at before opening.
Monday starts on the files that need a personThe clean files are already on their way. Karim spends his morning on the sixty-one with a reason attached.
04

The agent decides

One check to confirm, one proof to replace, then the account. Compliance closes the act with a rule update.

Step 7Viewer

Karim confirms the maiden name on the license

Karim opens the license in the viewer and zooms in on the name block: Garner is printed as her middle name. He clears the last name check with a note. Only onboarding and compliance can open these images, and each opening is recorded.

Driver's license, frontViewer
The note stays on the document. The rights follow the role.
The cleared check carries a nameCompliance can see who cleared it, when, and on which line of which image.
Step 8Assistant

The request for a new proof is drafted

The bill date cannot be cleared. Karim asks the assistant for a request to Claire. The draft says what is fine, what is missing and which proofs she can send instead, taken from the bank's list. He sends it to the app.

Onboarding OB-26-31207Case management
The request is filed in the file history, with its date.
One number to find: how many applicants give up when the first request reaches them three days after they applied?
Claire hears about it on Monday morningThe request names one document and why. She can answer from her phone the same day.
Step 9AI check

The new proof arrives and the check runs again

Claire uploads her October internet bill an hour later. It lands in the same slot, the address checks run again on it, and the status moves to Complete. The file moves to account opening.

Capture verdictAI console
The first bill stays on the file as an earlier version, for the compliance trail.
The account opens the day after she appliedKarim opens the account on a file where every check has passed or been cleared by a person.
Step 10Settings

Compliance keeps the list of accepted proofs

Sylvia, the compliance officer, owns the rules. This month she adds the latest W-2 or 1099 to the accepted proofs of address. The change is a sentence in the rule, live for the next upload, with no release.

Because these are identity documents, the bank runs the extraction model on its own premises. No image leaves its network, and every call is logged with its model and its date.

Rule: proof of addressAI console
The rule is plain language. Its history shows who changed it, and when.
Compliance owns the rules, and can read themWhat the check accepts is written where Sylvia can open it, change it and show it to an auditor.
05

What comes out

Each application lands in one of three states. Only the middle one needs Karim, and it tells him which proof to look at.

Complete

Every check passes

Accepted proofs, valid dates, names and address that match. Each check leaves its reason on the file, and the application goes on to account opening.

What follows: the file moves to account opening, where an agent opens the account.
Attention required

One point needs a person

A bill too old, a name that differs. The check says which, with the document and the line.

What follows: the agent clears it or requests a new proof; the check runs again when it arrives.
Not eligible

A proof is refused, and you know why

An expired passport, a document not on the list. The AI lists what passes first, then names the rule that fails.

What follows: the agent decides what to ask for, and the customer is told why.
What the AI does not do

It opens no account. It refuses no applicant. It clears no gap on its own. Across the ten steps on this page, every decision on the file is taken by an agent, with their own rights and their own trace.

The AI recognizes, extracts and checks. The rules are written by compliance, and the identity images stay on the bank's own infrastructure when the bank requires it.

06

In numbers

Taken from Claire's application. Your own numbers will follow your list of accepted proofs and your weekend volume.

0 fieldskeyed in from the proofs. Names, dates and numbers are extracted with their source.
Day 1when the new proof is requested, the morning after the customer applied.
1 fileopened by the agent for this applicant, with two checks to look at instead of three documents to read.

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 checks run on upload. The agent reads only what stopped, with its reason.
Zero lost proofsProcess reliabilityProofs, requests and replaced versions stay on the file. Nothing hides in a mailbox anymore.
Decision supportA person decidesEach verdict cites its document and line. Clearing a gap and opening the account stay with the agent.
07

The people involved

Onboarding, compliance and IT all sign off before a check like this goes live. Each gets something different out of it.

Business operations

Onboarding agents

Every photo gets looked at, just to find the one detail that is off.

  • Clean files move on without you opening them.
  • Each flagged file says which check stopped, and why.
  • The line that may explain a gap is pointed out.
  • The request to the customer is drafted from the bank's list.
Risk and compliance

Compliance and privacy officers

Approving a check you cannot read is out of the question.

  • The rules are yours, in plain language.
  • Every verdict and every cleared gap stays on the file, dated.
  • Identity images open only for the roles that need them.
  • The model can run on premises, so no image leaves the network.
IT and architecture

CIOs and architects

The app, the back office and the archive each keep a copy of the same license.

  • The app files the proofs through the API.
  • The check is a step in the onboarding process.
  • Question, answer and model are kept for every AI call.
  • Run in your own data center, or in the cloud if policy allows.

Your first move

With the proof of address. It fails most often, its rules are simple, and its date is easy to check. A few weeks of real uploads will show how many files go through clean.

Identity documents join the same check afterwards, with the list compliance already keeps.

Ready to try

Check your own proofs on upload

Bring your list of accepted proofs and a few anonymized samples. We will run the same checks on them with your onboarding and compliance teams.

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.