Use caseDocument processing services

Capture for a processing center

Northgate captures mail for an insurer, a utility and a lender, each on its own setup. Every new client costs weeks before its first batch.

One capture line, one configuration per clientOperators open only the fields the AI is unsure ofNothing leaves before the quality lead signs

Actions on this batch
The capture line1,204 documents, 6 types

The batch is split document by document and classified on Cedar Valley's own scheme: meter cards, ACH authorizations, complaint letters.

source · batch B-26-3108, 3,615 pages
Where each document goes

A field is unsure or fails a rule · a person corrects it

01

What gets in the way

In a nutshell

Three contracts at Northgate Document Services mean three capture setups, three sets of templates and three sets of screens to learn. Clients now ask harder questions too: what share of fields a person checked, and how they know their documents never sat in another client's queue. Each new client is a new tool to learn, and each audit is a spreadsheet built by hand.

One capture line replaces the three, with a configuration per client: its own classification scheme, its own fields and rules, its own threshold and its own export. The AI classifies and extracts, operators check what it is unsure of, and the quality lead signs before anything leaves.

Validation · Cedar Valley WaterCapture
Page and values, side by side. The operator approves or corrects each value, and only the doubtful one needs her.
Northgate · Three contracts todayWorkspace
The cost of one setup per client. Before the single line, every count here grew with each contract Northgate signed.

Every batch on this line passes the same gates: a batch belongs to one client from intake, the AI reads it with that client's rules, people spend their time on doubt, and the export waits for a signature. The steps follow one Cedar Valley batch through them, then watch a fourth client join.

02

The intake

Morning at Northgate: scanned mail, email attachments and files sent by clients, eleven batches by 8:30.

Step 1Intake

Each batch arrives on its client's chain

By 8:30, Kwame Asante, operations manager, has eleven batches waiting. Each client has its own intake: a scanner output folder, a mailbox, a partner API. Each intake feeds that client's capture chain, so a batch belongs to one client before any page is read.

Scanned mailEmail attachmentsPartner API
Intake · this morningCapture
The client is known from the intake, before the AI reads a page.
Clients are kept apart from the first pageA Cedar Valley batch can only run on Cedar Valley's chain. Nobody sorts the mail by hand.
Step 2Capture

The batch is split and classified on the client's scheme

The AI splits Cedar Valley's 3,615 pages document by document, then classifies each one on Cedar Valley's own classification scheme. A complaint letter is a complaint letter for Cedar Valley, and a claim form is a claim form for Larkfield.

Batch B-26-3108 · ClassificationCapture
The scheme is the client's. Northgate does not force a common one.
The client's words, on every documentEach type matches what the client's own systems expect, so nothing is renamed on the way out.
Step 3AI check

Fields come out with a confidence, and the rules run

On each document the AI extracts the values the client asked for, up to fifty per document, assigns each a confidence level, and checks them against the client's rules. On a handwritten meter card, the reading is clear, but the account number has a smudged digit and fails its checksum.

Account number: 10 digits, checksumMeter serial: in Cedar Valley's listReading date: not in the future
Meter reading card · page 214AI console
The flag points to the field and says which rule failed.
The doubt is named before a person looksThe operator does not reread the card. One field is flagged, with the reason.
03

The people

The AI handles the clear pages. People set the rules, check the doubt and sign.

Step 4Configuration

One configuration per client, written once

Mei Chen, solution architect, keeps one capture configuration per client: its classification scheme, its fields, its rules, its confidence threshold and its model. Cedar Valley's contract keeps documents inside the network, so its configuration runs a small model on premises. She improves it with instructions and a few examples.

Configuration · Cedar Valley WaterAdmin console
Thresholds and the cases that need a person are set upfront, per client.
Count it the next time a client changes one form: how many of your tools does someone open before the next batch can run?
A change for one client stays with that clientMei edits Cedar Valley's configuration. Larkfield's and Brightway's do not move.
Step 5Validation

Operators work only their clients' fields

Sara Lindgren is on team blue, assigned to Cedar Valley Water and Brightway Lending. Her queue shows only those two clients; access is set by role and by client. She opens the flagged card, reads the digit on the image, types 1, and the checksum passes.

Validation queue · team blueCapture
Every correction is kept with the operator's name.
Human time goes to the doubtful fieldSara opens one field on one card. The rest of the batch did not wait for her.
Step 6Quality

The quality lead checks and signs the batch

Before a batch leaves, Dana Hart, quality lead, runs the checks each contract asks for. Brightway's contract sends every loan agreement to a person whatever the confidence: reviews can be triggered by document type. Dana reviews the open points, then signs.

Quality check · B-26-3108Capture
Nothing goes out without sign-off.
The signature is a person'sThe export waits for Dana. The misread complaint letter goes back to Mei as an example for Cedar Valley's configuration.
04

The delivery

Signed batches leave for each client's system, each client reads its own figures, and a fourth one joins.

Step 7Export

Each client receives its batch in its own system

Once Dana signs, the operations engine loads the documents and their approved values into each client's repository. Cedar Valley Water runs SharePoint, Larkfield Insurance runs FileNet. Brightway Lending loads its own system from the Excel file of approved values.

Export · todayOperations engine
The export runs only on a signed batch.
No export script per clientThe target is part of the client's configuration. A new target is a setting on the chain.
Step 8Reporting

Each client reads its own figures

Every Monday Kwame sends each client its report, built from the line's own records: documents processed, queues, delays against the agreed deadlines, fields corrected by a person. AI consumption is tracked by use, and each client is its own use.

Report · Cedar Valley WaterCapture
The same records, filtered per client, also give Kwame his staffing plan.
The audit answer is already builtWhat a person checked, and when, comes from the line's records. Figures on the dashboard are sample values.
Step 9Setup

A fourth client joins with a test batch

Northgate signs Ashcombe Housing, an affordable housing provider sending lease forms and repair requests. Mei creates its configuration with two types and a few examples, sets its intake and its export, and runs 200 anonymized documents. Kwame reviews the result with Ashcombe's manager before go-live.

Test batch · Ashcombe HousingAI console
Go-live waits for the client's agreement on the test batch.
A new client is a configurationSame line, same screens, same people. Ashcombe adds a row, with its own rules.
05

Where each file lands

No document leaves on the AI's word. Each one lands on one of three paths, set by that client's threshold and rules.

Straight through

Every field passes

Each value is above the client's threshold and every rule holds.

After that: the document waits for the batch sign-off.
Operator check

One field needs a person

A value under the threshold, or a rule that fails. The flag says which.

After that: a validation task for the team assigned to that client.
Exception

No type fits

The document matches nothing on the client's scheme.

After that: an operator classifies it by hand, and it becomes an example.
What the AI leaves to you

It signs no batch. It sends nothing to a client. It changes no client's rules. Across the nine steps on this page, the export starts only after the quality lead signs, with her name on the batch.

The AI splits, classifies, extracts and checks. The thresholds and the cases that need a person are set upfront, per client, so the control holds when volumes rise.

06

The gains

Batch B-26-3108 and the three contracts behind it supply these counts. Other clients and other forms will give you other ones.

1 capture linefor three clients, each with its own scheme, rules, threshold and export.
1 fieldopened by the operator on the Cedar Valley card. The other three passed on their own.
0 batchessent to a client before the quality lead signs.

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 rules behind the gains

Clients apart by designProcess reliabilityA batch belongs to one client from intake, and runs only on that client's configuration.
Human time on doubtProductivityOperators open only the fields under the threshold or failing a rule.
A signature on every batchA person decidesThe quality lead signs before the operations engine loads anything.
07

The people involved

A processing center moves its clients onto one line once operations, the head of service and the people at the validation screen agree, each for a reason of their own.

Administrator

Operations managers

One tool per client, and a staffing plan built from guesses.

  • One line, one queue view per client.
  • Queues, delays and deadlines in one place.
  • Reports per client from the line's own records.
  • A new client onboarded with a test batch.
Product leadership

Heads of service

Each new contract costs weeks before its first batch.

  • A client is a configuration on the same line.
  • Its own scheme, fields and rules.
  • Set up with instructions and a few examples.
  • A small model inside your network when the contract requires it.
Business operations

Operators and quality leads

You reread clear pages to find the one unclear field.

  • Only flagged fields reach your queue.
  • The page and the value side by side.
  • Your clients only, set by role.
  • Your signature releases the batch.

Where to start

With one client and one document type. Take the form your operators key most often and run a test batch of real, anonymized pages through its own configuration.

Then compare the flagged fields with what your team corrects today, before you move the next client.

Your move

See it on your own clients' batches

Send us a sample batch per client and the systems they load into. We will run a test line with you: intake, validation, sign-off and export.

The screens on this page are drawn to show one step at a time, with example data. Northgate, its clients and the people named are fictional.

Uxopian Software helps service providers put AI to work across the systems their clients already run, without giving up control of the data or the decision.