Establish what an application is missing, pull income and obligations from the documents cited to source, and hand an underwriter a complete file — the credit decision and its reasons stay with a person.
Take the application as it arrives — branch, broker, portal or origination system — and record the date it was received.
02
Take in the documents supplied with it — pay records, tax and trading statements, bank statements and asset evidence.
Reason
03
Read income and obligations out of the documents and keep the page, date and line each figure came from.
04
Check the figures against each other and against what the applicant stated, and mark where they disagree.
05
Measure the file against the product's stated criteria and the documents that product requires.
Decide
06
List what is missing, stale or inconsistent, and what a named underwriter has to look at first.
07
Hold anything that would amount to a credit judgement, a score, a rank, a price or a reason for decline.
Out
08
Hand the underwriter a file with each figure traceable to its document, and the open items named.
09
Retain the application, the documents read, the extraction, the checks run, the clock and every correction.
→Product statement
The agent completes and evidences the file. Approving, declining, pricing, ranking an applicant and the reasons on any notice stay with named credit staff.
Example workflow
One application, end to end
AgentHuman
1Application receivedBranch, broker, digital channel or the origination system, with the date it arrived recorded
2Documents readPay records, tax and trading statements, bank statements, asset evidence and identification
3Income and obligations extractedEach figure kept with the document, page and date it came from, and the applicant's stated figure beside it
4File checked against the criteriaThe product's stated criteria and required documents, cross-document consistency, staleness and the clock
No human action required
Stages 1 to 4 run before an underwriter opens the file — intake, extraction and the checks finish first. Nothing in that stretch scores the applicant, ranks them or forms a view on the credit.
5DecisionSplits on whether the file is complete and internally consistent
Complete and consistent
Goes to an underwriter as a file ready to work.
Incomplete or contradictory
Held, with the gap named and the clock visible.
Underwriter or credit officer
Reads the file, each figure and the document behind it, then decides the application and owns the reasons on any notice that follows.
Take the file · Correct · Request information
File taken — handed back▼
6File handed over or the gap set outPassed to a named underwriter, or the outstanding items are written to the applicant's file with the clock
7Outcome evaluatedExtraction accuracy against the document, items missed, underwriter corrections, clock breaches and gaps by cohort
Corrections
Figures an underwriter re-reads from the document are counted.
What should not run autonomously
Human approval stays in control
Outside the boundary — human approval required8 items
Approving, declining or withdrawing an application.
The rate, the limit, the term or the price.
The reasons stated on an adverse-action notice.
Scoring or ranking an applicant.
Automation boundaryAgent acts unaided
✓Read income and obligations, and cite the document.
✓Check the figures against each other and the form.
✓Measure the file against the product's stated criteria and required documents.
✓Name what is missing or stale and keep the notification clock visible.
Write actions run only inside the approval boundaries agreed during implementation. The credit call is not one of them.
Deciding an income source counts, or how much.
Accepting a document that could not be verified.
Counteroffers, conditions and exceptions to policy.
Changing criteria, extraction rules or clock settings.
Example output
One application file, annotated
Everything the agent extracts is attached to the document and the page it came from.
Completeness output · single applicationIllustrative example
Applied for
Stated on the form
Documents
File status
Confidence
Credit decision
Fixed-term personal loan
Salaried, one employer
4 of 6
Incomplete — two items
88%
Not made by the agent
As receivedThe application as it was submitted and the documents attached to it — nothing on this side is inferred or rewritten.
Evidence usedPay record, page 2Bank statements, 90 daysStated income on the form
Why it is heldTwo required documents are absent and the pay record disagrees with the statements.
ActionTake the fileCorrectRequest information
What the score decidesHow hard the underwriter re-reads a figure against its source, not how the credit is decided.
Value
Where AI adds value
The same four claims, placed at the point in the workflow where each one applies.
Where the value landsValue 01 – 04
Every application receivedBranch, broker, portal or origination
03Completeness
Apply your own criteria
Measure the file against the product's stated criteria, the documents it requires and the figures the applicant supplied.
01Approved path
Hand over a worked file
Income and obligations arrive extracted and cited to the document, so the underwriter opens on the credit question instead of on data entry.
02Human review
Name the gap while there is time
Missing, stale and contradictory items surface early enough that the applicant can still supply them and the notification duty is met.
04Build an evidence trail
Retain the application, the documents read, each figure and its source, the checks run, the clock and the underwriter's correction — on both paths.
Integrations
Typical integrations
Five system groups connect to the same agent. Which of them are in scope is decided in discovery.
Integration availability depends on the client's existing systems and API access.
Agent controls
Six layers between the model and the credit file
Each control wraps the one inside it. A file clears every layer before an underwriter is asked to work it, and the credit decision sits outside all six.
L6 · Outermost — last line of defenceInward → L1 · closest to the model
L6Rollback / safe modeReturn the intake queue to unaided staff if evaluations or production signals degrade.Roll back
L5Clock and recordRecord the date received, the documents read, each figure and its source, and every correction.Record
L4Credit-decision gateApproval, decline, price, limit and the reasons on a notice stay with named credit staff.Gate
L3Attribute exclusionFields on your prohibited-basis and proxy list are excluded from what the agent reads and writes, and verification disparity is a standing test.Exclude
L2Consistency checksDocuments are read against each other and against the stated figures, and disagreements are marked.Compare
L1Source citationA figure is not presented unless the document, page and date sit beside it.Cite
Model coreFile assessed — the extracted figures, the document behind each one, what is missing and the confidence
L1 – L2Decide whether a figure may be shown
L3Excludes listed fields and tests for disparity
L4 – L5Keep the decision human and the clock visible
L6Pulls automation back when signals degrade
How Nestack evaluates it
Evaluate the file the underwriter gets — not only the figures on it.
Coverage runs the whole depth of the workflow, and every layer is cut by slice.
Surface — the file the underwriter opens
Depth of coverage ▼
E1Extraction evaluationDid each figure match the document it was taken from?
E2Completeness evaluationDid it name every item the product's criteria require?
E3Consistency evaluationWere contradictions between documents raised rather than averaged?
E4Disparity testingDo incompleteness and verification outcomes differ by group?
E5Slice evaluationHow does file quality change across specific application cohorts?
E6Business outcomeHow often was a file sent back, and did any clock run out?
Floor — the decision a credit officer has to defend
Failure modes
Where each failure originates in the agent
Seven failure modes plotted against the five stages of the agent lifecycle.
Agent lifecycleDirection of processing →
01 · Intake2 modes
LA-01
Application not logged as one
A worked-up enquiry starts no clock and is never reported.
LA-02
Altered document accepted
A regenerated pay record reads cleanly and enters the file.
Stage gathersThe application, the documents and the date received
02 · Extraction1 mode
LA-03
Variable income averaged wrong
Bonus, overtime or commission is annualised over the wrong period.
Stage readsIncome and obligations, each cited to its document
03 · Completeness2 modes
LA-04
Uneven proof burden
A verification step falls harder on one group of applicants.
LA-05
Clock spent re-checking
The file sits in re-extraction while the notification window runs down.
Stage checksThe file against the product's stated criteria
04 · Handover / write1 mode
LA-06
Gap handed over as a reason
A missing document is passed on as though it were the credit reason.
Stage handsThe file to an underwriter, or the gap to the file
05 · Change / Version1 mode
LA-07
Silent criteria drift
A product criterion changes and stale document rules stay in use.
Stage tracksModel, prompt, criteria and document-rule changes
Sev-1 · a duty owed to the applicant is missedSev-2 · a wrong figure reaches the underwriterSev-3 · the file degrades and work is redone
Rework concentrates in the files without a payslip
A salaried file with one employer and a clean pay record is close to solved. What comes back to be redone is the self-employed application, the seasonal one and the photographed pack. Nestack reports by slice, not only in total.
Slice performance — reported separately, not only in aggregateIllustrative example
Slice
Failure rate
Lift
Lift vs. threshold
Status
Self-employed and variable income
4.5%
2.9×
Review
Multiple or seasonal employers
3.4%
2.2×
Review
Photographed and scanned documents
2.9%
1.9×
Watch
Salaried, single employer
1.2%
0.8×
Normal
Bar: returned-file lift vs. single-employer baseline · scale 0–4.0× · tick marks the 2.0× review threshold2 of 4 slices over threshold
Evidence-linked improvement
A wrong figure is found by the underwriter, not by the agent
What tells you intake went wrong is the person who works the file next — a figure re-read from the document, an item asked for twice, a file that came back.
Improvement cycle · five stagesSwitchback — the path turns at Improve and returns at Learn
01Detect
Returned files, re-read figures or repeat requests rise in one application type.
02Diagnose
Read back against the document itself — the page, the extraction rule, the criteria list or the intake route.
03Improve
The extraction rule or the required-document list is re-approved by credit policy and version-linked.
04Verify
Replayed over past applications, including the files the underwriter sent back.
05Learn
The document that beat the extractor is kept, and the disparity test is re-run before release.
Learn → DetectThe return edge. Changing what the agent asks for changes who finds the process hard, so fair-lending testing runs on the change before it ships.
Typical build scope
Twelve workstreams across six weeks
The build scope read against the delivery timeline. Week structure follows the six-week plan — discovery, intake and extraction, the criteria and clock checks, evaluation, integration, then production validation and handover.
WorkstreamWeek 1Week 2Week 3Week 4Week 5Week 6
01Intake workflow and automation-boundary definition.
02Origination and document-system assessment.
03Product criteria and required-document lists.
04Application intake and receipt-date capture.
05Document classification and citation.
06Income and obligation extraction rules.
07Cross-document consistency and staleness checks.
08Protected-attribute field exclusion.
09Notification-clock capture and gap reporting.
10Extraction accuracy and disparity evaluation.
11Underwriter handover and integration.
12Observability, deployment and Agent Care handover.
12 workstreams · 6 weeks · bar shows the weeks a workstream is active — several run in parallelFinal scope and sequence confirmed in discovery
Engagement tiers
What each tier includes
Rows are the capabilities named in each tier's scope. Higher tiers include everything below them.
Capability✓ in scope · — not at this tierPilotOne product, one channelProductionOrigination integrationAdvancedMulti-product / multi-entity
Introduced at Pilot
Extraction cited to the document✓✓✓
Cross-document consistency checks✓✓✓
Completeness against your criteria✓✓✓
Protected-attribute exclusion✓✓✓
Credit decision left to an underwriter✓✓✓
Receipt date, clock and audit trail✓✓✓
Baseline evaluation✓✓✓
Introduced at Production
Origination and workbench integration—✓✓
Observability and evaluation—✓✓
Introduced at Advanced
Multiple products and criteria sets——✓
Multi-entity and enterprise controls——✓
Build priceFrom $5,000From $8,000Custom quote
Final build priceConfirmed after discovery based on products and criteria sets in scope, origination and document-system integrations, application volume, verification sources, approval controls and deployment requirements.
Separate from buildBuild pricing is separate from recurring Agent Care, which covers managed monitoring, evaluations, incidents and verified improvements after launch.
What we need from you
What you bring, and what we build with it
Each input maps to a piece of build scope and a week in the delivery timeline.
You bringWe build with it
01The products in scope and the criteria each one states→Product criteria and required-document listsWeek 1
02Access to origination, core and document systems→Origination and document-system assessment, then integrationWeek 2
03A representative set of what applicants actually send you→Document classification, page-level citation and the extraction baselineWeek 2
04How you calculate income for each employment type→Income and obligation extraction rulesWeek 3
05Your notification clocks and how a file is closed or withdrawn→Receipt-date capture, clock tracking and gap reportingWeek 4
06The applications your underwriters sent back last year→Evaluation suite, regression cases and failure-mode testingWeek 4
07Named underwriters and whoever owns fair-lending testing→Handover workflow, disparity testing, then supervised filesWeeks 5–6
Nothing else is requiredDeployment, documentation and Agent Care handover are ours.
Delivery timeline
Four phases across six weeks
Phases are drawn over the weeks they actually occupy. Week 5 carries both the last of the evaluation work and the first rebuilt files.
PhaseW1W2W3W4W5W6
DiscoveryW1
BuildW2 – W3
EvaluateW4 – W5
Pilot & LaunchW5 – W6
Week focusW1The products in scope, their criteria and the automation boundaryW2Intake, receipt-date capture and document classificationW3Income and obligation extraction, cited to the pageW4Consistency and clock checks, evaluation suite and disparity testingW5Files rebuilt from applications you decided last year, nothing sentW6Underwriters work from live files under review, then handover
Reading the bandExtraction accuracy and disparity testing are measured in week 4. Week 5 rebuilds applications you already decided, so nothing the agent produces reaches an applicant.
At the end of W6Underwriters have worked live files the agent prepared, with each figure checked against its document, then Agent Care takes over monitoring.
DurationSix-week plan shown · typical delivery 4–6 weeks depending on scope confirmed in discovery.
Next step · Banking AI agent
Build an application agent around your own credit criteria.
Show us one product's criteria, the documents your applicants actually send and the files your underwriters sent back. We'll rebuild a month of applications you have already decided, show you what the agent would have called missing, and where the notification clock would have stood.
