HMDA & Lending-Data-Integrity AI Agent

What this agent does

Reconciles the register, not the decision

An application is taken, and it is ingested from the LOS beside the pricing, geocoding and credit-file records.

A field is coded — tract, rate spread, action taken — and each is reconciled to the system it came from.

Reason

A final action is taken, and the record reaches the register inside the thirty days § 1003.4(f) allows.

A file is priced, and the rate spread is checked against the APOR table in force that week, not a cached one.

A quarter is counted against the filing trigger — covered loans and applications combined, purchases excluded.

Decide

An edit fires in the platform, and it routes to a person to verify against the file, never cleared on a score.

A small-business register is scoped for the rebuilt 2028 rule — far fewer lenders, first filing in 2029.

Out

A field is retained with its source system, the exception raised on it and the person who cleared it.

Execute write actions only inside the approval boundaries agreed during implementation.

→ Product statement

The agent reconciles and assembles; a representative with knowledge of the data certifies, submits, and resubmits if a value proves wrong.

Example workflow

One register, field to certification

AgentHuman

1Final action recordedLOS record, pricing engine, geocoder or credit-file entry

2Fields reconciledEach register field tied back to the system of record it was drawn from

3Register assembledField values, exceptions, edits and confidence

4Controls appliedSource reconciliation, the § 1003.4(f), sixty-day and 1 March clocks, edit checks and confidence threshold

No human action required

Stages 1 to 4 run unaided and certify nothing — the agent records the decision a person already made, and the certifier's lane opens at the gate.

5DecisionBranches at the confidence threshold

High confidence

Goes to the named certifier to read.

Low confidence

Adds a compliance-manager read first.

Certifier review

The register is held with its field sources, its open exceptions and the confidence.

Approve · Correct · Send to compliance review

Certified — the annual filing only▼

6Register systems updatedOnly where write access and approval policy allow it

7Outcome evaluatedField-defect counts, correction distance, edit outcomes and resubmissions

Corrections

Every certifier correction is counted in the evaluation.

What should not run autonomously

Human approval stays in control

Outside the boundary — human approval required8 items

Certifying accuracy and completeness of the register.

Submitting the register to the federal agency.

Verifying a quality edit against the loan file.

Retesting coverage — a March 2026 order may reopen it.

Automation boundaryAgent acts unaided

✓Reconcile each register field to its system of record.

✓Track the § 1003.4(f) recording and § 1003.5 filing clocks for the named owner.

✓Assemble the evidence each platform exception turns on into the review queue.

✓Flag the exceptions and the unmatched fields, and hold.

Any write happens inside the boundaries agreed at implementation, never ahead of certification.

Making or revisiting the credit decision on a file.

Determining the action taken where the file is unclear.

Deciding what a resubmission covers and changes.

Changes to field mappings or automation thresholds.

Example output

One register field, annotated

Everything the agent reconciles is attached to the system it was drawn from — that is the § 1003.6(b) evidence.

Loan

Value on the LAR

Source of record

Confidence

Clock position

Closed-end refinance

Rate spread, derived against the APOR in force

1.87

Pricing engine

96%

Recorded within the quarter

As receivedTaken from the pricing engine and the APOR table in force — nothing on this side is written by the agent.

Source facts used Pricing engine record APOR table, that week Credit file disclosure

Why this valueIt ties to the pricing engine, not to a value the register re-derived for itself.

ActionApproveCorrectSend to compliance review

What the score decidesBelow the configured threshold the field picks up a compliance-manager read before the certifier.

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 register fieldFrom the system of record

03Reconciliation

Reconcile against source

Draw on the LOS, the pricing engine and the geocoder — HMDA was among the FDIC's most-cited findings in 2025.

01Approved path

Knowledge, not rank, certifies

The register arrives reconciled, so whoever certifies can point at the system behind any field on it.

02Human review

Send review to the exceptions

Exceptions are marked, and § 1003.6(c) shelters a good-faith quarterly error only if it clears before 1 March.

04Build an evidence trail

The field, the system it was drawn from and the representative who certified stay on the register.

Integrations

Typical integrations

Five system groups connect to the same agent. Which of them are in scope is decided in discovery.

Origination systemsEncompass · Empower
MeridianLink · Byte

Core and servicingFiserv · FIS · Jack Henry
Servicing and portfolio data

Filing and editsHMDA Platform submissions
LAR format · edit reports

Agent

HMDA & lending data integrity

Reads the record
Reconciles the fields
Holds for certification

Pricing and geocodingPricing engine · APOR
FFIEC geocoder · tracts

Observability & evaluationOpenTelemetry · Langfuse
Supported monitoring/evaluation sources

Integration availability depends on the client's existing systems and API access.

Agent controls

Six checks between the model and the register

Six checks, narrowing as they go. What survives the last one is named in the map below.

L6 · Outermost — last line of defenceInward → L1 · closest to the model

L6Rollback / safe modeNarrow the agent to field reconciliation when evaluation or production signals degrade.Roll back

L5Version monitoringTrack model, prompt, field-mapping and clock-configuration changes.Track

L4TraceabilityRecord the source system, the value, the exceptions, the corrections and the certification time.Record

L3Certifier reviewHold the register for the named certifier; it governs release, not whether a certified value is right.Gate

L2Policy guardrailsTest fields against the configured § 1003.4 rules and mappings; a failure returns the field.Restrict

L1Confidence thresholdsRoute low-confidence fields to a compliance-manager read before the certifier sees them.Require review

Model coreRegister assembled — field values, exceptions, edits and confidence

L1 – L2Test whether a field may stand

L3Puts the certification in a person's hands

L4 – L5Keep the field and the system behind it

L6Reverts to field reconciliation when signals degrade

How Nestack evaluates it

Evaluate the reconciliation workflow — not only the finished register.

Coverage runs the whole depth of the workflow, and every layer is cut by slice.

Surface — the register the agency reads

Depth of coverage ▼

E1Final-output evaluationDid every field on the register match the system it was drawn from?

E2Step-level evaluationDid the agent use the right systems, field mappings and clock configuration?

E3Tool evaluationDid it read and write the correct loan and the correct field?

E4Confidence calibrationDo low-confidence fields actually attract more certifier corrections?

E5Slice evaluationHow does performance change across specific data fields?

E6Business outcomeHow many fields needed a correction or a resubmission after filing?

Floor — the outcome the institution answers for

Failure modes

Where each failure originates in the agent

Seven failure modes, placed at the stage each one originates.

Agent lifecycleDirection of processing →

01 · Retrieval1 mode

HW-03

Superseded system of record

Built on an address the credit file has since replaced.

Stage gathersLoan files, LOS records, pricing and geocode data

02 · Reasoning2 modes

HW-04

Stale benchmark table

Rate spread derived against a cached APOR vintage.

HW-06

Action-taken mismapping

A changed LOS workflow maps a denial to withdrawal.

Stage proposesField values, exceptions, edits and confidence

03 · Tool / write2 modes

HW-02

Edits cleared in bulk

Quality edits closed without a person verifying them.

HW-05

Unreviewed field drift

A resubmission changes fields nobody asked to change.

Stage writesOnly where write access and approval policy allow it

04 · Output1 mode

HW-01

Signed without knowledge

The register is certified by someone who has not opened a file.

Stage returnsThe register a named representative certifies

05 · Change / Version1 mode

HW-07

Silent mapping regression

A rule change quietly alters how a field is derived.

Stage tracksModel, prompt, field rules and mapping config

Sev-1 · acts outside the boundary Sev-2 · a wrong value reaches the register Sev-3 · a source degrades, the field is held

See the complete Banking failure-mode catalogue →

Affected slices

One weak field can force a full-register fix

A register-level accuracy figure can read as clean while a few data fields carry most of the defects — and resubmission is directed field by field. Nestack reports the defect rate by slice, not only in total.

Slice performance — reported separately, not only in aggregateIllustrative example

Slice	Failure rate	Lift	Status
Rate spread on priced loans	7.3%	3.7×	Review
Action-taken and reason codes	5.2%	2.7×	Review
Census tract and geocoding	3.4%	1.7×	Watch
Retail closed-end originations	1.5%	0.8×	Normal

Bar: field-defect-rate lift vs. retail-origination baseline · scale 0–4.0× · tick marks the 2.0× review threshold 2 of 4 slices over threshold

Evidence-linked improvement

The loop closes on a regression case

The loop shuts when the resubmission is a regression case, not when it has been explained. That suite is what the next register assembled is measured against.

Improvement cycle · five stagesSwitchback — the path turns at Improve and returns at Learn

01Detect

A field's defect count crosses the resubmission threshold.

02Diagnose

The rate-spread column that was wrong for a whole quarter is read back until one cause holds.

03Improve

Any change goes out numbered, with the fields that caused it attached.

04Verify

A register case still failing is enough to hold the release back.

05Learn

One case added to the suite, one line added to the field record.

Learn → DetectThe return edge. The next detection runs against a suite one case longer.

Typical build scope

Twelve workstreams across six weeks

The build scope read against the delivery timeline. Week structure follows the six-week plan — discovery, sources, reconciliation workflow, evaluation, integration, then production validation and handover.

Workstream Week 1Week 2Week 3Week 4Week 5Week 6

01HMDA workflow discovery and boundary definition.

02Origination and pricing source review.

03Field mapping, edit rules and submission clocks.

04Loan-record ingestion and normalisation.

05Reconciliation logic and source binding.

06Confidence scoring and exception routing.

07Certifier review workflow.

08Filing and origination-system integration.

09Field and reconciliation cases.

10Guardrails and certification controls.

11Register-trail instrumentation.

12Deployment, documentation and Agent Care handover.

12 workstreams · 6 weeks · bar shows the weeks a workstream is active — several run in parallel Final 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 tier PilotOne portfolio, one register ProductionProduction filing systems AdvancedMultiple registers / entities

Introduced at Pilot

Reconciliation to your systems✓✓✓

Certifier review✓✓✓

Field-accuracy baseline✓✓✓

Introduced at Production

Reporting by data field—✓✓

Certifier review workflow in your systems—✓✓

Approved write-back—✓✓

Origination-system integration—✓✓

Introduced at Advanced

Multi-channel field mappings——✓

Multi-stage compliance review——✓

High application volume——✓

Multi-institution register controls——✓

Build price From $5,000 From $8,000 Custom quote

Final build priceConfirmed after discovery based on integrations, workflow complexity, transaction volume, 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

01Your loan systems and field mappings → Loan-record ingestion and field mappingWeek 1

02Representative filed registers → Reconciliation baseline, source binding and clock modellingWeek 2

03Your edit-resolution and correction rules → Field mapping, edit rules and submission-clock modellingWeek 1

04Access to relevant APIs, feeds or exports → Origination, pricing and geocode assessment, then integration setupWeek 2

05Registers you would not want resubmitted → Edit cases and failure-mode testingWeek 4

06What no certification may cover → Confidence scoring, exception routing, guardrails and certification controlsWeek 3

07Named certifiers with knowledge of the data → Certifier review workflow, then pilot and production validationWeeks 5–6

Nothing else is required Deployment, documentation and Agent Care handover are ours.

Delivery timeline

Four phases across six weeks

Each band spans the weeks its phase actually takes, which is why the fifth carries two of them.

Phase W1W2W3W4W5W6

Discovery W1

Build W2 – W3

Evaluate W4 – W5

Pilot & Launch W5 – W6

Week focus W1HMDA workflow discovery, field mapping and the automation boundary W2Source integration and the reconciliation baseline W3Reconciliation workflow, confidence logic and certification controls W4Evaluation suite, edit checks and failure-mode testing W5Filing integration, a pilot quarter and targeted corrections W6One filing season run under the compliance manager, then Agent Care handover

Reading the bandEach bar sits on the weeks its work is named in and no others. The week 5 doubling is real work, not padding.

At the end of W6Once the season validates, Agent Care assumes the running agent.

DurationSix-week plan shown · typical delivery 4–6 weeks depending on scope confirmed in discovery.

Next step · Banking AI agent

Build a HMDA agent around the person who certifies.

Regulation B's effects test was repealed in July 2026; Regulation C did not move. Show us your loan systems, your field mappings and who certifies — the certification stays with them.

Discuss this agent →

Nestack Agents · HMDA & lending data integrityAGT-BK-15 · Agent Care available after launch