Stablecoin Reserve-Attestation AI Agent

What this agent does

Assembles the pack, not the certification

A reserve is held at a custodian, and the position is pulled from supported custody, ledger and chain sources.

A holding is tested against the closed asset list at GENIUS Act § 4(a)(1)(A), and anything outside it is named.

Reason

A Treasury position is re-tested for remaining maturity daily, because the limit is not a purchase-date test.

A reserve pool is tied to a single stablecoin brand, and a commingled position is flagged rather than allocated.

A coin count is reconciled from the mint-and-burn ledger to on-chain supply, and each difference is described.

Decide

A redemption settles, and the reserve movement behind it is matched to the published redemption policy.

A reserve use is logged against the § 4(a)(2) exception claimed for it, and an unmatched use stays open.

Out

A pack is retained as a dated version, alongside the composition disclosure and what each officer was shown.

A write action runs only inside the approval boundaries agreed during implementation.

→ Product statement

The agent maintains the record and assembles the pack; a registered public accounting firm examines it, and the CEO and CFO both certify.

Example workflow

One month, custody to certification

AgentHuman

1Month-end positions receivedCustody statements, ledger extracts and on-chain supply reads

2Composition assembledEligibility, residual maturity, average tenor, custody location and coins outstanding

3Pack draftedComposition schedule, exception log, open items and confidence

4Controls appliedEligibility tests, maturity re-tests, brand-segregation checks and confidence threshold

No human action required

Stages 1 to 4 run unaided, and nothing is certified at any of them — the agent is assembling a record, and the treasury lane opens at the confidence gate.

5DecisionBranches at the confidence threshold

High confidence

Goes to the reserve owner to approve.

Low confidence

Adds a controller read first.

Reserve-owner approval

The pack is held with its custodian confirmations, its open items and the confidence.

Approve · Amend · Send to controller review

Approved — released to the accounting firm▼

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

7Outcome evaluatedAmendment distance, open-item outcomes, examination findings and post-publication corrections

Amendments

Every reviewer amendment is counted in the evaluation.

What should not run autonomously

Human approval stays in control

Outside the boundary — human approval required8 items

Certifying the monthly report — the CEO and the CFO, both.

The monthly examination — a registered public accounting firm.

Deciding that a reserve asset qualifies.

Invoking an exception to the reuse prohibition.

Automation boundaryAgent acts unaided

✓Reconcile reserve positions across custodians to the ledger.

✓Re-test residual maturity and eligibility, day after day.

✓Tie coins outstanding to on-chain supply, and name the difference.

✓Draft the composition disclosure, and hold the pack for its owner.

Writes run only inside the boundaries agreed at implementation, and never ahead of approval.

Publishing the monthly composition to the issuer's website.

Setting or amending the public redemption policy.

Engaging and instructing the accounting firm.

Changes to eligibility, segregation or approval rules.

Example output

One reserve position, annotated

Everything the agent assembles is attached to the position it was drawn from.

Reserve record output · single positionIllustrative example

Custodian

Instrument

Remaining maturity

Source of record

Confidence

Eligibility basis

Primary reserve custodian

Treasury bill · remaining maturity re-tested

61 days

Custodian statement

88%

Named item on the § 4(a)(1)(A) list

As receivedTaken from the custodian statement and the month-end extract — nothing on this side is written by the agent.

Source facts used Custodian statement Month-end position file On-chain supply read

Why this is eligibleRemaining maturity is re-tested each day, so eligibility reads as a current fact.

ActionApproveAmendSend to controller review

What the score decidesBelow the configured threshold the position picks up a controller read first.

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 positionFrom the custody record

03Assembly

Test what the statute lists

Eligible assets are a closed list, and the limit runs on remaining maturity — GENIUS Act § 4(a)(1)(A).

01Approved path

Two officers, criminal exposure

A false certification imports the criminal penalties of 18 U.S.C. § 1350(c), by way of § 4(a)(3)(C).

02Human review

Assembly, not attestation

The agent builds what the firm tests; the examination under § 4(a)(3)(A) is the accounting firm's, and its report stays the firm's.

04Build an evidence trail

The reserve, the composition rule it was tested against and the officers who certified stay on the pack.

Integrations

Typical integrations

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

Custody and reservesBNY · State Street
Anchorage · Fireblocks

Chain and token dataNode and indexer APIs
Mint-and-burn ledger

Treasury and general ledgerKyriba · GTreasury
Core banking · GL extracts

Agent

Reserve record & examination pack

Reads the positions
Assembles the pack
Holds for approval

Close and disclosureWorkiva · close tooling
Website · disclosure feed

Observability & evaluationOpenTelemetry · Langfuse
Supported monitoring/evaluation sources

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

Agent controls

Six layers between the model and the pack

Six controls wrapped around one another. What none of them catches is named in the map beneath.

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

L6Rollback / safe modeFall back to record assembly only, when evaluation or production signals degrade.Roll back

L5Version monitoringTrack model, prompt, eligibility-rule and custodian-configuration changes.Track

L4TraceabilityRecord the source positions, the drafted pack, the open items and the approval time.Record

L3Owner approvalHold the pack for its named owner; it governs release, not whether a position is eligible.Gate

L2Policy guardrailsTest the pack against the eligibility and segregation rules; a failure returns the pack.Restrict

L1Confidence thresholdsRoute low-confidence positions to a controller read before the owner sees them.Require review

Model corePack drafted — composition schedule, exception log, open items and confidence

L1 – L2Test whether the pack may stand

L3Puts the release in the owner's hands

L4 – L5Keep the reserve and the composition rule behind it

L6Holds the pack at unreconciled when signals degrade

How Nestack evaluates it

Evaluate the assembly workflow — not only the finished pack.

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

Surface — the disclosure the public can read

Depth of coverage ▼

E1Final-output evaluationDid every reserve line trace to the custody position behind it?

E2Step-level evaluationDid the agent use the right positions, eligibility rules and custodian configuration?

E3Tool evaluationDid it read and write the correct custodian and the correct period?

E4Confidence calibrationDo low-confidence positions actually attract more reviewer amendments?

E5Slice evaluationHow does performance change across specific reserve classes?

E6Business outcomeHow many lines were amended, or corrected after the disclosure was published?

Floor — the outcome the officers answer for

Failure modes

Where each failure originates in the agent

Seven failure modes, each placed at the stage it originates in.

Agent lifecycleDirection of processing →

01 · Retrieval1 mode

RG-03

Unconfirmed custodian balance

Prior month's position carried without a flag.

Stage gathersCustody statements, chain data and ledger extracts

02 · Reasoning2 modes

RG-04

Maturity tested at purchase

Eligibility is not re-run as a bill ages.

RG-06

Default exception label

A reserve use is logged under the wrong basis.

Stage proposesComposition schedule, exception log and confidence

03 · Tool / write2 modes

RG-02

Coin supply unreconciled

Ledger count is not tied to on-chain supply.

RG-05

Allocated, not segregated

One omnibus account is split by pro-rata share.

Stage writesOnly where write access and approval policy allow it

04 · Output1 mode

RG-01

Disclosure differs from pack

Website figure is generated separately.

Stage returnsThe pack the firm examines and the officers sign

05 · Change / Version1 mode

RG-07

Silent eligibility drift

A model or rule change alters what counts as eligible.

Stage tracksModel, prompt, eligibility rules and custodian config

Sev-1 · a wrong pack reaches a certification Sev-2 · a wrong line reaches the disclosure Sev-3 · source degrades, line goes to review

See the complete Banking failure-mode catalogue →

Affected slices

One reserve class can sit under a clean total

A programme-level reconciliation figure can read as clean while a few reserve classes absorb most of the amendments. Nestack reports the amendment rate by reserve class, not only in total.

Slice performance — reported separately, not only in aggregateIllustrative example

Slice	Failure rate	Lift	Status
Tokenised money market funds	8.6%	3.7×	Review
Omnibus custody accounts	7.0%	3.0×	Review
Overnight repo positions	4.0%	1.7×	Watch
Direct-held Treasury bills	1.2%	0.5×	Normal

Bar: amendment-rate lift vs. direct-held-bill baseline · scale 0–4.0× · tick marks the 2.0× review threshold 2 of 4 slices over threshold

Evidence-linked improvement

A cycle ends where a test begins

A cycle closes when the unreconciled reserve is a case the next release has to catch. That suite is what the next pack assembled is measured against.

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

01Detect

Amendment rate rises in a reserve class.

02Diagnose

The month the composition moved and the pack still said otherwise is read back until the cause narrows to one.

03Improve

Number the correction, and the reserves that surfaced it stay fastened to it.

04Verify

No release while a touched reserve case is outstanding; it reruns first.

05Learn

The case is retained, and the composition rules change in the same commit.

Learn → DetectThe return edge. The next month is detected 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, reserve workflow, evaluation, integration, then production validation and handover.

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

01Reserve workflow discovery and boundary mapping.

02Custody, ledger and chain assessment.

03Eligibility, maturity and segregation rule mapping.

04Position ingestion and reconciliation.

05Pack assembly and source binding.

06Confidence scoring and exception routing.

07Reserve-owner approval workflow.

08Custody and ledger integration.

09Composition and segregation cases.

10Guardrails and attestation controls.

11Reserve-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 brand, one month ProductionProduction custody systems AdvancedMultiple brands / issuers

Introduced at Pilot

Reserve record and reconciliation✓✓✓

Reserve-owner approval✓✓✓

Reconciliation-completeness baseline✓✓✓

Introduced at Production

Reporting by reserve class—✓✓

Exception workflow in your systems—✓✓

Approved write-back—✓✓

Custody and ledger integration—✓✓

Introduced at Advanced

Multi-jurisdiction custody rules——✓

Multi-stage treasury approvals——✓

High reserve volume——✓

Multi-issuer reserve controls——✓

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

Final build priceConfirmed after discovery based on integrations, workflow complexity, reserve 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 custodian list and reserve policy → Eligibility, maturity and segregation rule mappingWeek 1

02Representative prior month-end packs → Position ingestion, reconciliation and the assembly baselineWeek 2

03Your documented eligible-asset definitions → Reserve-policy mapping and automation-boundary definitionWeek 1

04Access to relevant APIs, feeds or exports → Custody, ledger and chain assessment, then integration setupWeek 2

05Packs you would not want examined → Composition cases and the evaluation suiteWeek 4

06What no certification may rest on → Confidence scoring, exception routing, guardrails and approval controlsWeek 3

07Named reserve owners to review the pack → Reserve-owner approval 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

The bands follow the monthly cycle rather than the slide, so the fifth week carries two phases.

Phase W1W2W3W4W5W6

Discovery W1

Build W2 – W3

Evaluate W4 – W5

Pilot & Launch W5 – W6

Week focus W1Reserve workflow discovery, rule mapping and the automation boundary W2Source integration and the reconciliation baseline W3Assembly workflow, confidence logic and approval controls W4Evaluation suite, eligibility checks and failure-mode testing W5Custody integration, a pilot month and targeted corrections W6One monthly cycle assembled under the chief financial officer, then handover

Reading the bandEach bar covers only the weeks its work is named in. The week 5 overlap is real, not padding.

At the end of W6The last checks clear on a live cycle and Agent Care picks up monitoring.

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

Next step · Banking AI agent

Build the reserve record before the first certification falls due.

Show us your custodians, your eligible-asset policy and who signs. A wrong reserve line, once certified, is a criminal exposure carried by two named officers — not a supervisory finding.

Discuss this agent →

Nestack Agents · Stablecoin reserve attestationAGT-BK-18 · Agent Care available after launch