Trade, Tariff & Country-of-Origin AI Agent

What this agent does

Proposes the classification, not the entry

A part is added to the item master, and its drawings, as-shipped weights and supplier declarations are pulled in.

A code is proposed, and the reasoning and any CBP ruling it was read against are recorded beside it.

Reason

A rate moves in the Federal Register, and the parts sitting on that 9903 subheading are flagged against it.

A part sits near the 85 percent metal test that replaced 95 percent on 8 June 2026, and it is held for a check.

A derivative is entered, and the metal and non-metal content are worked out as two lines, not one.

Decide

A steel part arrives, and melt and pour is read from the mill certificate, not from the supplier's address.

A 232 exclusion is modelled, and the Section 301 forced-labour line it opens is added, not netted out.

Out

A pack is assembled, and the evidence, the proposal and the amendments are held with it for the named manager.

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

→ Product statement

The agent proposes the classification; the importer of record, in person or through a licensed customs broker, files it under penalty.

Example workflow

One part, item master to entry

AgentHuman

1Part record receivedItem master, drawing, supplier declaration or commercial invoice

2Evidence assembledWeights, bills of material, mill certificates and prior rulings, each with its named source

3Classification proposedHTS code, 9903 subheading, origin tests and confidence

4Controls appliedMetal-threshold checks, dual-line rules, melt-and-pour evidence and confidence threshold

No human action required

Stages 1 to 4 run unaided, and nothing is filed at any of them — the agent is proposing, and the manager's lane opens at the confidence gate.

5DecisionBranches at the confidence threshold

High confidence

Goes to the trade-compliance manager.

Low confidence

Adds a customs-broker read first.

Manager approval

The proposal is held with its evidence, its open gaps and the confidence.

Approve · Amend · Send to broker review

Approved — released to the filer▼

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

7Outcome evaluatedAmendment rate, ruling outcomes, CBP requests and post-entry corrections

Amendments

Every manager amendment is counted in the evaluation.

What should not run autonomously

Human approval stays in control

Outside the boundary — human approval required8 items

Filing the entry or entry summary with CBP.

Adopting the classification the entry will rest on.

Transacting customs business for another party.

Certifying US content or country of origin.

Automation boundaryAgent acts unaided

✓Propose an HTS code and the 9903 subheading beside it.

✓Carry each origin answer with the legal test it answers.

✓Compute metal-content and US-content worksheets from source data.

✓Flag the gaps the manager should weigh, and hold the pack for them.

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

Requesting a ruling, or relying on another party's.

Deciding whether to make a prior disclosure.

Deciding whether to protest a liquidation.

Changes to rate tables, thresholds or filing boundaries.

Example output

One classification, annotated

Everything the agent proposes is attached to the record it was drawn from.

Classification output · single partIllustrative example

Part

Description

Metal content

Proposed treatment

Confidence

Origin test

Aluminium bracket

Cast aluminium bracket, machined and plated

88% by weight

Composed entirely of metal

91%

Smelt and cast, from the mill

As receivedTaken from the item master and the mill certificate — nothing on this side is inferred.

Evidence used Mill certificate As-shipped weights Prior CBP ruling

Why this treatmentIt clears the metal test as it stands after 8 June 2026 — the line the manager weighs.

ActionApproveAmendSend to broker review

What the score decidesBelow the configured threshold the proposal picks up a broker read before it.

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 partFrom the item master

03Classification

Propose against your rules

Draw on the weights and rulings on file, and the subheadings in force on the day.

01Approved path

A code is a statement to CBP

Routine parts arrive with a proposed code and the subheading in force attached.

02Human review

Send review to the exposed lines

Parts near a threshold and low-confidence proposals are marked, so the manager's read starts where exposure concentrates.

04Build an evidence trail

The classification, the ruling it was read against and the broker who filed it stay on the entry.

Integrations

Typical integrations

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

ERP and item masterSAP · Oracle
Dynamics · Infor · QAD

Customs filingABI / ACE broker systems
Descartes · e2open

Trade contentHTSUS · CROSS rulings
Federal Register · CSMS

Agent

Trade, tariff and origin

Reads the part
Proposes the code
Holds for approval

Supplier documentsMill certificates · invoices
Origin declarations

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 entry

Six controls, one within the next. What the whole stack lets through is named in the map below.

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

L6Rollback / safe modePull the agent back to duty reporting when evaluation or production signals degrade.Roll back

L5Version monitoringTrack model, prompt, rate-table and classification-rule changes.Track

L4TraceabilityRecord the source data, the proposal, the gaps, the amendments and the approval.Record

L3Manager approvalHold proposals for the named manager; it governs release, not whether an adopted code is right.Gate

L2Policy guardrailsTest proposals against the 9903 subheadings in force; a concluded 232 finding is not a rate.Restrict

L1Confidence thresholdsRoute low-confidence proposals to a broker read before the manager sees them.Require review

Model coreClassification proposed — HTS code, 9903 subheading, origin tests and confidence

L1 – L2Test whether a code may stand

L3Puts the release in a manager's hands

L4 – L5Keep the classification and the ruling behind it

L6Falls back to duty reporting when signals degrade

How Nestack evaluates it

Evaluate the classification workflow — not only the code at the end.

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

Surface — the code on the entry

Depth of coverage ▼

E1Final-output evaluationDid the proposed heading match the one the manager adopted?

E2Step-level evaluationDid the agent use the right weights, rules and any company-specific rate?

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

E4Confidence calibrationDo low-confidence proposals actually attract more amendments?

E5Slice evaluationHow does performance change across specific part groups?

E6Business outcomeHow many entries still carried an IEEPA line after 24 February 2026?

Floor — the exposure the importer 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

TD-03

Superseded rate table

A 9903 line read after the rate it carried ceased.

Stage gathersItem master, weights, certificates and rate tables

02 · Reasoning2 modes

TD-04

One origin, three tests

One origin field answers three different legal tests.

TD-06

Exclusion read as saving

Exclusion netted without the 301 line it opens.

Stage proposesHTS code, 9903 subheading, origin and confidence

03 · Tool / write2 modes

TD-02

Low-confidence adoption

Proposal adopted despite insufficient certainty.

TD-05

Weight from nominal BOM

Metal weight taken from a BOM, not the shipment.

Stage writesOnly where write access and approval policy allow it

04 · Output1 mode

TD-01

Content line uncapped

US content declared above the cap the proclamation sets.

Stage returnsThe classification the manager adopts

05 · Change / Version1 mode

TD-07

Silent rule regression

A rate or threshold change widens what the agent proposes.

Stage tracksModel, prompt, rate tables and threshold rules

Sev-1 · acts outside the filing boundary Sev-2 · a wrong code reaches the entry Sev-3 · source degrades, part routes to review

See the complete Manufacturing failure-mode catalogue →

Affected slices

One tariff line can carry most of the risk

A blended duty rate across the catalogue can look settled while a small number of tariff lines carry most of the exposure. Nestack reports the amendment rate by slice, not only in total.

Slice performance — reported separately, not only in aggregateIllustrative example

Slice	Failure rate	Lift	Status
USMCA dual-line derivatives	9.2%	3.8×	Review
Metal content near the test	7.4%	3.1×	Review
Multi-country supply chains	4.6%	1.9×	Watch
Single-origin stock parts	1.2%	0.5×	Normal

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

Evidence-linked improvement

Every cycle ends by adding a case

A cycle closes when the misclassified part is a case the next release has to catch. That suite is what the next entry prepared is measured against.

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

01Detect

Amendment rate rises in a tariff-line slice.

02Diagnose

The line that cleared for three years under the wrong code is read back to a single cause.

03Improve

The fix carries a version number, and the entries that forced it travel with it.

04Verify

Nothing goes out until every touched classification case has passed a second time.

05Learn

It is kept for good, and the classification rules are amended in the same commit.

Learn → DetectThe return edge. The next entry is prepared 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, classification workflow, evaluation, integration, then production validation and handover.

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

01Trade workflow discovery and boundary set and boundary definition.

02Item-master and broker-system assessment.

03HTS, 9903 subheading and origin-rule mapping.

04Part-data ingestion and normalisation.

05Classification logic and evidence binding.

06Confidence scoring and gap routing.

07Trade-compliance manager approval.

08Entry and broker-system integration.

09Classification and origin cases.

10Guardrails and filing controls.

11Entry-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 part family, one origin ProductionProduction entry systems AdvancedMultiple plants / programmes

Introduced at Pilot

Proposals to your parts and rules✓✓✓

Manager approval✓✓✓

Classification-accuracy baseline✓✓✓

Introduced at Production

Reporting by tariff line—✓✓

Approval workflow in your systems—✓✓

Approved write-back—✓✓

Item-master integration—✓✓

Introduced at Advanced

Multiple origins and regimes——✓

Multi-stage trade approvals——✓

High entry volume——✓

Multi-programme duty 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 item master and part weights → Part-data ingestion and evidence mappingWeek 1

02Representative entries already filed → Classification baseline and evidence bindingWeek 2

03Your rate tables and origin rules → HTS, 9903 and origin-rule mappingWeek 1

04Access to relevant APIs, feeds or exports → Item-master and broker-system assessment, then integration setupWeek 2

05Entries you would not want examined → Origin cases and failure-mode testingWeek 4

06What no declaration may rest on → Confidence scoring, gap routing, guardrails and filing controlsWeek 3

07A named trade-compliance manager to approve → Manager 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 cover the weeks each phase really eats, 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 W1Trade workflow discovery, rule mapping and the automation boundary W2Item-master integration and the classification baseline W3Classification workflow, confidence logic and approval controls W4Evaluation suite, origin and threshold checks and failure-mode testing W5Broker-system integration, pilot entries and targeted corrections W6One entry cycle prepared under the trade-compliance manager, then Agent Care handover

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

At the end of W6Validation closes on live entries, and Agent Care picks up monitoring.

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

Next step · Manufacturing AI agent

Build a tariff and origin agent around your entry process.

Show us your parts and who approves a code. If one origin field serves your marking rule, your melt-and-pour report and your non-preferential test, then two of the three are already wrong.

Discuss this agent →

Nestack Agents · Trade, tariff & originAGT-MFG-13 · Agent Care available after launch