Nestack Agent Care
Industries / Retail & E-commerce / Route-exception agent

Retail AI agent · Shipping exceptions

Shipping & Route-Exception AI Agent

Detect and classify carrier exceptions, draft the delay notice with the consent basis the rule actually requires, and leave the reroute, the claim and the send to the people who own them.

4–6 weeksTypical delivery
Your stackDeployment
Draft-onlyManager release
Agent CareAfter launch

What this agent does

Works the exception, does not decide it

In
01

Ingest tracking events, tender records, freight invoices and lane schedules from supported carrier.

02

Normalise carrier milestone codes into one event vocabulary, and keep the raw code beside each one.

Reason
03

Detect and classify exceptions against the thresholds configured for that lane and that service.

04

Read the order's notice history, and treat a renewed delay differently from the first one.

05

Draft the delay notice and the claim packet, each bound to the shipment record behind it.

Decide
06

Mark shipments whose claim deadline, hazmat status or temperature setpoint puts the decision beyond the agent.

07

Route every notice to the transport manager and every claim position to the claims manager.

Out
08

Retain the milestone data, the notice sent, its consent basis and the person who released it.

09

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

Product statement

The agent works the exception; the transport manager authorises the reroute, the claims manager takes the claim position, and the retailer answers for the notice.

Example workflow

One shipment, tender to resolution

AgentHuman
1Milestone event receivedCarrier tracking event, tender record, freight invoice or a lane-schedule change
2Milestones assembledOrder and notice history, service commitment, tariff deadlines and the commodity's handling profile
3Exception classifiedException type, drafted notice, claim exposure and confidence
4Thresholds appliedNotice-sequence checks, hazmat and setpoint checks, deadline checks and the confidence threshold
No human action required

Stages one to four run unaided, and nothing reaches a buyer at any of them — the agent is drafting, and the manager's lane opens at the confidence gate.

5DecisionSplits at the notice gate
On the expected path

Goes to the transport manager to release.

Off the expected path

Adds a claims-manager read first.

Manager release

The notice is held with its milestone data, its consent basis and the confidence.

Release · Amend · Send to claims review
Released — notice sent
6Carrier and order systems updatedOnly where write access and approval policy allow it
7Exception evaluatedNotice timing, consent basis, claim outcomes and refunds owed after the fact
Reversals

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
Authorising a reroute, re-consignment or mode change.
Any hazmat routing, repacking or re-labelling decision.
Filing, conceding, denying or settling a freight claim.
Changing classification, valuation or country of origin.
Automation boundaryAgent acts unaided
Poll carrier tracking and normalise milestone events across lanes.
Detect and classify exceptions against configured.
Draft delay notices and claim packets for human.
Reconcile freight invoices and flag every accessorial variance.
Any write happens inside the boundaries agreed at implementation, never ahead of the manager's release.
Dispositioning a temperature-excursed food shipment.
Approving or waiving a demurrage or detention charge.
Approving the delay-notice template and its consent logic.
Directing a gig delivery driver's method or sequence.

Example output

One delay notice, annotated

Everything the agent drafts is attached to the shipment it was drawn from.

Exception output · single shipmentIllustrative example
Shipment
Drafted notice
Notice state
Source of record
Confidence
Where it went
Cross-border parcel
Revised delivery date, with the cancel-and-refund option stated in the same message
Renewed notice
Carrier milestone and order record
81%
Transport manager
As receivedTaken from the carrier's milestone feed and the order's own notice history.
Evidence used Carrier milestone Prior notice sent Service commitment
Why this noticeIt is the second notice, so silence is not consent and a person still decides.
ActionReleaseAmendSend to claims review
What the score decidesBelow the configured threshold the notice picks up a claims read before the manager sees 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 shipmentFrom the carrier feed
03Exception handling

Classify the exception

Draw on the milestone feed, the order's notice history and the service commitment configured for that lane.

01Approved path

Catch the exception early

Routine tracking, exception classification and invoice reconciliation arrive already done.

02Human review

Send review to the notices that bind

Shipment means goods physically in the carrier's possession, not a label bought or an order picked — so the notices resting on that distinction are marked and the manager reads those first.

04Build an evidence trail

The milestone data, the notice sent and its consent basis stay with the shipment.

Integrations

Typical integrations

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

Carrier and trackingFedEx · UPS · USPS APIs
DHL · regional carrier feeds
Visibility platformsproject44 · FourKites
Tive · Controlant
Transport managementOracle OTM · Blue Yonder TMS
MercuryGate · e2open

Agent

Shipping and route exceptions

Reads the milestone
Classifies the exception
Holds for release

Orders and customsShopify · order platforms
Customs-broker filings
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 notice

Each wraps the last. The map below names what each one lets through.

L6 · Outermost — last line of defenceInward → L1 · closest to the model
L6Rollback / safe modeStop notices and hold them for a person when evaluation or production signals degrade.Roll back
L5Version monitoringTrack model, prompt, carrier-API and notice-template changes.Track
L4TraceabilityRecord the milestone data, the notice, its consent basis and the release time.Record
L3Manager releaseHold notices for the transport manager; it governs the send, not whether the consent basis underneath it is right.Gate
L2Policy guardrailsTest notices against the notice sequence, hazmat rules, setpoints and tariff deadlines; a failure returns the notice.Restrict
L1Confidence thresholdsRoute low-confidence exceptions to a claims read before the manager sees them.Require review
Model coreException produced — exception type, drafted notice, claim exposure and confidence
L1 – L2Test whether a notice may stand
L3Puts the send in a manager's hands
L4 – L5Preserve the notice sequence and its basis
L6Stops notices and holds them for a person

How Nestack evaluates it

Evaluate the whole exception path — not only the notice at the end of it.

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

Surface — the notice the buyer receives
Depth of coverage ▼
E1Final-output evaluationDid the notice carry the revised date and the cancel-and-refund option?
E2Step-level evaluationDid the agent read the right milestone, notice history and service commitment?
E3Tool evaluationDid it read and write the correct shipment, the correct order and the correct field?
E4Confidence calibrationDo low-confidence exceptions actually attract more manager amendments?
E5Slice evaluationHow does notice timing change across specific lanes and services?
E6Business outcomeHow many notices were amended, and how many refunds were owed afterwards?
Floor — the delivery the customer gets

Failure modes

Where each failure originates in the agent

Seven modes, each at its point of origin.

Agent lifecycleDirection of processing →
01 · Retrieval1 mode
SX-01

Pre-transit scan read as delivery

An information-received scan closes an exception on an undelivered parcel.

Stage gathersMilestone events, notice history, with the source each came from
02 · Reasoning2 modes
SX-02

Renewed notice treated as a first

Silence is taken as consent on orders the rule has already deemed cancelled.

SX-03

Placarded load routed on transit time

A reroute optimised for speed runs a hazmat load through a restricted route.

Stage proposesException type, drafted notice and confidence
03 · Tool / write2 modes
SX-04

Re-consignment without a setpoint

A temperature-controlled load moves to a lane nobody confirmed holds it.

SX-05

Demurrage approved unread

An invoice clears inside the dispute window and the mitigation right is gone.

Stage writesOnly where write access and approval policy allow it
04 · Output1 mode
SX-06

Notice omits the refund option

A new estimated date goes out without the cancel-and-refund choice.

Stage returnsThe notice the manager releases and the buyer
05 · Change / Version1 mode
SX-07

Carrier code changes meaning

An API bump reclassifies delivery refused as in transit, and nothing announces it.

Stage tracksModel, prompt, carrier-API versions and notice templates
Sev-1 · a held act performed by the agent Sev-2 · a non-compliant notice reaches Sev-3 · feed degrades, exception routes to review

Affected slices

The worst cohort names itself

Cross-border parcels on a renewed notice are their own answer: mishandled exceptions run several times the all-shipment baseline there Nestack reports it by slice rather than in aggregate..

Slice performance — reported separately, not only in aggregateIllustrative example
SliceFailure rateLift Lift vs. thresholdStatus
Cross-border, renewed notice9.1%3.5× Review
Hazmat and cold chain, disrupted7.3%2.8× Review
Intermodal, claim deadline running3.9%1.5× Watch
Domestic parcel, first notice1.3%0.5× Normal
Bar: mishandled-exception lift vs. the all-shipment baseline · scale 0–4.0× · tick marks the 2.0× review threshold 2 of 4 slices over threshold

Evidence-linked improvement

The regression suite is what closes a cycle

A cycle is finished when the failure sits in the suite as a case the next release must pass.

Improvement cycle · five stagesSwitchback — the path turns at Improve and returns at Learn
01Detect

Mishandled exceptions rise on one lane.

02Diagnose

The manager reads the notices and the milestones behind them until one cause is left.

03Improve

The correction carries its version and the exceptions behind it.

04Verify

The affected cases are re-run before anything ships.

05Learn

It lands in the permanent suite and in the exception playbook.

Learn → DetectThe return edge. The next detection runs against a suite this cycle lengthened.

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, exception workflow, evaluation, integration, then production validation and handover.

Workstream Week 1Week 2Week 3Week 4Week 5Week 6
01Lane and exception-type discovery and boundary definition.
02Carrier, visibility and TMS source assessment.
03Notice-sequence, deadline and handling-rule mapping.
04Milestone ingestion and event normalisation.
05Exception classification and notice.
06Confidence scoring and release routing.
07Transport-manager release.
08Carrier, TMS and order-system integration.
09Notice regression cases.
10Guardrails and notice controls.
11Notice-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 lane, one carrier ProductionProduction carrier estate AdvancedMultiple modes / regions
Introduced at Pilot
Exception handling on your lanes
Manager release
Notice-timing baseline
Introduced at Production
Reporting by lane
Release workflow in your systems
Approved write-back
Visibility-platform integration
Introduced at Advanced
Multi-jurisdiction notice rules
Multi-stage transport approvals
High shipment volume
Enterprise carrier 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 lanes, carriers and service commitments Milestone ingestion and event normalisationWeek 1
02Representative exceptions already worked Exception-classification baseline and notice draftingWeek 2
03Your notice templates and consent logic Notice-sequence and handling-rule mapping, and automation-boundary definitionWeek 1
04Access to relevant APIs, feeds or exports Carrier, visibility and TMS assessment, then integration setupWeek 2
05Exceptions you found out about late Notice-timing cases and the evaluation suiteWeek 4
06What must reach a person before a notice goes out Exception thresholds, notice routing and controlsWeek 3
07A named transport manager to authorise reroutes Transport-manager release 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

Phases sit where the work is, which is why week 5 holds evaluation and pilot at the same time.

Phase W1W2W3W4W5W6
Discovery W1
Build W2 – W3
Evaluate W4 – W5
Pilot & Launch W5 – W6
Week focus W1Lane and exception discovery, notice mapping and the automation boundary W2Carrier feeds connected, then a baseline W3Exception workflow, confidence logic and release controls W4Notice-timing cases and carrier guardrails W5Carrier and TMS integration, pilot lanes and targeted corrections W6A week of live exceptions under the transport manager, then handover
Reading the bandWeek 5 shows two bars because two phases actually run in it.
At the end of W6Everything verified on live lanes, with Agent Care carrying it forward.
DurationSix-week plan shown · typical delivery 4–6 weeks depending on scope confirmed in discovery.

Next step · Retail AI agent

Build an exception agent around the manager who releases the notice.

Show us your lanes, your carriers and who signs a claim position. If your notice logic treats a renewed delay the way it treats the first one, the orders it leaves live have already been deemed cancelled unless the buyer affirmatively agreed — and a credit, a voucher or a gift card is not the refund that owes. We map the exception workflow, set the automation boundary, and name what stays with the transport manager, the claims manager, the hazmat employee and your broker.

Nestack Agents · Shipping and route exceptionsAGT-RT-07 · Agent Care available after launch