Main site

Transportation AI agent · Delivery WISMO

Delivery and WISMO Chatbot AI Agent

Answer 'where is my order' from the order record itself, disclose that it is AI before anything else, and leave promising a date and granting a remedy to a person.

Typical delivery
4–6 weeks
Deployment
Your stack
Person promises
Discloses first
After launch
Agent Care

What this agent does

Answers from the record, and promises nothing

In

  1. 01

    Ingest the order, the shipment record and the merchant's own policy text from supported order, desk or carrier sources.

  2. 02

    Disclose at the first interaction, proactively and in plain language, because Maine's rule carries no intent element.

Reason

  1. 03

    Meet the EU disclosure duty where an EU person is on the other end, enforceable since August.

  2. 04

    Quote policy from the merchant's controlled corpus rather than composing it, and cite the record each answer rests on.

  3. 05

    State a carrier estimate as an estimate, and a committed date only where the record actually holds one.

Decide

  1. 06

    Enforce remedy caps, entitlement and eligibility in the tool layer, server-side, never by prompt instruction.

  2. 07

    Decline and escalate anything it cannot substantiate, in preference to a plausible answer.

Out

  1. 08

    Retain the conversation verbatim, because the transcript is the representation your firm made.

  2. 09

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

Product statement

The agent answers; a named person promises a date or grants a remedy, and whatever the bot said, your firm said.

Example workflow

One enquiry, question to answer

  1. 1Enquiry receivedChat, email, portal message or a post-purchase tracking page
  2. 2Records gatheredThe order, the shipment record, the carrier's latest status and the merchant's policy text, each with its source
  3. 3Answer preparedAnswer, sources, remedy state, confidence
  4. 4Controls appliedDisclosure checks, source-binding checks, remedy caps and the confidence threshold

No human action required

Stages 1 to 4 run unaided and promise nothing — the answer is drafted, and the person's lane opens at the confidence gate.

5DecisionBranches at the confidence threshold
High confidence

Answers from the record.

Low confidence

Hands to an agent first.

A person takes it

The answer is held with its source records and the confidence.

Send · Amend · Hand to an agent

Answered — or handed to a person

  1. 6Order records updatedOnly where write access and approval policy allow it
  2. 7Outcome evaluatedDisclosures delivered, sources cited, hand-offs taken and what each enquiry actually needed

Hand-offs

Every hand-off to a person is counted in the evaluation.

What should not run autonomously

Human approval stays in control

Outside the boundary — human approval required

8 items

  • Promising a consumer a delivery or shipping date.
    • Re-promising a date once the first one has slipped.
    • Granting a refund, a credit or any other remedy.
    • Stating a policy that is not in the policy corpus.

  • Automation boundary

    Agent acts unaided

    • ✓Disclose that it is an AI system at the first interaction.
    • ✓Answer from the order and shipment records, with the source.
    • ✓Quote the merchant's own policy text rather than writing it for the named owner.
    • ✓Hand over to a person the moment it cannot substantiate.

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

    • Deciding whether an order may still be cancelled.
    • Answering on liability for loss or for damage.
    • Turning the AI disclosure off for a given market.
  • Changes to the policy corpus or the remedy caps.

Example output

One answer, annotated

No US appellate court has ruled on a chatbot's words, so everything here is tied to its record.

Answer output · single enquiry

Illustrative example
Order
Two-item parcel
What was answered
In transit, with the carrier's own estimate quoted as an estimate
Carrier estimate
Est. Thursday
Record it came from
Carrier tracking record
Confidence
92%
Disclosure given
AI disclosed at first message

As received

Taken from the order and shipment records — nothing on this side is recalled by the model or written by it.

What it was read from

  • The order record itself
  • The carrier's tracking status
  • The merchant's policy text

Why it is not a promise

Apparent authority, negligent misrepresentation and FTC Act §5 are the live exposure.

What the score decides

Below the configured threshold the answer picks up a person before the consumer ever sees it.

Action

SendAmendHand to an agent

Value

Where AI adds value

The same four claims, placed at the point in the workflow where each one applies.

Where the value lands

Value 01 – 04

Every enquiry

From chat, email or the portal

03Answering

Answer from the record

Draw on the order, the shipment record and the merchant's own controlled policy text.

01Approved path

Tell them what is known

Routine status questions come back answered and sourced.

02Human review

Send the rest to a person

Date requests, remedy asks and low-confidence answers are marked, so the team's read starts where risk concentrates.

04

Build an evidence trail

The answer, the tracking record behind it and the agent who took it over stay on the enquiry.

Integrations

Typical integrations

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

  • Order and commerce

    • Shopify
    • Salesforce
    • SAP
    • Oracle Commerce

  • Service desk

    • Zendesk
    • Gorgias
    • Intercom
    • Freshdesk

  • Carrier tracking

    • Carrier APIs
    • EDI
    • Visibility platforms

Agent

Delivery and WISMO answers

  • Reads the record
  • Discloses and answers
  • Hands over on ask

  • Policy and transcripts

    • Policy corpus
    • knowledge base
    • Transcript archives

  • Observability & evaluation

    • OpenTelemetry
    • 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 customer

Each control wraps the one inside it. What a layer does not catch is named in the map below it.

L6 · Outermost — last line of defence

Inward → L1 · closest to the model

L6Rollback / safe modeDrop the agent to status-only answers when evaluation or production signals degrade.Roll back
L5Version monitoringTrack model, prompt, policy-corpus and disclosure-text changes.Track
L4TraceabilityRecord the transcript, the sources cited and the disclosure delivered.Record
L3Person on requestHand the enquiry to a named person on request; it governs who answers next, not what was already said.Gate
L2Remedy capsTest each remedy against caps and entitlement in the tool layer; a failure stops the answer.Restrict
L1Confidence thresholdsRoute low-confidence answers to a person before the consumer sees them.Require review
Model coreAnswer prepared — the text, its sources, the remedy state and confidence
L1 – L2
Test whether an answer may go out
L3
Puts the reply in a person's hands
L4 – L5
Keep the answer and the tracking record behind it
L6
Drops the agent to status-only when signals degrade

How Nestack evaluates it

Evaluate the whole conversation — not only the sentence that answered.

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

Surface — the reply the customer reads

  1. E1Final-output evaluationDid the disclosure land at the first interaction, before anything else?
  2. E2Step-level evaluationDid the agent read the right order, shipment and policy text?
  3. E3Tool evaluationDid it read the correct order and write the correct case?
  4. E4Confidence calibrationDo low-confidence answers actually attract more hand-offs?
  5. E5Slice evaluationHow does performance change across specific enquiry types?
  6. E6Business outcomeHow many answers were handed over, and how many should have been?

Floor — the promise your firm has to honour

Failure modes

Where each failure originates in the agent

Seven ways an answer goes wrong, placed by stage.

Agent lifecycle

Direction of processing →

  1. 01 · Retrieval

    1 mode

    • BA-03

      Stale shipment record

      The answer rests on a status the carrier has since moved.

    Stage gathers

    Order, shipment record, carrier status and policy

  2. 02 · Reasoning

    2 modes

    • BA-04

      Estimate stated as a date

      A carrier prediction is repeated as a firm commitment.

    • BA-06

      Policy written, not quoted

      A rule is composed rather than taken from the corpus.

    Stage proposes

    The answer, its sources and confidence

  3. 03 · Tool / write

    2 modes

    • BA-02

      Remedy granted in chat

      A refund is offered before entitlement was checked.

    • BA-05

      Duplicate case raised

      One enquiry opens the same case twice over.

    Stage writes

    Only where write access and approval policy allow it

  4. 04 · Output

    1 mode

    • BA-01

      Disclosure arrives late

      The AI notice lands after the first substantive reply.

    Stage returns

    The reply the customer reads and relies on

  5. 05 · Change / Version

    1 mode

    • BA-07

      Silent policy regression

      A model or corpus change widens what the agent will state.

    Stage tracks

    Model, prompt, policy corpus and disclosure text

  • Sev-1 · remedy with no person
  • Sev-2 · a date the record cannot support
  • Sev-3 · record degrades, answer routes on
See the complete Transportation failure-mode catalogue

Affected slices

Take the total apart by enquiry type first

Do not read the aggregate until it is split: two enquiry types carry the hand-offs, and averaging them into the routine ones makes both invisible. Nestack reports the hand-off rate per enquiry type.

Slice performance — reported separately, not only in aggregate

Illustrative example
SliceFailure rateLiftLift vs. thresholdStatus
Delayed or missed delivery dates3.5%3.3×Review
Refund and remedy requests2.7%2.6×Review
Lost or damaged parcels1.9%1.8×Watch
Routine in-transit status0.6%0.6×Normal

Bar: hand-off-rate lift vs. routine-status baseline · scale 0–4.0× · tick marks the 2.0× review threshold

2 of 4 slices over threshold

Evidence-linked improvement

Unless it becomes a test, it is only a note

A cycle closes when the failure is a regression case the next release has to pass. That suite is what the next enquiry answered is measured against.

Improvement cycle · five stages

Switchback — the path turns at Improve and returns at Learn

  1. 01

    Detect

    Hand-off rate rises in an enquiry type.

  2. 02

    Diagnose

    The transcripts and the records behind them are read until one cause holds.

  3. 03

    Improve

    The change ships against a version, with the enquiries that exposed it attached.

  4. 04

    Verify

    Release is blocked until the affected regression cases pass again.

  5. 05

    Learn

    The case joins the permanent suite and the service playbook.

  6. Learn → Detect

    The 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, answering workflow, evaluation, integration, then production validation and handover.

Workstream

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

  1. 01Enquiry workflow discovery and boundary definition.Week 1
  2. 02Order and carrier source assessment.Week 1, Week 2
  3. 03Disclosure, policy-corpus and remedy-cap rule mapping.Week 1, Week 2
  4. 04Order and shipment-record ingestion.Week 2
  5. 05Answer logic and source binding.Week 2, Week 3
  6. 06Confidence scoring and hand-off routing.Week 3
  7. 07Person-on-request workflow.Week 3, Week 4
  8. 08Order-system and service-desk integration.Week 5
  9. 09Promise and remedy cases.Week 4, Week 5
  10. 10Guardrails and escalation controls.Week 4
  11. 11Enquiry-trail instrumentation.Week 5, Week 6
  12. 12Deployment, documentation and Agent Care handover.Week 6

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 tierPilotOne market, one channelProductionProduction order and deskAdvancedMultiple markets / brands
Introduced at Pilot
Answering from your own records✓✓✓
Person on request✓✓✓
Answer-accuracy baseline✓✓✓
Introduced at Production
Reporting by service level—✓✓
Hand-off workflow in your systems—✓✓
Approved write-back—✓✓
Order-system integration—✓✓
Introduced at Advanced
Multi-market policy corpora——✓
Multi-stage remedy approvals——✓
High enquiry volume——✓
Multi-market service controls——✓
Build priceFrom $5,000From $8,000Custom quote
Final build price
Confirmed after discovery based on integrations, workflow complexity, transaction volume, approval controls and deployment requirements.
Separate from build
Build 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.

  1. 01Your order records and policy text

    Order and shipment-record ingestion and source binding

    Week 1

  2. 02Representative past enquiries

    Answer baseline, source binding and the policy corpus

    Week 2

  3. 03Your disclosure text and remedy caps

    Disclosure, policy-corpus and remedy-cap rule mapping

    Week 1

  4. 04Access to relevant APIs, feeds or exports

    Order and carrier source assessment, then integration setup

    Week 2

  5. 05Answers you would not want relied on

    Promise cases and the evaluation suite

    Week 4

  6. 06What an answer may never promise

    Confidence scoring, hand-off routing, guardrails and remedy controls

    Week 3

  7. 07Named people to take handed-over enquiries

    Person-on-request workflow, then pilot and production validation

    Weeks 5–6

Nothing else is required

Deployment, documentation and Agent Care handover are ours.

Delivery timeline

Four phases across six weeks

Each phase sits on the weeks it actually occupies, and week 5 carries both evaluation and launch work.

Phase

W1

W2

W3

W4

W5

W6

  1. DiscoveryW1
  2. BuildW2 – W3
  3. EvaluateW4 – W5
  4. Pilot & LaunchW5 – W6

Week focus

W1Enquiry workflow discovery, policy mapping and the boundary

W2Order and carrier integration and the answer baseline

W3Answering workflow, confidence logic and hand-off controls

W4Evaluation suite, promise cases and failure-mode testing

W5Service-desk integration, a pilot market and corrections

W6One peak week answered under supervision, then Agent Care handover

Reading the band
Each bar covers only the weeks its work is named in. The week 5 overlap is real, not padding.
At the end of W6
Validation closes on live enquiries, and Agent Care picks up monitoring.
Duration
Six-week plan shown · typical delivery 4–6 weeks depending on scope confirmed in discovery.

Next step · Transportation AI agent

Build a WISMO agent that discloses first and promises nothing.

Show us your order records, your policy text and the dates you state to customers. Tell us who signs off the disclosure wording and who owns the remedy caps — those two names set the outer edge of what the bot may ever say.

Typical delivery
4–6 weeks
Deployment
Your order stack
Person promises
Discloses first
After launch
Agent Care available

Nestack Agents · Delivery and WISMO answers

AGT-TR-12 · Agent Care available after launch

Build a WISMO agent

Four questions so the call starts from your actual setup — then pick a time that suits you.

About you
Your enquiries

No obligation. We’ll map the workflow, name the automation boundary and tell you if an agent is the wrong answer.