Main site

Transportation AI agent · Documents

Freight Document Processing AI Agent

Read rate confirmations, bills of lading and invoices into structured records, carry the page each field came from, and never generate, amend or replace the document itself.

Typical delivery
4–6 weeks
Deployment
Your stack
Person accepts
Original kept
After launch
Agent Care

What this agent does

Reads the document, writes only the record

In

  1. 01

    Rate confirmations, bills of lading and invoices, ingested from supported TMS, document, email or EDI sources.

  2. 02

    Field labels and formats normalised in the record only, with the page and the document each value was read from.

Reason

  1. 03

    A rate confirmation as a contract — terms extracted and compared, never amended.

  2. 04

    A bill of lading as a receipt, a contract of carriage and sometimes a document of title.

  3. 05

    The straight-versus-order distinction surfaced, because endorsing the wrong one moves title.

Decide

  1. 06

    Declared-value and limitation-of-liability terms flagged for a person, because they set what is recoverable after a loss.

  2. 07

    An invoice as an assertion — tested against the contract, with any absence reported.

Out

  1. 08

    Electronic bills kept as documents of title: derived copies marked non-authoritative.

  2. 09

    Write actions executed only inside the approval boundaries agreed during implementation.

Product statement

The agent reads and structures; a named person accepts each field, and the original document stays where it is, unchanged.

Example workflow

One document, arrival to acceptance

  1. 1Document receivedRate confirmation, bill of lading, commercial invoice or supporting paperwork
  2. 2Document type establishedWhat the document legally is, what may lawfully be done to it, and the pages each field is read from
  3. 3Record preparedFields, page references and confidence
  4. 4Controls appliedDocument-type rules, required-element checks, authoritative-copy marking and the confidence threshold

No human action required

Stages 1 to 4 run unaided and alter no document — the record is prepared, and the person's lane opens at the confidence gate.

5DecisionBranches at the confidence threshold
High confidence

Goes to the named person to accept.

Low confidence

Adds a document-desk read first.

A person accepts

The record is held with its page references, its flags and the confidence.

Accept · Correct · Send to the document desk

Accepted — record released

  1. 6Downstream systems updatedOnly where write access and approval policy allow it
  2. 7Outcome evaluatedField accuracy, corrections on acceptance, absent-element reports and downstream rework

Corrections

Every correction made on acceptance is counted in the evaluation.

What should not run autonomously

Human approval stays in control

Outside the boundary — human approval required

8 items

  • Generating, altering or re-issuing a bill of lading.
    • Amending, signing or accepting a rate confirmation.
    • Generating an invoice or filling a field left blank.
    • Deciding which values populate a customs entry.

  • Automation boundary

    Agent acts unaided

    • ✓Read the document and write the structured record from it.
    • ✓Carry each field forward with the page it was read from.
    • ✓Compare extracted terms against the tender and the agreement.
    • ✓Report a required element as absent, and hold it for a person.

    Any write happens inside the boundaries agreed at implementation, and never to the document itself.

    • Setting a declared value or a limitation of liability.
    • Deciding the country of origin of imported goods.
    • Holding or emitting an authoritative electronic copy.
  • Changes to extraction rules, thresholds or approvals.

Example output

One extracted field, annotated

Everything the agent extracts is attached to the page it was read from.

Extraction output · single document

Illustrative example
Document
Order bill of lading
Extracted field
Declared value stated on the face of the bill
Value read
$50,000.00
Page reference
Page 1, value box
Confidence
88%
Status
Flagged, original untouched

As received

Taken from the page as it was scanned — nothing on this side is inferred, and the document itself is not changed.

What the page shows

  • The value box as printed
  • The negotiability marking
  • The named consignee

Why it stops here

A declared value sets what is recoverable after a loss and a person still decides.

What the score decides

Below the configured threshold the field picks up a document-desk read before it.

Action

AcceptCorrectSend to the document desk

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 document

From the intake channel or the TMS

03Reading

Read to the rules for the type

Draw on what the document legally is, the pages in front of the agent and your field definitions.

01Approved path

Read it, keep the original

Routine documents come back as records, with page references attached.

02Human review

Send the rest to a person

Absent elements, ambiguous terms and low-confidence fields are marked, so the operator's read starts where risk concentrates.

04

Build an evidence trail

The extracted field, the page it came from and the person who accepted it stay with the document.

Integrations

Typical integrations

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

  • Document intake

    • Email
    • scanned mail
    • SharePoint
    • Box
    • Dropbox

  • TMS and shipment records

    • McLeod
    • MercuryGate
    • Trimble
    • Revenova

  • eBL and trade platforms

    • Bolero
    • essDOCS
    • WaveBL
    • Carrier eBL portals

Agent

Freight document processing

  • Reads the document
  • Writes the record
  • Holds for a person

  • Payables and EDI

    • EDI 210
    • 214
    • 990
    • ERP and payables

  • 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 record

Controls stack inward. What the stack does not catch is set out in the map below.

L6 · Outermost — last line of defence

Inward → L1 · closest to the model

L6Rollback / safe modeNarrow the agent to filing and indexing when evaluation or production signals degrade.Roll back
L5Version monitoringTrack model, prompt, extraction-rule and document-type configuration changes.Track
L4TraceabilityRecord the document, the page, the extracted field, the flags and who accepted it.Record
L3Person acceptsHold the record for a named person; it governs what is accepted, not whether the document is genuine.Gate
L2Policy guardrailsTest records against the configured document-type and required-element rules; a failure returns the record.Restrict
L1Confidence thresholdsRoute low-confidence fields to a document-desk read before the person sees them.Require review
Model coreRecord produced — fields, page references, flags and confidence
L1 – L2
Test whether a record may stand
L3
Puts acceptance in a person's hands
L4 – L5
Keep the field and the page it came from
L6
Narrows to filing and indexing when signals degrade

How Nestack evaluates it

Evaluate the reading workflow — not only the finished record.

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

Surface — the record the business acts on

  1. E1Final-output evaluationDid each extracted field match the page it was read from?
  2. E2Step-level evaluationDid the agent apply the rules for the document type in front of it?
  3. E3Tool evaluationDid it read and write the correct document and the correct field?
  4. E4Confidence calibrationDo low-confidence fields actually attract more corrections on acceptance?
  5. E5Slice evaluationHow does performance change across specific document types?
  6. E6Business outcomeHow many fields were corrected, or reworked after acceptance?

Floor — the outcome the operations team answers for

Failure modes

Where each failure originates in the agent

Seven ways a read goes wrong, placed at its own stage.

Agent lifecycle

Direction of processing →

  1. 01 · Retrieval

    1 mode

    • BD-03

      Wrong copy read

      A field is taken from a superseded or duplicate copy.

    Stage gathers

    Rate confirmations, bills of lading

  2. 02 · Reasoning

    2 modes

    • BD-04

      Document type misread

      A contract is handled under the rules for an assertion.

    • BD-06

      Ambiguity settled silently

      An unclear term is recorded as though it were agreed.

    Stage proposes

    Fields, page references and confidence

  3. 03 · Tool / write

    2 modes

    • BD-02

      Absence supplied

      A blank required element is filled by inference.

    • BD-05

      Derived copy unmarked

      A derived artefact circulates without its marking.

    Stage writes

    Only where write access and approval policy allow it

  4. 04 · Output

    1 mode

    • BD-01

      Page reference lost

      A field arrives without the page it was read from.

    Stage returns

    The record a person accepts and the business acts on

  5. 05 · Change / Version

    1 mode

    • BD-07

      Silent extraction regression

      A model or rule change widens what the agent asserts from a page.

    Stage tracks

    Model, prompt, extraction rules and type config

  • Sev-1 · a document is written or altered
  • Sev-2 · a wrong field reaches a downstream system
  • Sev-3 · scan degrades, field routes to review
See the complete Transportation failure-mode catalogue

Affected slices

Overall accuracy can hide a document type

Handwritten bills of lading are the cohort a total under-counts: a small share of the volume, a large share of the corrections. Nestack reports the correction rate by document type, not only in aggregate.

Slice performance — reported separately, not only in aggregate

Illustrative example
SliceFailure rateLiftLift vs. thresholdStatus
Handwritten bills of lading5.1%3.2×Review
Scanned and faxed copies4.3%2.7×Review
Non-English invoices3.0%1.9×Watch
Digital rate confirmations1.0%0.6×Normal

Bar: correction-rate lift vs. digital rate-confirmation baseline · scale 0–4.0× · tick marks the 2.0× review threshold

2 of 4 slices over threshold

Evidence-linked improvement

A cycle closes on a case, not a correction

An apology does not close a cycle; a case the next release must pass does. That suite is what the next document read into the system is measured against.

Improvement cycle · five stages

Switchback — the path turns at Improve and returns at Learn

  1. 01

    Detect

    Corrections rise in one document type.

  2. 02

    Diagnose

    No cause is accepted until the document, the page and the extracted field have been read back against each other.

  3. 03

    Improve

    The correction is versioned, with the documents that motivated it attached.

  4. 04

    Verify

    A failing case holds the release until it passes.

  5. 05

    Learn

    The case is added permanently, and the extraction rules move with it.

  6. Learn → Detect

    The return edge. The next document read is measured 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, reading workflow, evaluation, integration, then production validation and handover.

Workstream

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

  1. 01Document workflow discovery and boundary definition.Week 1
  2. 02Document, TMS and EDI source assessment.Week 1, Week 2
  3. 03Document-type rules and required-element field mapping.Week 1, Week 2
  4. 04Document ingestion and field normalisation.Week 2
  5. 05Extraction logic and page binding.Week 2, Week 3
  6. 06Confidence scoring and field routing.Week 3
  7. 07Acceptance workflow.Week 3, Week 4
  8. 08Document-system integration.Week 5
  9. 09Field-extraction regression cases.Week 4, Week 5
  10. 10Guardrails and acceptance controls.Week 4
  11. 11Document-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 document type, one laneProductionProduction document systemsAdvancedMultiple formats / entities
Introduced at Pilot
Reading to your document rules✓✓✓
A person accepts each field✓✓✓
Extraction-accuracy baseline✓✓✓
Introduced at Production
Reporting by document type—✓✓
Acceptance workflow in your systems—✓✓
Approved record write-back—✓✓
Document-system integration—✓✓
Introduced at Advanced
Multi-format and multi-language rules——✓
Multi-stage acceptance approvals——✓
High document volume——✓
Multi-format document 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 document types and where each one arrives

    Document-type rules and required-element mapping

    Week 1

  2. 02Representative documents, including the bad scans

    Extraction baseline, field normalisation and page binding

    Week 2

  3. 03Your field definitions and the record they feed

    Extraction-rule mapping and automation-boundary definition

    Week 1

  4. 04Access to relevant APIs, feeds or exports

    Document, TMS and EDI assessment, then integration setup

    Week 2

  5. 05Fields you would not want posted

    Extraction cases and the evaluation suite

    Week 4

  6. 06What an extracted field may never replace

    Confidence scoring, field routing, guardrails and acceptance controls

    Week 3

  7. 07Named people to accept extracted fields

    Acceptance 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 band covers the weeks the work really takes, so week 5 carries evaluation and launch together.

Phase

W1

W2

W3

W4

W5

W6

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

Week focus

W1Document workflow discovery, type rules and the automation boundary

W2Source integration and the extraction baseline

W3Extraction workflow, confidence logic and acceptance controls

W4Evaluation suite, required-element checks and failure-mode testing

W5Document-system integration, pilot documents and targeted corrections

W6One document cycle read under the operations team, then handover

Reading the band
A bar sits on the weeks its work is named in and no others. The week 5 overlap is real work, not padding.
At the end of W6
Validation finishes on live documents and Agent Care assumes monitoring.
Duration
Six-week plan shown · typical delivery 4–6 weeks depending on scope confirmed in discovery.

Next step · Transportation AI agent

Build a document agent around what may lawfully be done to each document.

Which documents may the agent only read, which may it compare, and who accepts a field before it moves? Show us where they arrive, and we'll map the workflow and set the boundary.

Typical delivery
4–6 weeks
Deployment
Your document channels
Person accepts
Original kept
After launch
Agent Care available

Nestack Agents · Freight document processing

AGT-TR-15 · Agent Care available after launch

Build a document agent

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

About you
Your documents

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