Driver-Support Copilot AI Agent

What this agent does

Answers the question, and stops where it must

When a driver asks, the copilot reads your policies, the recorded clock and the load from supported fleet systems.

When a policy is quoted, the reply carries the document and the section it was read from.

Reason

Where the recorded clock is the answer, it is shown as recorded — not as permission to drive.

When hours remain but fatigue is raised, the copilot says the clock is not a fitness judgement (49 CFR 392.3).

Where a driver cites hours, fatigue, illness or a defect, the exchange stops and routes to a person.

Decide

When a request has already been refused, it is never put a second way, reframed or re-costed.

Where pay, ranking, priority or standing would answer, that output is blocked instead (49 CFR 390.6).

Out

When the vehicle is moving, the copilot will not press for a reply (49 CFR 392.80, 392.82).

Where a write is needed, it happens only inside the approval boundaries agreed during implementation.

→ Product statement

The copilot answers; a named manager takes whatever it stops on, and the driver's own judgement under 49 CFR 392.3 stays the last word.

Example workflow

One question, driver to manager

AgentHuman

1Driver question receivedIn-cab app, phone, message thread or driver portal

2Policy and record gatheredYour written policies, the recorded duty status, the load and the unit's open defects, each with its source

3Answer draftedAnswer, the policy cited and confidence

4Controls appliedCoercion-gate checks, consequence-language blocks, duty-status gate and confidence threshold

No human action required

Stages 1 to 4 run unaided and press nobody — a refusal ends the exchange where it was made, and the manager's lane opens at the confidence gate.

5DecisionBranches at the confidence threshold

High confidence

Answers the driver from the policy.

Low confidence

Adds a manager's read first.

Manager hand-off

The exchange is held with the driver's words, the policy read and the confidence.

Acknowledge · Answer · Send to manager

Taken — handed to a person▼

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

7Outcome evaluatedStops taken, blocked consequence language, manager hand-offs and what the driver did next

Hand-offs

Every manager hand-off is counted in the evaluation.

What should not run autonomously

Human approval stays in control

Outside the boundary — human approval required8 items

Telling a driver they are fit or safe to drive.

Editing, certifying or resubmitting the hours record.

Re-asking after a driver has refused to drive.

Raising pay, ranking or standing in an hours exchange.

Automation boundaryAgent acts unaided

✓Answer routine questions from your own written policies for the named owner.

✓Show the recorded clock, and the section it came from.

✓Stop the exchange when a driver cites hours or fatigue.

✓Log the driver's words and the copilot's reply verbatim into the review queue.

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

Clearing a reported defect or releasing the unit.

Giving a driver legal, medical or compliance advice.

Deciding whether a driver should be disciplined.

Changes to the escalation rules or the stop gates.

Example output

One exchange, annotated

Everything the copilot says is attached to the policy it was read from.

Driver-support output · single exchangeIllustrative example

Driver

What was asked

Recorded clock

Policy read

Confidence

What happened next

Regional line-haul

“I am out of hours for that delivery window”

1h 40m on the 14

Fatigue and hours policy

91%

Stopped, handed to a manager

As receivedTaken from the driver's own words and the recorded duty status — nothing on this side is inferred by the copilot.

What was read Your fatigue policy The recorded duty status The unit's open defects

Why it stoppedThe driver cited hours — under 49 CFR 390.6 the next sentence is the carrier's.

ActionAcknowledgeAnswerSend to manager

What the score decidesBelow the configured threshold the exchange picks up a manager's read before.

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 driver questionFrom the cab or the app

03Answering

Answer from your policy

Draw on your own written policies, the recorded duty status and the load record for this driver.

01Approved path

Answer without pressing

Routine policy and paperwork questions come back already answered.

02Human review

Send the rest to a person

Stops, blocked outputs and low-confidence answers are marked, so the manager's read starts where risk concentrates.

04Build an evidence trail

The question, the policy it was answered from and the manager who took it stay on the record.

Integrations

Typical integrations

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

Fleet and hours systemsSamsara · Motive
Omnitracs · Platform Science

Dispatch and TMSMcLeod · Trimble
MercuryGate · Revenova

Driver channelsIn-cab app · messaging
Driver portal · phone

Agent

Driver-support assistance

Reads the policy
Answers the driver
Stops and escalates

People and settlementHR systems · payroll
Safety and compliance

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 driver

Every layer wraps the next. What none of them catches is in the map below.

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

L6Rollback / safe modeFall back to signposting when evaluation or production signals degrade.Roll back

L5Version monitoringTrack model, prompt, stop-gate and policy-source configuration changes.Track

L4TraceabilityRecord the driver's words, the copilot's reply and the hand-off time.Record

L3Manager hand-offHand the exchange to a named manager; it governs who speaks next, not what the driver decides.Gate

L2Coercion gatesTest each reply against the 390.6 stop rules and the consequence-language block; a failure returns it.Restrict

L1Confidence thresholdsRoute low-confidence answers to a manager's read before the driver sees them.Require review

Model coreAnswer drafted — the reply, the policy cited, the stop result and confidence

L1 – L2Test whether a reply may stand

L3Puts the next word in a manager's hands

L4 – L5Hold the answer and the policy behind it

L6Falls back to signposting when signals degrade

How Nestack evaluates it

Evaluate the whole exchange — 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 driver reads

Depth of coverage ▼

E1Final-output evaluationDid the reply match the policy section it cited?

E2Step-level evaluationDid the copilot read the right policy, clock and load for this driver?

E3Tool evaluationDid it read the correct driver and write the correct record?

E4Confidence calibrationDo low-confidence replies actually attract more manager hand-offs?

E5Slice evaluationHow does performance change across specific question types?

E6Business outcomeHow many exchanges should have stopped, and how many of them did?

Floor — the driver who has to decide

Failure modes

Where each failure originates in the agent

Seven ways an exchange goes wrong, by stage.

Agent lifecycleDirection of processing →

01 · Retrieval1 mode

AI-03

Superseded policy read

The reply is drawn from a policy version no longer in force.

Stage gathersPolicies, duty status, load record and open defects

02 · Reasoning2 modes

AI-04

Clock read as permission

A legal clock is treated as a judgement about fitness.

AI-06

Consequence in the reply

Pay, ranking or standing surfaces in an hours exchange.

Stage proposesThe reply, the policy cited and confidence

03 · Tool / write2 modes

AI-02

Reply sent without a person

A write answers the driver before a manager has taken it.

AI-05

Refused request, put again

The same request comes back put a second way.

Stage writesOnly where write access and approval policy allow it

04 · Output1 mode

AI-01

Answer without its policy

A reply is returned with no policy or section behind it.

Stage returnsThe reply the driver reads and may act on

05 · Change / Version1 mode

AI-07

Silent gate regression

A model or rule change narrows what the stop gates catch.

Stage tracksModel, prompt, stop gates and policy sources

Sev-1 · a driver is pressed after refusing Sev-2 · a wrong answer reaches the driver Sev-3 · a policy source degrades, reply routes to review

See the complete Transportation failure-mode catalogue →

Affected slices

Overall answer quality can hide one question type

The exchanges an average under-counts are the fatigue ones — rare enough to disappear fleet-wide, and the ones where being wrong is a 49 CFR 390.6 problem. Nestack reports the hand-off rate by question type, not only in total.

Slice performance — reported separately, not only in aggregateIllustrative example

Slice	Failure rate	Lift	Status
Fatigue and fitness to drive	6.3%	3.7×	Review
Hours and duty-status questions	3.9%	2.3×	Review
Defect and DVIR questions	2.5%	1.5×	Watch
Routine paperwork questions	1.4%	0.8×	Normal

Bar: hand-off-rate lift vs. routine-paperwork baseline · scale 0–4.0× · tick marks the 2.0× review threshold 2 of 4 slices over threshold

Evidence-linked improvement

A person picks it up, then it closes

The loop shuts when the miss is a case in the suite, not when it has been explained. That suite is what the next driver question is measured against.

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

01Detect

Hand-off rate rises in a question type.

02Diagnose

The manager who took the exchange reads it back against the policy until one cause holds.

03Improve

Whatever changes ships against a version, with the exchanges that prompted it attached.

04Verify

Nothing ships until the affected cases pass a second time.

05Learn

The suite grows by one case; so does the coercion guardrail set.

Learn → DetectThe 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

01Driver-support workflow discovery and boundary definition.

02Fleet, ELD and channel source assessment.

03Policy, stop-gate and coercion-guardrail rule mapping.

04Question and duty-status ingestion.

05Answering logic and policy binding.

06Confidence scoring and stop routing.

07Manager hand-off workflow.

08Fleet and driver-channel integration.

09Coercion-language cases.

10Guardrails and escalation controls.

11Exchange-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 terminal, one channel ProductionProduction fleet systems AdvancedMultiple terminals / channels

Introduced at Pilot

Answering from your own policies✓✓✓

Manager hand-off✓✓✓

Answer-quality baseline✓✓✓

Introduced at Production

Reporting by question type—✓✓

Hand-off workflow in your systems—✓✓

Approved write-back—✓✓

Fleet-system integration—✓✓

Introduced at Advanced

Multi-terminal policy sets——✓

Multi-stage escalation paths——✓

High question volume——✓

Multi-terminal support 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 driver policies and escalation paths → Question and duty-status ingestion and policy mappingWeek 1

02Representative past driver exchanges → Answering baseline, policy binding and the stop gatesWeek 2

03Your policy source and your stop rules → Policy, stop-gate and coercion-guardrail rule mappingWeek 1

04Access to relevant APIs, feeds or exports → Fleet, ELD and channel assessment, then integration setupWeek 2

05Answers you would not want a driver to act on → Coercion cases and failure-mode testingWeek 4

06Where an answer must stop and wait for a person → Confidence scoring, stop routing, guardrails and escalation controlsWeek 3

07Named managers to take held exchanges → Manager hand-off 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 real work rather than a plan, so evaluation and pilot genuinely share the fifth week.

Phase W1W2W3W4W5W6

Discovery W1

Build W2 – W3

Evaluate W4 – W5

Pilot & Launch W5 – W6

Week focus W1Driver-support workflow discovery, policy mapping and the boundary W2Fleet, ELD and channel integration and the answering baseline W3Answering workflow, confidence logic and escalation controls W4Evaluation suite, coercion cases and failure-mode testing W5Channel integration, a pilot driver queue and targeted corrections W6A live driver queue answered under supervision, then Agent Care handover

Reading the bandBars are drawn over the weeks the work occupies. The fifth week doubles because evaluation and launch overlap.

At the end of W6Once the queue validates, Agent Care owns the running agent.

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

Next step · Transportation AI agent

Build a driver-support copilot that stops where the rule says stop.

Show us your driver policies, your channels and who takes an escalation. Being wrong here is not a poor answer — it is a written record of a driver pressed after saying no, and 390.6(b) gives that driver somewhere to file it.

Discuss this agent →

Nestack Agents · Driver supportAGT-TR-03 · Agent Care available after launch