Main site

Transportation AI agent · Safety coaching

Safety-Coaching & Driver-Workforce AI Agent

Surface telematics and video events for a supervisor's coaching conversation, with the record behind each one attached, and keep the score out of hiring, discipline and discharge.

Typical delivery
4–6 weeks
Deployment
Your stack
Supervisor led
Coaching-first
After launch
Agent Care

What this agent does

Surfaces the event, never scores the person

In

  1. 01

    Ingesting triggered events, telematics and video from supported ELD, camera and fleet-safety sources.

  2. 02

    Carrying the record behind each event — the footage or the trace — through to the coaching queue.

Reason

  1. 03

    Prioritising events for a supervisor's conversation, because the conversation is the part the evidence credits.

  2. 04

    Stating what is being measured: a triggered event, not a crash, and those are two different claims.

  3. 05

    Keeping the score out of hiring, discipline, discharge and load allocation, and holding anything that touches employment.

Decide

  1. 06

    Auditing that no event penalises a required break, a refusal on hours or fatigue grounds, or a reported defect.

  2. 07

    Routing each flagged event to the named supervisor, who decides whether it is coached at all.

Out

  1. 08

    Retaining the event, its record and the coaching outcome under a schedule the fleet approves.

  2. 09

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

Product statement

The agent surfaces events; a named supervisor holds the conversation, and no telematics score decides a person's employment.

Example workflow

One event, trigger to conversation

  1. 1Event triggeredTelematics trigger, in-cab camera event, ELD signal or a reported concern
  2. 2Record assembledThe footage or trace, the route, the equipment, the conditions and the prior coaching history
  3. 3Event preparedEvent, record, exposure notes and confidence
  4. 4Controls appliedEmployment-use blocks, protected-activity checks, exposure notes and the confidence threshold

No human action required

Stages 1 to 4 run unaided and reach no driver — the event is prepared, and the supervisor's lane opens at the confidence gate.

5DecisionBranches at the confidence threshold
High confidence

Goes to the named supervisor to coach.

Low confidence

Adds a safety-desk read first.

Supervisor coaches

The event is held with its record, its exposure notes and the confidence.

Coach · Dismiss · Send to the safety desk

Coached — conversation recorded

  1. 6Fleet-safety records updatedOnly where write access and approval policy allow it
  2. 7Outcome evaluatedFlag precision, dismissed events, coaching completion and repeat events by cause

Dismissals

Every supervisor dismissal is counted in the evaluation.

What should not run autonomously

Human approval stays in control

Outside the boundary — human approval required

8 items

  • Hiring, discipline, discharge or promotion decisions.
    • Allocating loads or ranking drivers by a score.
    • Deciding whether an event is coached, and how.
    • Holding the coaching conversation with a driver.

  • Automation boundary

    Agent acts unaided

    • ✓Surface triggered events with the record behind each one.
    • ✓Group events by cause so a supervisor can see the pattern into the review queue.
    • ✓Note the route, equipment and conditions around the event.
    • ✓Flag an event that penalises protected activity, and hold it for the named owner.

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

    • Turning on in-cab audio or a face-based model.
    • Directing how an owner-operator performs the work.
    • Setting or lifting a retention or litigation hold.
  • Changes to coaching rules, thresholds or approvals.

Example output

One triggered event, annotated

Everything the agent surfaces is attached to the record it came from.

Coaching output · single event

Illustrative example
Event
Following distance
What triggered
Close following on a wet interstate grade, running downhill
Duration
12 seconds
Record on file
Forward camera clip
Confidence
89%
Employment use
Blocked — coaching only

As received

Taken from the telematics trigger and the clip on file — nothing on this side is a judgement about the driver.

What the record shows

  • The forward clip
  • The route and the grade
  • The weather at the time

Why it is not a score

One event, on one road, in one condition and a person still decides.

What the score decides

Below the configured threshold the event picks up a safety-desk read before it.

Action

CoachDismissSend to the safety 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 triggered event

From telematics or the in-cab camera

03Coaching

Surface it for the conversation

Draw on the event record, the route and conditions around it, and the coaching rules your fleet configured.

01Approved path

Coach it, never score the person

Routine events arrive grouped by cause, with the record attached.

02Human review

Pass the rest to the supervisor

Ambiguous events, protected-activity flags and low-confidence triggers are marked, so the supervisor's read starts where risk concentrates.

04

Build an evidence trail

The event, the footage or telematics behind it and the supervisor who coached 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.

  • Telematics and ELD

    • Samsara
    • Motive
    • Omnitracs
    • Platform Science

  • Video safety

    • Lytx
    • Netradyne
    • Forward and in-cab cameras

  • Driver and training records

    • Driver files
    • HR systems
    • Training and LMS platforms

Agent

Safety coaching and workforce

  • Reads the event
  • Groups by cause
  • Holds for a supervisor

  • Safety and claims

    • Safety management systems
    • Incident and claims records

  • 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 driver

The controls are nested. What survives all of them appears in the map underneath.

L6 · Outermost — last line of defence

Inward → L1 · closest to the model

L6Rollback / safe modeHold coaching for the supervisor when evaluation or production signals degrade.Roll back
L5Version monitoringTrack model, prompt, trigger-threshold and coaching-rule changes.Track
L4TraceabilityRecord the event, the footage or trace, the flags, the decision and who coached.Record
L3Supervisor gateHold events for a named supervisor; it governs the conversation, not whether the trigger was fair.Gate
L2Policy guardrailsTest events against the configured employment-use and protected-activity rules; a failure returns the event.Restrict
L1Confidence thresholdsRoute low-confidence events to a safety-desk read before the supervisor sees them.Require review
Model coreEvent produced — trigger, record, exposure notes and confidence
L1 – L2
Test whether an event may stand
L3
Puts the conversation in a supervisor's hands
L4 – L5
Show the event and the record behind it
L6
Holds coaching for the supervisor when signals degrade

How Nestack evaluates it

Evaluate the coaching workflow — not only the trigger that fired.

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

Surface — the event a supervisor sees

  1. E1Final-output evaluationDid the event match the record behind it?
  2. E2Step-level evaluationDid the agent read the route, the conditions and the equipment around it?
  3. E3Tool evaluationDid it read and write the correct driver record and the correct event?
  4. E4Confidence calibrationDo low-confidence events actually attract more supervisor dismissals?
  5. E5Slice evaluationHow does performance change across specific route and duty types?
  6. E6Business outcomeHow many events were dismissed, or coached and then disputed?

Floor — the outcome the fleet answers for

Failure modes

Where each failure originates in the agent

Seven ways a flag goes wrong, set at its own stage.

Agent lifecycle

Direction of processing →

  1. 01 · Retrieval

    1 mode

    • BF-03

      Record not retrieved

      The footage or trace behind an event is missing.

    Stage gathers

    Triggers, footage, routes, conditions and coaching history

  2. 02 · Reasoning

    2 modes

    • BF-04

      Exposure dropped

      Route, weather and equipment fall out of the read.

    • BF-06

      Protected activity flagged

      A required break or a refusal is surfaced as a fault.

    Stage proposes

    Event, record, exposure notes and confidence

  3. 03 · Tool / write

    2 modes

    • BF-02

      Score reaches employment

      A telematics figure informs a decision about a person.

    • BF-05

      Duplicate event raised

      One incident is surfaced twice from two feeds.

    Stage writes

    Only where write access and approval policy allow it

  4. 04 · Output

    1 mode

    • BF-01

      Event without its record

      A flag arrives with no footage or trace behind it.

    Stage returns

    The event the supervisor reads and coaches on

  5. 05 · Change / Version

    1 mode

    • BF-07

      Silent threshold regression

      A model or threshold change widens what the agent will flag.

    Stage tracks

    Model, prompt, trigger thresholds and coaching rules

  • Sev-1 · a score touches an employment decision
  • Sev-2 · a wrong flag reaches a driver
  • Sev-3 · a feed degrades, event routes to review
See the complete Transportation failure-mode catalogue

Affected slices

One route type can carry the false flags

Base rates differ by route before any model runs. Night and long-haul work triggers far more often than regional daytime work, so a flag there means less. Nestack reports the dismissed-flag rate by route type, not only in total.

Slice performance — reported separately, not only in aggregate

Illustrative example
SliceFailure rateLiftLift vs. thresholdStatus
Night and long-haul runs8.2%3.4×Review
Urban stop-and-go routes5.5%2.3×Review
Winter and wet conditions4.3%1.8×Watch
Regional daytime runs2.2%0.9×Normal

Bar: dismissed-flag-rate lift vs. regional-daytime baseline · scale 0–4.0× · tick marks the 2.0× review threshold

2 of 4 slices over threshold

Evidence-linked improvement

A cycle ends in a standing case

Explaining a bad flag does not close the cycle. A standing regression case does, and that suite is what the next event flagged is measured against.

Improvement cycle · five stages

Switchback — the path turns at Improve and returns at Learn

  1. 01

    Detect

    Dismissed flags rise in one route type.

  2. 02

    Diagnose

    If the flag was wrong, the event, the record behind it and the coaching note are read back together until the cause is one thing.

  3. 03

    Improve

    The fix is versioned against the events that produced it.

  4. 04

    Verify

    The release stops until every affected case is passing.

  5. 05

    Learn

    The case stays in the suite, and the coaching policy is amended.

  6. Learn → Detect

    The return edge. The next event flagged 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, feeds, coaching workflow, evaluation, integration, then production validation and handover.

Workstream

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

  1. 01Coaching workflow discovery and boundary definition.Week 1
  2. 02Telematics, video and ELD source review.Week 1, Week 2
  3. 03Trigger, exposure and coaching-policy rule mapping.Week 1, Week 2
  4. 04Event ingestion and record normalisation.Week 2
  5. 05Cause grouping and exposure logic.Week 2, Week 3
  6. 06Confidence scoring and event routing.Week 3
  7. 07Supervisor coaching workflow.Week 3, Week 4
  8. 08Telematics and video integration.Week 5
  9. 09False-flag regression cases.Week 4, Week 5
  10. 10Guardrails and employment controls.Week 4
  11. 11Event-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 terminal, one fleetProductionProduction telematicsAdvancedMultiple terminals / fleets
Introduced at Pilot
Surfacing events to your coaching rules✓✓✓
Supervisor coaching gate✓✓✓
Flag-precision baseline✓✓✓
Introduced at Production
Reporting by event type—✓✓
Coaching workflow in your systems—✓✓
Approved record write-back—✓✓
Telematics integration—✓✓
Introduced at Advanced
Multi-state and union rule sets——✓
Multi-stage safety approvals——✓
High event volume——✓
Multi-terminal coaching 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 coaching policy and who holds the conversation

    Coaching-rule mapping and the employment-use boundary

    Week 1

  2. 02Representative events, including the ones you dismissed

    Flag baseline, cause grouping and exposure notes

    Week 2

  3. 03Your route, duty and equipment mix

    Exposure mapping and automation-boundary definition

    Week 1

  4. 04Access to relevant APIs, feeds or exports

    Telematics, video and ELD assessment, then integration setup

    Week 2

  5. 05Flags you would not want acted on

    False-flag cases and the evaluation suite

    Week 4

  6. 06What must reach a supervisor before it touches employment

    Confidence scoring, event routing, guardrails and employment-use controls

    Week 3

  7. 07Named supervisors to coach on events

    Supervisor coaching 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

Phases occupy the weeks the work really needs, so week 5 runs evaluation and launch side by side.

Phase

W1

W2

W3

W4

W5

W6

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

Week focus

W1Coaching workflow discovery, rule mapping and the automation boundary

W2Telematics integration and the flag baseline

W3Coaching workflow, confidence logic and supervisor controls

W4Evaluation suite, false-flag cases and failure-mode testing

W5Video integration, pilot terminals and targeted corrections

W6One coaching cycle run under safety, then handover

Reading the band
A bar runs across the weeks its work is named in and no more. The week 5 overlap is real work, not padding.
At the end of W6
The cycle closes validation and Agent Care picks up the monitoring.
Duration
Six-week plan shown · typical delivery 4–6 weeks depending on scope confirmed in discovery.

Next step · Transportation AI agent

Build a coaching agent around the supervisor who holds the conversation.

If you show us your coaching policy, your event feeds and who holds the conversation, we'll map the workflow, set the automation boundary and name what never touches employment.

Typical delivery
4–6 weeks
Deployment
Your telematics and video
Supervisor led
Coaching-first
After launch
Agent Care available

Nestack Agents · Safety coaching and driver workforce

AGT-TR-17 · Agent Care available after launch

Build a coaching agent

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

About you
Your fleet

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