Watch a fleet of automated machines through a field operation — progress, telemetry, boundaries and stops — and page the named supervisor, who keeps control of every machine and answers for the operation.
4Run checked against the planProgress, coverage and overlap, boundary adherence, and interventions read in aggregate
No human action required
Stages 1 to 4 run continuously, not when somebody opens a screen. The agent watching is not the supervisor watching, and a quiet lane is not permission to look away. A stop or a boundary event ends the stretch the moment it is seen.
5DecisionSplits on what pages a person now and what waits for the shift report
No stop, boundary event or silence
Raised in the shift report, not paged.
Stop, boundary event or silence
Pages the named supervisor immediately.
Named supervisor
Reads the event, the machine state and the telemetry around it, then decides what happens to the machine and the field.
Attend · Call the operator · Stand the fleet down
Attended — handed back▼
6Alert raised and recordedSent by the agreed path and repeated until a person acknowledges; no command reaches a machine
7Outcome evaluatedTime to acknowledgement, missed and late escalations, false alerts and load by field condition
Interventions
Every stop and every intervention is counted, and read in aggregate for a developing fault.
What should not run autonomously
Human approval stays in control
Outside the boundary — human approval required8 items
Clearing a stop or restarting a machine.
Sending any command to a machine or implement.
Moving, widening or switching off a boundary.
Deciding a detection event was a false alarm.
Automation boundaryAgent acts unaided
✓Watch progress, coverage, telemetry and implement state against the plan.
✓Raise stops, obstacle-detection events, boundary events and telemetry gaps.
✓Escalate by the agreed path and keep escalating until a person acknowledges.
✓Record what happened, who was paged, who answered and how long it took.
Write actions run only inside the boundaries agreed in implementation. No control path to a machine exists.
Judging a field fit for autonomous work.
Authorising road travel between fields.
Setting how many machines one person supervises.
Changing alert rules, thresholds or escalation paths.
Example output
One stop event, annotated
Everything the agent sends is attached to the machine, the moment and the telemetry it came from.
Alert output · single machine eventIllustrative example
Machine
Event
Conditions
Sent to
Confidence
Machine state
Autonomous tractor, unit 4
Stopped itself, headland pass
21:06, low light
Named supervisor, paged
93%
Stopped by its own system
As receivedThe event as the machine reported it, with the telemetry either side of it.
Evidence usedMachine stop codePosition and boundaryLast telemetry, 40s
Why a person was pagedIt stopped itself and stayed stopped, and nothing in the telemetry says why it did.
ActionAttendCall the operatorStand the fleet down
What the score decidesConfidence decides how the alert is worded, not whether it is sent at all.
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 machine in the runFrom telemetry, the work order and the field file
03Plan & boundary
Apply the plan that governs the run
Use the work order, the current field file, the boundary and exclusion zones, and what each machine reports — none of which shows what a sensor missed.
01Approved path
Get the event to a person in time
A stop, a boundary event or a machine gone quiet reaches whoever is on the rota, by name, instead of waiting for the next look at a screen.
02Human review
Show the pattern, not just the event
Interventions that look ordinary one at a time — three stops in the same corner, a creeping fuel burn — are read together and put in front of a person.
04Build an evidence trail
Retain the event, the machine state, the telemetry around it, the field file in force, who was paged, who answered and when — on both paths.
Integrations
Typical integrations
Five system groups connect to the same agent. Which of them are in scope is decided in discovery.
Integration availability depends on the client's existing systems and API access.
Agent controls
Six layers between the model and the fleet
Each control wraps the one inside it. An event clears every layer before a person is paged, and none of the six is a substitute for the machine's own safety systems.
L6 · Outermost — last line of defenceInward → L1 · closest to the model
L6Rollback / safe modeReturn watching to your existing alarms and rota if feeds or evaluations degrade.Roll back
L5TraceabilityRecord the event, the telemetry, the field file, who was paged and who answered.Record
L4Supervisor gateClearing a stop, restarting and any boundary change stay with the responsible person.Gate
L3EscalationAn alert repeats and widens down the rota until a named person acknowledges it.Escalate
L2No control pathThe agent holds no channel that can start, steer, stop or restart a machine.Block
L1Event detectionEvery stop, boundary event and telemetry gap is raised, not scored away.Raise
Model coreEvent raised — what the machine did, the telemetry either side of it, the plan in force and confidence
L1 – L2Raise every event, and hold no path to a machine
L3Decides that an alert reaches a person
L4 – L5Keep the machine with a person and the record intact
L6Pulls automation back when signals degrade
How Nestack evaluates it
Evaluate the whole watch — not only the alert that got sent.
Coverage runs the whole depth of the workflow, and every layer is cut by slice.
Surface — the alert the supervisor reads
Depth of coverage ▼
E1Final-output evaluationWas the event real, and did it describe what the machine did?
E2Step-level evaluationDid it read the current field file, boundary and machine state?
E3Tool evaluationDid it poll the right machine, feed and telemetry window?
E4Escalation timingHow long from the machine event to a named person acknowledging it?
E5Slice evaluationHow do detection and escalation change by field condition?
E6Business outcomeHow many events were missed, late, or raised for nothing?
Floor — whether a person actually attended
Failure modes
Where each failure originates in the agent
Seven failure modes plotted against the five stages of the agent lifecycle.
Agent lifecycleDirection of processing →
01 · Telemetry / intake2 modes
EQ-02
Telemetry gap reads as normal
A silent feed looks like a machine still working.
EQ-03
Stale boundary file
An exclusion zone changed after the file was pulled.
Stage gathersMachine state, position, implement and the field file
02 · Watching1 mode
EQ-04
Pattern only visible in aggregate
Repeat stops in one corner never add up to a fault.
Stage comparesThe run against the plan, the boundary and the coverage
03 · Alerting2 modes
EQ-01
Stop surfaced late
A machine sits stopped with nobody paged.
EQ-05
Alert flood dulls the watch
So much is raised that alerts stop being read.
Stage raisesThe event, who it names and how far it escalates
04 · Output1 mode
EQ-06
Detection limits not stated
A quiet screen is read as a clear field.
Stage returnsWhat the supervisor sees when the alert arrives
05 · Change / Version1 mode
EQ-07
Silent feed regression
A feed or field-file change moves what is watched.
Stage tracksModel, prompt, field-file and telemetry-feed changes
Sev-1 · a hazard or a stop goes unattendedSev-2 · the supervisor is misled about the fieldSev-3 · watching degrades, more falls to people
Watching does not hold up evenly across field conditions
A late-escalation rate that reads acceptably across a season sits mostly in the conditions where sensing and connectivity are worst — dust, darkness and broken field edges. Nestack reports performance by slice, not only in total.
Slice performance — reported separately, not only in aggregateIllustrative example
Slice
Failure rate
Lift
Lift vs. threshold
Status
Dust and harvest conditions
8.4%
3.8×
Review
Low light and night work
6.0%
2.7×
Review
Irregular and small boundaries
4.2%
1.9×
Watch
Daylight single-machine work
1.7%
0.8×
Normal
Bar: late-escalation rate lift vs. daylight baseline · scale 0–4.0× · tick marks the 2.0× review threshold2 of 4 slices over threshold
Evidence-linked improvement
The field is put right first, then the watch is changed
A machine standing in a field is not a ticket. It is attended and the field made safe first — the loop only decides what the next shift is watched with.
Improvement cycle · five stagesSwitchback — the path turns at Improve and returns at Learn
01Detect
Late escalations, missed events and false alerts cluster by field condition first.
02Diagnose
The feed, the field file, the watch rule and the escalation path are each ruled in or out.
03Improve
Your safety lead approves the changed rule, source or routing, and the shift it starts on is recorded.
04Verify
Recorded runs from the same conditions are replayed, including the events nobody answered.
05Learn
The event is added to the replay set, and the next shift briefing names what changed.
Learn → DetectThe return edge. Changing what is watched or who is paged is a safety change — your safety lead signs it before a shift runs on it.
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, watching logic, evaluation, integration, then production validation and handover.
WorkstreamWeek 1Week 2Week 3Week 4Week 5Week 6
01Workflow discovery and automation-boundary definition.
02Machine, implement and telemetry feed assessment.
03Supervision model, rota and escalation paths.
04Field files, boundaries and exclusion zones.
05Event and telemetry ingestion.
06Progress, coverage and boundary watching.
07Stop, intervention and telemetry-gap detection.
08Alerting, acknowledgement and escalation workflow.
09Escalation-timing and missed-event evaluation.
10False-alert and supervisor-load testing.
11Fleet-system, alerting and record integration.
12Observability, deployment and Agent Care handover.
12 workstreams · 6 weeks · bar shows the weeks a workstream is active — several run in parallelFinal 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 machine, one fieldProductionProduction fleet integrationAdvancedMulti-fleet / contractor operations
Introduced at Pilot
Stop and telemetry-gap detection✓✓✓
Alerting to a named supervisor✓✓✓
Machine control left with the supervisor✓✓✓
Acknowledgement and escalation record✓✓✓
Baseline evaluation✓✓✓
Introduced at Production
Progress, coverage and overlap watching—✓✓
Boundary and exclusion-zone adherence—✓✓
Intervention-pattern reporting—✓✓
Observability and evaluation—✓✓
Introduced at Advanced
Multi-fleet and contractor operations——✓
Shift handover and enterprise controls——✓
Build priceFrom $5,000From $8,000Custom quote
Final build priceConfirmed after discovery based on machine types and telemetry access, fleet-system integrations, field and boundary sources, alerting paths, the supervision model, 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 machines, implements and what each one reports→Machine, implement and telemetry feed assessmentWeek 1
02Who supervises, on what rota, and how they are reached→Supervision model, rota and escalation pathsWeek 1
03Field boundaries and exclusion zones you actually trust→Field files, boundaries and exclusion-zone checksWeek 2
04What each machine's own safety system does when it stops→Event detection mapped to what the machine already doesWeek 3
05Runs that went wrong, including the near misses→Evaluation suite, regression cases and failure-mode testingWeek 4
06What your alerting can carry, and what already gets ignored→False-alert and supervisor-load testingWeek 5
07A named supervisor and a safety lead to review→Acknowledgement workflow, then supervised shifts and validationWeeks 5–6
Nothing else is requiredDeployment, documentation and Agent Care handover are ours.
Delivery timeline
Four phases across six weeks
Phases are drawn over the weeks they actually occupy. Week 5 carries both the load testing and the first supervised shifts.
PhaseW1W2W3W4W5W6
DiscoveryW1
BuildW2 – W3
EvaluateW4 – W5
Pilot & LaunchW5 – W6
Week focusW1Workflow discovery, the supervision model and the automation boundaryW2Telemetry ingestion, field files and boundary geometryW3Progress, coverage, stop and telemetry-gap watchingW4Escalation-timing, missed-event and false-alert testingW5Fleet integration, supervisor-load testing and supervised shiftsW6Supervisors work from live alerts, then Agent Care starts
Reading the bandEscalation is tested in week 4, before a supervisor works from an alert in week 5. Nothing is relied on in a working field until it has.
At the end of W6Alerts have run alongside your existing radio and phone practice and been answered by the people named on the rota, then Agent Care takes over monitoring.
DurationSix-week plan shown · typical delivery 4–6 weeks depending on scope confirmed in discovery.
Next step · Agriculture AI agent
Build a supervision agent around your fleet and your rota.
Show us a week of machine data, your field files and how a stop reaches a person today. We'll run a shadow week alongside your rota, paging nobody, and compare what we would have raised against what was actually seen.
