Build the day's schedule from the skills, hazards and agreement rules already on record, surface what the record does not clear, and hold the job for the supervisor who releases it.
Where the work order and site record live, ingest them from supported workforce systems.
02
When a site carries more than one record, normalise the fields and carry each hazard forward with its source.
Reason
03
When the constraints are in, build a proposed schedule and route from the skills, hazards and windows on the job.
04
Where a collective agreement sets call-out rotation or overtime order, apply it as a hard constraint.
05
When a job needs a credential, read the register and block the assignment if it is missing or expired.
Decide
06
Where the record does not clear a hazard — structure, RF, atmosphere or approach distance — say so and stop.
07
Route every job to the named supervisor who releases it.
Out
08
Retain the constraints applied, the proposal, the supervisor's changes and the release against the work order.
09
Execute write actions only inside the approval boundaries agreed during implementation.
→Product statement
The agent proposes a schedule; the named supervisor releases each job, and the employer stays responsible for the safety of the work.
Example workflow
One job, record to release
AgentHuman
1Work order receivedTrouble ticket, planned-work order, site visit or storm call-out
2Constraints assembledSite hazards, credentials, agreement rules and travel windows, each with its named source
3Schedule proposedTechnician, window, route and confidence
4Controls appliedCredential-register checks, hazard-record checks, agreement-rule checks and confidence threshold
No human action required
Stages 1 to 4 run unaided, and nobody is sent anywhere at any of them — the agent is proposing, and the supervisor's lane opens at the confidence gate.
5DecisionBranches at the confidence threshold
High confidence
Goes to the named supervisor to release.
Low confidence
Adds a safety-lead read first.
Supervisor release
The job is held with its constraints, its unresolved hazards and the confidence.
Release · Amend · Send to safety review
Released — job pack issued▼
6Workforce systems updatedOnly where write access and approval policy allow it
7Outcome evaluatedOverride rates, hazard-flag outcomes, on-site stops and post-job corrections
Overrides
Every supervisor change is counted in the evaluation.
What should not run autonomously
Human approval stays in control
Outside the boundary — human approval required8 items
Authorising a climb, or work on an energised line.
Deciding that a person is qualified or competent.
Clearing an RF zone, or which exposure limit applies.
Dispatching into a hazard the record does not clear.
Automation boundaryAgent acts unaided
✓Build a proposed schedule against the configured rule set.
✓Assemble the job pack from the skills and hazards on record.
✓Apply the employer's own tie-off, access and agreement rules.
✓Surface what the record does not say, and hold the job for release.
Any write happens inside the boundaries agreed at implementation, never ahead of release.
Overriding a rule in the collective agreement.
Testing a pole or structure, or declaring it safe.
Applying lockout/tagout on behalf of a person.
Changes to hazard, credential or agreement rules.
Example output
One job, annotated
Everything the agent proposes is attached to the record it was drawn from.
Dispatch output · single jobIllustrative example
Job
Proposed work
Window
Source of record
Confidence
Held for
Rooftop antenna swap
Two-technician visit to a shared rooftop with three licensees
07:30 – 11:00
Site hazard register
91%
Named supervisor, not released
As receivedTaken from the work order and the site hazard register — nothing on this side is written by the agent.
Contractor and subcontractor crews sit furthest down the chain and are the least visible in any aggregate. Nestack reports the supervisor-override rate by slice, not only in total.
Slice performance — reported separately, not only in aggregateIllustrative example
Slice
Failure rate
Lift
Lift vs. threshold
Status
Tower and elevated work
8.6%
3.3×
Review
Multi-tenant rooftop sites
6.8%
2.6×
Review
Storm-restoration call-outs
4.9%
1.9×
Watch
Routine premises visits
1.8%
0.7×
Normal
Bar: supervisor-override-rate lift vs. routine-premises baseline · scale 0–4.0× · tick marks the 2.0× review threshold2 of 4 slices over threshold
Evidence-linked improvement
The loop closes on a test, not a debrief
The loop closes on a case the next release must pass, not on an explanation. That suite is what the next job put to a technician is measured against.
Improvement cycle · five stagesSwitchback — the path turns at Improve and returns at Learn
01Detect
Supervisor-override rate rises in a job slice.
02Diagnose
Read the jobs and the records behind them until the cause narrows to one constraint.
03Improve
The fix is versioned with the jobs that motivated it.
04Verify
Nothing ships while an affected case is failing.
05Learn
The case is added for good, and the dispatch rules change.
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, dispatch workflow, evaluation, integration, then production validation and handover.
WorkstreamWeek 1Week 2Week 3Week 4Week 5Week 6
01Dispatch workflow discovery and automation-boundary definition.
02Workforce and asset source assessment.
03Skill, hazard and collective-agreement rule mapping.
04Work-order ingestion and normalisation.
05Scheduling logic and constraint binding.
06Confidence scoring and hazard routing.
07Supervisor release workflow.
08Workforce-system and dispatch integration.
09Hazard and competence cases.
10Guardrails and dispatch controls.
11Job-trail instrumentation.
12Deployment, documentation 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 region, one crew typeProductionProduction workforce systemsAdvancedMultiple regions / contractors
Introduced at Pilot
Scheduling to your record and rules✓✓✓
Supervisor release✓✓✓
Dispatch-quality baseline✓✓✓
Introduced at Production
Reporting by job type—✓✓
Release workflow in your systems—✓✓
Approved write-back—✓✓
Workforce-system integration—✓✓
Introduced at Advanced
Multi-agreement and multi-state rules——✓
Multi-stage safety approvals——✓
High job volume——✓
Multi-region dispatch controls——✓
Build priceFrom $5,000From $8,000Custom 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 job types and work-order structure→Work-order ingestion and constraint mappingWeek 1
02Representative completed jobs→Scheduling baseline, constraint extraction and hazard bindingWeek 2
03Your skills matrix, hazard register and agreement terms→Skill, hazard and collective-agreement rule mappingWeek 1
04Access to relevant APIs, feeds or exports→Workforce and asset assessment, then integration setupWeek 2
05Jobs you would not want dispatched→Hazard cases and the evaluation suiteWeek 4
06What must reach a supervisor before anyone climbs→Confidence scoring, hazard routing, guardrails and release controlsWeek 3
07Named supervisors to release jobs→Supervisor release workflow, then pilot and production validationWeeks 5–6
Nothing else is requiredDeployment, documentation and Agent Care handover are ours.
Delivery timeline
Four phases across six weeks
Each phase occupies the weeks it needs, so the fifth week carries two kinds of work.
PhaseW1W2W3W4W5W6
DiscoveryW1
BuildW2 – W3
EvaluateW4 – W5
Pilot & LaunchW5 – W6
Week focusW1Dispatch workflow discovery, rule mapping and the automation boundaryW2Workforce and asset integration and the scheduling baselineW3Scheduling workflow, confidence logic and release controlsW4Evaluation suite, hazard-record checks and failure-mode testingW5Dispatch integration, pilot crews and targeted correctionsW6One dispatch cycle run under field operations, then handover
Reading the bandA bar covers the weeks its work is named in, and nothing else. The week 5 overlap is real, not padding.
At the end of W6The cycle closes validation and Agent Care assumes monitoring.
DurationSix-week plan shown · typical delivery 4–6 weeks depending on scope confirmed in discovery.
Next step · Telecom AI agent
Build a dispatch agent that stops where the climbing starts.
Show us your job types, your hazard register and the agreement you work under. If you can name who releases a job today, we'll map the scheduling workflow to stop at that person and set the boundary there.
