An example of truck roll avoidance as a governed process: agents do the 9 steps, and a person signs 3 gates before anything irreversible happens. Download it, import it into your workspace, and adapt it to your systems.
The graph9 agent steps3 human gatessigns: Field-ops dispatch manager
Truck-roll avoidance autopilot
Carriers run 3-8M field dispatches a year and 20-40% are no-fault-found truck rolls that a remote reboot, line resync or config push would have cleared, at roughly $250-500 each. Diagnosis today is manual call-center guesswork against fragmented OSS and EMS systems, so a tech is rolled the moment a customer complains rather than only when physical work is genuinely required. Routine impairments are diagnosed and remotely remediated by agents in minutes, and clearly self-healing or non-physical faults never generate a dispatch. Only tickets with a real physical root cause reach a human dispatcher, who authorizes every irreversible truck-roll commit.
The governed flow · branches, parallel work & a human on the irreversible step
proceed to diagnosissuppress (known outage, duplicate, or non-technical issue)routine diagnosis (node fault, common premises issue)complex or unknown fault (rare device, cross-carrier, ambiguous classification)node / outage fault (no physical work)premises fault (remotely fixable or physical)resolved — line restoredstill impaired — re-diagnose (rework)unresolved — physical root causeapprove truck rollreject truck roll — issue deemed non-physical or deferred to next window
Start
agent · low risk
Pull the trouble ticket and customer/service record, and enrich with account and prior-truck-roll history
gate · human sign-off
Is this ticket worthy of remote diagnosis, or should it be auto-suppressed (duplicate, known outage, customer behavior issue)? Gate prevents diagnostic effort waste on non-technical tickets.signs: Field-ops triage specialist
parallel · fan-out / join
Gather device and network telemetry concurrently
agent · low risk
Read live device and line telemetry: modem/ONT status, DSL/PON sync, SNR/RxPower, error counters
agent · low risk
Read surrounding node/network health and active outage/alarm state for the serving DSLAM/OLT
agent · medium risk
Correlate both telemetry streams to a root cause, separate node/outage faults from premises faults, and classify remotely-fixable vs needs-physical-work
decision
Does the diagnosis require expert review (rare fault, cross-carrier, unknown device, or unusual classification)?
gate · human sign-off
Senior network engineer reviews diagnosis, approves fault classification and remediation strategy before proceedingsigns: Senior Network Engineer
decision
Fault type?
agent · low risk
Self-healing or known node/outage fault: suppress dispatch, attach the outage ticket, and queue for outage-restore monitoring (no premises work)
agent · medium risk
Run guided remote remediation (modem reboot, line/profile resync, config or firmware push) and re-verify the line; auto-roll back on regression
decision
Line healthy after remediation?
agent · low risk
Draft the dispatch recommendation with root cause, evidence, skill/parts needed, and a truck-roll-vs-defer rationale
gate · human sign-off
Review the evidence and authorize (or reject) the truck rollsigns: Field-ops dispatch manager
agent · high riskirreversible
Commit the authorized field work order, reserve the technician slot and parts, and notify the customer of the appointment
agent · low risk
Track dispatch/restore outcome and SLA, capture no-fault-found feedback, and update the diagnostic model and ticket
Done
low riskmedium riskhigh riskbranch / reworkgate · human sign-off
Use this example
01
Download the file
A minctrl.process/v1 document: the graph and the hash of the process it becomes.
02
Import it in Processes
Import into Minctrl opens this example in your workspace; one click stores it as your first version. Import JSON does the same with the file, and a file changed after download is refused.
03
Connect your systems
Every connector starts in shadow: steps run, nothing leaves Minctrl until you configure a connector and switch it live.
04
Adapt it
Change signers, time limits and steps on the canvas. Each save is a new version; a running case stays on the version it started with.
Questions
How do I automate truck roll avoidance with Minctrl?+
Start from this example. Import the file in Processes, connect your own systems, and adapt the steps on the canvas. Agents run the reversible steps; every irreversible step waits at a gate for the role you choose. The example has 9 steps and 3 gates; you can change any of them.
Is truck roll avoidance in Minctrl auditable?+
Every run start, signature and change to the process is written to a hash-chained audit log your auditor can verify and export. A run is pinned to the exact graph it started on.
Does the AI decide everything?+
No. Minctrl will not make a process runnable while an irreversible step can be reached without a human gate, and one person cannot sign two gates of the same run.