{
"Comment": "Outage escalation — re-diagnose a prolonged outage and escalate to field dispatch and restoration",
"StartAt": "SetEscalationContext",
"States": {
"SetEscalationContext": {
"Type": "Pass",
"Parameters": {
"outageId.$": "$.outageId",
"affectedNodeId.$": "$.affectedNodeId",
"outageType.$": "$.outageType",
"severity.$": "$.severity",
"detectedBy.$": "$.detectedBy",
"region.$": "$.region",
"carrier.$": "$.carrier",
"estimatedAffectedSubscribers.$": "$.estimatedAffectedSubscribers",
"detectedAt.$": "$.detectedAt",
"escalationReason.$": "$.escalationReason",
"meta": {
"workflow": "OutageEscalation",
"trigger": "PROLONGED_OUTAGE_ESCALATION"
}
},
"Next": "RevalidateOutage"
},
"RevalidateOutage": {
"Type": "Task",
"Resource": "arn:aws:states:::lambda:invoke",
"Parameters": {
"FunctionName": "${ValidateOutageReportFunctionArn}",
"Payload.$": "$"
},
"ResultPath": "$.revalidation",
"Retry": [
{
"ErrorEquals": [
"Lambda.ServiceException",
"Lambda.AWSLambdaException",
"Lambda.SdkClientException",
"Lambda.TooManyRequestsException"
],
"IntervalSeconds": 2,
"MaxAttempts": 3,
"BackoffRate": 2
}
],
"Next": "IsOutageStillActive"
},
"IsOutageStillActive": {
"Type": "Choice",
"Choices": [
{
"Variable": "$.revalidation.Payload.isValid",
"BooleanEquals": true,
"Next": "EscalationHold"
}
],
"Default": "EscalationFailed"
},
"EscalationHold": {
"Type": "Wait",
"Seconds": 5,
"Next": "ReInvestigateInParallel"
},
"ReInvestigateInParallel": {
"Type": "Parallel",
"Branches": [
{
"StartAt": "ReDiagnoseRootCause",
"States": {
"ReDiagnoseRootCause": {
"Type": "Task",
"Resource": "arn:aws:states:::lambda:invoke",
"Parameters": {
"FunctionName": "${DiagnoseRootCauseFunctionArn}",
"Payload.$": "$.revalidation.Payload"
},
"End": true
}
}
},
{
"StartAt": "ReAssessImpact",
"States": {
"ReAssessImpact": {
"Type": "Task",
"Resource": "arn:aws:states:::lambda:invoke",
"Parameters": {
"FunctionName": "${AssessImpactRadiusFunctionArn}",
"Payload.$": "$.revalidation.Payload"
},
"End": true
}
}
}
],
"ResultPath": "$.escalatedInvestigation",
"Next": "EscalatedFieldDispatch"
},
"EscalatedFieldDispatch": {
"Type": "Task",
"Resource": "arn:aws:states:::lambda:invoke",
"Parameters": {
"FunctionName": "${DispatchFieldTechFunctionArn}",
"Payload.$": "$.escalatedInvestigation[1].Payload"
},
"ResultPath": "$.dispatch",
"Next": "EscalatedRestoreService"
},
"EscalatedRestoreService": {
"Type": "Task",
"Resource": "arn:aws:states:::lambda:invoke",
"Parameters": {
"FunctionName": "${RestoreServiceFunctionArn}",
"Payload.$": "$.dispatch.Payload"
},
"ResultPath": "$.restore",
"Next": "IsServiceRestored"
},
"IsServiceRestored": {
"Type": "Choice",
"Choices": [
{
"Variable": "$.restore.Payload.serviceStatus",
"StringEquals": "FULLY_RESTORED",
"Next": "EscalationResolved"
},
{
"Variable": "$.restore.Payload.serviceStatus",
"StringEquals": "PARTIALLY_RESTORED",
"Next": "EscalationResolved"
}
],
"Default": "EscalationFailed"
},
"EscalationResolved": {
"Type": "Succeed"
},
"EscalationFailed": {
"Type": "Fail",
"Error": "OutageEscalationFailed",
"Cause": "Escalated outage could not be resolved — manual NOC intervention required"
}
}
}Expand
100%
Telecommunications teams can use patterns like this to build reliable, compliant, and scalable automation for payment systems and can test and refine these flows locally with Thrubit to reduce cloud cost and speed up iteration.