{
"Comment": "Outage management pipeline — validate, diagnose, assess impact, reroute, dispatch field tech, restore, and report",
"StartAt": "ValidateOutageReport",
"States": {
"ValidateOutageReport": {
"Type": "Task",
"Resource": "arn:aws:states:::lambda:invoke",
"Parameters": {
"FunctionName": "${ValidateOutageReportFunctionArn}",
"Payload.$": "$"
},
"ResultPath": "$.validation",
"Retry": [
{
"ErrorEquals": [
"Lambda.ServiceException",
"Lambda.AWSLambdaException",
"Lambda.SdkClientException",
"Lambda.TooManyRequestsException"
],
"IntervalSeconds": 2,
"MaxAttempts": 3,
"BackoffRate": 2
}
],
"Catch": [
{
"ErrorEquals": [
"States.ALL"
],
"Next": "OutageFailed",
"ResultPath": "$.error"
}
],
"Next": "IsReportValid"
},
"IsReportValid": {
"Type": "Choice",
"Choices": [
{
"Variable": "$.validation.Payload.isValid",
"BooleanEquals": true,
"Next": "InvestigateOutage"
}
],
"Default": "OutageFailed"
},
"InvestigateOutage": {
"Type": "Parallel",
"Branches": [
{
"StartAt": "DiagnoseRootCause",
"States": {
"DiagnoseRootCause": {
"Type": "Task",
"Resource": "arn:aws:states:::lambda:invoke",
"Parameters": {
"FunctionName": "${DiagnoseRootCauseFunctionArn}",
"Payload.$": "$.validation.Payload"
},
"Retry": [
{
"ErrorEquals": [
"Lambda.ServiceException",
"Lambda.AWSLambdaException",
"Lambda.SdkClientException",
"Lambda.TooManyRequestsException"
],
"IntervalSeconds": 2,
"MaxAttempts": 3,
"BackoffRate": 2
}
],
"End": true
}
}
},
{
"StartAt": "AssessImpactRadius",
"States": {
"AssessImpactRadius": {
"Type": "Task",
"Resource": "arn:aws:states:::lambda:invoke",
"Parameters": {
"FunctionName": "${AssessImpactRadiusFunctionArn}",
"Payload.$": "$.validation.Payload"
},
"Retry": [
{
"ErrorEquals": [
"Lambda.ServiceException",
"Lambda.AWSLambdaException",
"Lambda.SdkClientException",
"Lambda.TooManyRequestsException"
],
"IntervalSeconds": 2,
"MaxAttempts": 3,
"BackoffRate": 2
}
],
"End": true
}
}
}
],
"ResultPath": "$.investigation",
"Catch": [
{
"ErrorEquals": [
"States.ALL"
],
"Next": "OutageFailed",
"ResultPath": "$.error"
}
],
"Next": "ApplyNetworkReroute"
},
"ApplyNetworkReroute": {
"Type": "Task",
"Resource": "arn:aws:states:::lambda:invoke",
"Parameters": {
"FunctionName": "${ApplyNetworkRerouteFunctionArn}",
"Payload.$": "$.investigation[1].Payload"
},
"ResultPath": "$.reroute",
"Retry": [
{
"ErrorEquals": [
"Lambda.ServiceException",
"Lambda.AWSLambdaException",
"Lambda.SdkClientException",
"Lambda.TooManyRequestsException"
],
"IntervalSeconds": 2,
"MaxAttempts": 3,
"BackoffRate": 2
}
],
"Catch": [
{
"ErrorEquals": [
"States.ALL"
],
"Next": "OutageFailed",
"ResultPath": "$.error"
}
],
"Next": "DispatchFieldTech"
},
"DispatchFieldTech": {
"Type": "Task",
"Resource": "arn:aws:states:::lambda:invoke",
"Parameters": {
"FunctionName": "${DispatchFieldTechFunctionArn}",
"Payload.$": "$.reroute.Payload"
},
"ResultPath": "$.dispatch",
"Retry": [
{
"ErrorEquals": [
"Lambda.ServiceException",
"Lambda.AWSLambdaException",
"Lambda.SdkClientException",
"Lambda.TooManyRequestsException"
],
"IntervalSeconds": 2,
"MaxAttempts": 3,
"BackoffRate": 2
}
],
"Catch": [
{
"ErrorEquals": [
"States.ALL"
],
"Next": "OutageFailed",
"ResultPath": "$.error"
}
],
"Next": "RestoreService"
},
"RestoreService": {
"Type": "Task",
"Resource": "arn:aws:states:::lambda:invoke",
"Parameters": {
"FunctionName": "${RestoreServiceFunctionArn}",
"Payload.$": "$.dispatch.Payload"
},
"ResultPath": "$.restore",
"Retry": [
{
"ErrorEquals": [
"Lambda.ServiceException",
"Lambda.AWSLambdaException",
"Lambda.SdkClientException",
"Lambda.TooManyRequestsException"
],
"IntervalSeconds": 2,
"MaxAttempts": 3,
"BackoffRate": 2
}
],
"Catch": [
{
"ErrorEquals": [
"States.ALL"
],
"Next": "OutageFailed",
"ResultPath": "$.error"
}
],
"Next": "GenerateIncidentReport"
},
"GenerateIncidentReport": {
"Type": "Task",
"Resource": "arn:aws:states:::lambda:invoke",
"Parameters": {
"FunctionName": "${GenerateIncidentReportFunctionArn}",
"Payload.$": "$.restore.Payload"
},
"ResultPath": "$.report",
"Retry": [
{
"ErrorEquals": [
"Lambda.ServiceException",
"Lambda.AWSLambdaException",
"Lambda.SdkClientException",
"Lambda.TooManyRequestsException"
],
"IntervalSeconds": 2,
"MaxAttempts": 3,
"BackoffRate": 2
}
],
"Catch": [
{
"ErrorEquals": [
"States.ALL"
],
"Next": "OutageFailed",
"ResultPath": "$.error"
}
],
"Next": "OutageResolved"
},
"OutageResolved": {
"Type": "Succeed"
},
"OutageFailed": {
"Type": "Fail",
"Error": "OutageManagementFailed",
"Cause": "Outage report could not be validated, diagnosed, or resolved through the management pipeline"
}
}
}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.