The PersonaEvalSuites REST API manages comprehensive evaluation collections that group multiple related evaluations. Create, manage, and execute evaluation suites for holistic persona assessment across different dimensions and scenarios.
Base URL: https://your-api-name.mercury.ratiomachina.com Authentication: x-mercury-api-key: YOUR_API_KEY
limit - Number of results (default: 50, max: 100)offset - Skip results for paginationstatus - Filter by suite status (active, archived)personaExternalId - Filter by persona external IDtags - Filter by tags (comma-separated){
"personaEvalSuites": [
{
"id": "123e4567-e89b-12d3-a456-426614174000",
"name": "Customer Service Excellence Suite",
"description": "Comprehensive evaluation for customer service personas",
"personaExternalId": "cs-agent-v1",
"status": "active",
"totalEvaluations": 12,
"tags": ["customer-service", "quality-assurance"],
"configuration": {
"executionTimeout": 300,
"parallelExecution": true,
"failureThreshold": 20
},
"schedule": {
"enabled": true,
"frequency": "weekly",
"nextRun": "2024-01-22T09:00:00Z"
},
"lastRun": {
"executedAt": "2024-01-15T09:00:00Z",
"status": "completed",
"passRate": 91.7,
"duration": 180
},
"createdAt": "2024-01-01T12:00:00Z",
"updatedAt": "2024-01-15T14:30:00Z"
}
],
"pagination": {
"total": 1,
"limit": 50,
"offset": 0,
"hasMore": false
}
}{
"name": "Customer Service Excellence Suite",
"description": "Comprehensive evaluation for customer service personas",
"personaExternalId": "cs-agent-v1",
"externalId": "cs-eval-suite-v2",
"evaluationIds": [
"eval-tone-check-123",
"eval-accuracy-456",
"eval-response-time-789"
],
"configuration": {
"executionTimeout": 300,
"parallelExecution": true,
"failureThreshold": 20,
"retryFailedEvals": true,
"generateReport": true
},
"schedule": {
"enabled": true,
"frequency": "weekly",
"dayOfWeek": "monday",
"hour": 9,
"timezone": "UTC"
},
"notifications": {
"onCompletion": true,
"onFailure": true,
"webhookUrl": "https://your-system.com/webhooks/eval-results",
"emailRecipients": ["qa-team@company.com"]
},
"tags": ["customer-service", "quality-assurance", "automated"]
}{
"personaEvalSuite": {
"id": "123e4567-e89b-12d3-a456-426614174000",
"name": "Customer Service Excellence Suite",
"description": "Comprehensive evaluation for customer service personas",
"personaExternalId": "cs-agent-v1",
"externalId": "cs-eval-suite-v2",
"status": "active",
"totalEvaluations": 3,
"evaluationIds": [
"eval-tone-check-123",
"eval-accuracy-456",
"eval-response-time-789"
],
"configuration": {
"executionTimeout": 300,
"parallelExecution": true,
"failureThreshold": 20,
"retryFailedEvals": true,
"generateReport": true
},
"schedule": {
"enabled": true,
"frequency": "weekly",
"nextRun": "2024-01-22T09:00:00Z"
},
"tags": ["customer-service", "quality-assurance", "automated"],
"createdAt": "2024-01-15T16:30:00Z",
"updatedAt": "2024-01-15T16:30:00Z"
}
}id - PersonaEvalSuite UUIDincludeEvaluations - Include full evaluation details (default: false)includeHistory - Include execution history (default: false)includeMetrics - Include performance metrics (default: false){
"personaEvalSuite": {
"id": "123e4567-e89b-12d3-a456-426614174000",
"name": "Customer Service Excellence Suite",
"description": "Comprehensive evaluation for customer service personas",
"personaExternalId": "cs-agent-v1",
"externalId": "cs-eval-suite-v2",
"status": "active",
"totalEvaluations": 3,
"evaluationIds": [
"eval-tone-check-123",
"eval-accuracy-456",
"eval-response-time-789"
],
"configuration": {
"executionTimeout": 300,
"parallelExecution": true,
"failureThreshold": 20,
"retryFailedEvals": true,
"generateReport": true
},
"schedule": {
"enabled": true,
"frequency": "weekly",
"nextRun": "2024-01-22T09:00:00Z"
},
"lastRun": {
"executedAt": "2024-01-15T09:00:00Z",
"status": "completed",
"passRate": 91.7,
"duration": 180,
"executionArn": "arn:aws:states:us-west-2:123456789012:execution:persona-eval-runner:run-123"
},
"metrics": {
"totalRuns": 24,
"successRate": 95.8,
"averageExecutionTime": 165,
"averagePassRate": 89.2
},
"tags": ["customer-service", "quality-assurance", "automated"],
"createdAt": "2024-01-01T12:00:00Z",
"updatedAt": "2024-01-15T14:30:00Z"
}
}{
"name": "Enhanced Customer Service Suite",
"description": "Updated comprehensive evaluation suite with new metrics",
"evaluationIds": [
"eval-tone-check-123",
"eval-accuracy-456",
"eval-response-time-789",
"eval-sentiment-analysis-101"
],
"configuration": {
"executionTimeout": 420,
"parallelExecution": true,
"failureThreshold": 15,
"retryFailedEvals": true,
"generateReport": true
},
"schedule": {
"enabled": true,
"frequency": "daily",
"hour": 6,
"timezone": "UTC"
},
"tags": ["customer-service", "quality-assurance", "automated", "enhanced"]
}{
"personaEvalSuite": {
"id": "123e4567-e89b-12d3-a456-426614174000",
"name": "Enhanced Customer Service Suite",
"description": "Updated comprehensive evaluation suite with new metrics",
"personaExternalId": "cs-agent-v1",
"externalId": "cs-eval-suite-v2",
"status": "active",
"totalEvaluations": 4,
"evaluationIds": [
"eval-tone-check-123",
"eval-accuracy-456",
"eval-response-time-789",
"eval-sentiment-analysis-101"
],
"configuration": {
"executionTimeout": 420,
"parallelExecution": true,
"failureThreshold": 15,
"retryFailedEvals": true,
"generateReport": true
},
"schedule": {
"enabled": true,
"frequency": "daily",
"nextRun": "2024-01-16T06:00:00Z"
},
"tags": ["customer-service", "quality-assurance", "automated", "enhanced"],
"createdAt": "2024-01-01T12:00:00Z",
"updatedAt": "2024-01-15T16:45:00Z"
}
}Permanently delete a persona evaluation suite. This will also cancel any scheduled runs and remove all associated execution history.
id - PersonaEvalSuite UUID to deleteforce - Force deletion even if suite has active runs (default: false){
"message": "PersonaEvalSuite deleted successfully",
"deletedSuite": {
"id": "123e4567-e89b-12d3-a456-426614174000",
"name": "Customer Service Excellence Suite",
"status": "deleted"
},
"deletedAt": "2024-01-15T17:30:00Z",
"activeRunsCancelled": 0,
"scheduleCancelled": true
}Execute a persona evaluation suite immediately using AWS Step Functions. Returns execution tracking information for monitoring progress.
{
"configuration": {
"priority": "high",
"timeoutMinutes": 60,
"retryOnFailure": true
}
}configuration - Override suite configuration for this runevaluationIds - Run only specific evaluations from the suitetags - Add run-specific tags{
"personaEvalSuiteRun": {
"id": "789e1234-e89b-12d3-a456-426614174000",
"suiteId": "123e4567-e89b-12d3-a456-426614174000",
"suiteName": "Customer Service Excellence Suite",
"status": "running",
"totalEvals": 4,
"passedEvals": 0,
"failedEvals": 0,
"executionArn": "arn:aws:states:us-west-2:123456789012:execution:hermes-persona-eval-runner-staging:789e1234-e89b-12d3-a456-426614174000",
"startedAt": "2024-01-15T18:00:00Z",
"completedAt": null
}
}Important: The persona-eval-suites endpoints do not validate the x-mercury-api-key header. These endpoints are currently accessible without proper authentication. Use caution when calling these endpoints and ensure proper access controls are in place at the network level.