The PersonaEvalSuiteRuns REST API manages execution instances of evaluation suites. Track comprehensive evaluation runs, aggregate results, and analyze suite-level performance metrics across multiple evaluation dimensions.
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 paginationsuiteId - Filter by evaluation suite IDpersonaId - Filter by persona IDstatus - Filter by run status (running, completed, failed, stopped)startDate - Filter runs after dateendDate - Filter runs before date{
"runs": [
{
"id": "uuid-suite-run-123",
"suiteId": "uuid-suite-456",
"suiteName": "Customer Service Excellence Suite",
"personaId": "uuid-persona-789",
"personaName": "Customer Support Specialist",
"status": "completed",
"startedAt": "2024-01-15T09:00:00Z",
"completedAt": "2024-01-15T09:47:00Z",
"duration": 2820000,
"overallScore": 8.3,
"results": {
"evaluationsCompleted": 4,
"evaluationsFailed": 0,
"totalConversationsEvaluated": 156,
"averageScoreByCategory": {
"communication": 8.7,
"problemResolution": 8.1,
"empathy": 8.5,
"processAdherence": 7.9
},
"passFailStatus": "passed",
"thresholdMet": true,
"minimumScoreRequired": 7.0
},
"evaluationBreakdown": [
{
"evaluationId": "uuid-eval-001",
"evaluationName": "Communication Clarity Assessment",
"score": 8.7,
"weight": 0.35,
"weightedScore": 3.045,
"status": "completed",
"conversationsEvaluated": 45
},
{
"evaluationId": "uuid-eval-002",
"evaluationName": "Problem Resolution Effectiveness",
"score": 8.1,
"weight": 0.25,
"weightedScore": 2.025,
"status": "completed",
"conversationsEvaluated": 38
}
],
"priority": "normal",
"tags": ["scheduled", "routine_assessment"],
"createdAt": "2024-01-15T09:00:00Z",
"updatedAt": "2024-01-15T09:47:00Z"
}
],
"pagination": {
"total": 89,
"limit": 50,
"offset": 0,
"hasNext": true,
"hasPrev": false
}
}id - Suite run UUIDincludeConversations - Include evaluated conversation detailsincludeScoreBreakdown - Include detailed score analysisincludeRecommendations - Include improvement recommendations{
"run": {
"id": "uuid-suite-run-123",
"suiteId": "uuid-suite-456",
"suiteName": "Customer Service Excellence Suite",
"personaId": "uuid-persona-789",
"personaName": "Customer Support Specialist",
"status": "completed",
"startedAt": "2024-01-15T09:00:00Z",
"completedAt": "2024-01-15T09:47:00Z",
"duration": 2820000,
"overallScore": 8.3,
"scoreDistribution": {
"excellent": 23,
"good": 89,
"fair": 35,
"poor": 9
},
"performanceMetrics": {
"averageResponseTime": 1250,
"customerSatisfactionScore": 4.2,
"resolutionRate": 0.87,
"escalationRate": 0.08,
"firstCallResolutionRate": 0.73
},
"evaluationResults": [
{
"evaluationId": "uuid-eval-001",
"evaluationName": "Communication Clarity Assessment",
"score": 8.7,
"weight": 0.35,
"weightedScore": 3.045,
"status": "completed",
"executionTime": 890000,
"conversationsEvaluated": 45,
"scoreBreakdown": {
"clarity": 8.9,
"professionalism": 8.6,
"empathy": 8.5
},
"recommendations": [
"Continue excellent clarity in explanations",
"Consider slightly more casual tone for younger customers"
]
},
{
"evaluationId": "uuid-eval-002",
"evaluationName": "Problem Resolution Effectiveness",
"score": 8.1,
"weight": 0.25,
"weightedScore": 2.025,
"status": "completed",
"executionTime": 1200000,
"conversationsEvaluated": 38,
"scoreBreakdown": {
"diagnosisAccuracy": 8.4,
"solutionEffectiveness": 7.9,
"followUpQuality": 8.0
},
"recommendations": [
"Improve solution verification with customers",
"Enhance follow-up consistency"
]
}
],
"overallRecommendations": [
"Excellent performance across all evaluation areas",
"Focus on solution verification improvements",
"Maintain current communication excellence standards"
],
"comparisonWithPrevious": {
"previousRunId": "uuid-suite-run-100",
"previousScore": 7.9,
"improvement": 0.4,
"trend": "improving"
},
"settings": {
"parallelExecution": false,
"timeoutMinutes": 45,
"priority": "normal"
},
"createdAt": "2024-01-15T09:00:00Z",
"updatedAt": "2024-01-15T09:47:00Z"
}
}Retrieve comprehensive detailed results including conversation-level breakdowns, scoring rationale, and extensive analytics.
format - Response format (json, csv, pdf)includeTranscripts - Include conversation transcriptsevaluationId - Filter by specific evaluationscoreThreshold - Filter conversations by minimum score{
"runId": "uuid-suite-run-123",
"detailedResults": {
"conversationLevelResults": [
{
"conversationId": "uuid-conv-001",
"overallScore": 8.9,
"evaluationScores": {
"uuid-eval-001": {
"score": 9.1,
"criteria": {
"clarity": { "score": 9.0, "rationale": "Excellent clear explanations" },
"professionalism": { "score": 9.2, "rationale": "Maintained professional tone throughout" }
}
},
"uuid-eval-002": {
"score": 8.7,
"criteria": {
"diagnosisAccuracy": { "score": 9.0, "rationale": "Correctly identified root cause" },
"solutionEffectiveness": { "score": 8.4, "rationale": "Solution resolved the issue" }
}
}
},
"conversationMetadata": {
"duration": 12.5,
"messageCount": 18,
"customerSatisfaction": 5,
"issueType": "technical_support",
"priority": "medium",
"resolution": "resolved",
"firstCallResolution": true
}
}
],
"aggregateAnalytics": {
"scoreDistribution": {
"byCategory": {
"communication": { "mean": 8.7, "stdDev": 0.8, "min": 6.2, "max": 10.0 },
"problemResolution": { "mean": 8.1, "stdDev": 1.1, "min": 5.8, "max": 9.8 }
},
"byConversationType": {
"technical_support": { "mean": 8.4, "count": 67 },
"billing_inquiry": { "mean": 8.1, "count": 45 },
"general_inquiry": { "mean": 8.6, "count": 44 }
}
},
"correlationAnalysis": {
"conversationDurationVsScore": 0.12,
"messageCountVsScore": -0.05,
"customerSatisfactionVsScore": 0.78
}
}
}
}