> ## Documentation Index > Fetch the complete documentation index at: https://evalgate.com/docs/llms.txt > Use this file to discover all available pages before exploring further. # Create evaluations dataset > Requires scopes: runs:read ## OpenAPI ````yaml /api-reference/openapi.json post /api/evaluations/{id}/runs/{runId}/dataset openapi: 3.1.0 info: title: EvalGate API version: 3.7.6 description: EvalGate API. See docs/api-contract.md for stability commitments. servers: - url: https://evalgate.com description: Production - url: http://localhost:3000 description: Local security: [] paths: /api/evaluations/{id}/runs/{runId}/dataset: post: tags: - evaluations summary: Create evaluations dataset description: 'Requires scopes: runs:read' operationId: post_evaluations_id_runs_runId_dataset parameters: - name: id in: path required: true schema: type: integer - name: runId in: path required: true schema: type: integer responses: '200': description: Successful response content: application/json: schema: $ref: >- #/components/schemas/PostApiEvaluationsIdRunsRunIdDatasetResponse200ApplicationJson '400': $ref: '#/components/responses/ValidationError' '401': $ref: '#/components/responses/Unauthorized' '403': $ref: '#/components/responses/Forbidden' '404': $ref: '#/components/responses/NotFound' '409': $ref: '#/components/responses/Conflict' '429': $ref: '#/components/responses/RateLimited' '500': $ref: '#/components/responses/InternalError' security: - bearerAuth: - runs:read components: schemas: PostApiEvaluationsIdRunsRunIdDatasetResponse200ApplicationJson: type: object properties: run: type: object properties: status: type: string evaluationId: type: number id: type: number createdAt: type: string format: date-time organizationId: $ref: '#/components/schemas/OrganizationId' environment: oneOf: - type: 'null' - type: string trajectory: type: object properties: schemaVersion: type: number entries: type: array items: type: object properties: testCaseId: type: number status: oneOf: - type: string enum: - failed - type: string enum: - passed behavior: oneOf: - type: string enum: - tool_use - type: string enum: - classification - type: string enum: - retrieval - type: string enum: - extraction - type: string enum: - multi_step_reasoning taskType: type: string trajectory: type: object properties: id: type: string input: type: string finalOutput: type: string steps: type: array items: type: object properties: index: type: number type: oneOf: - type: string enum: - final - type: string enum: - reasoning - type: string enum: - tool_call - type: string enum: - tool_result content: type: string toolName: type: string toolArgs: type: object additionalProperties: $ref: '#/components/schemas/JsonValue' timestamp: type: number additionalProperties: false required: - index - type - content totalSteps: type: number totalToolCalls: type: number durationMs: type: number terminatedEarly: oneOf: - type: boolean enum: - false - type: boolean enum: - true error: type: string additionalProperties: false required: - id - input - finalOutput - steps - totalSteps - totalToolCalls - durationMs idealTrajectory: type: object properties: expectedSteps: type: number expectedToolCalls: type: number requiredTools: type: array items: type: string forbiddenTools: type: array items: type: string allowParallel: oneOf: - type: boolean enum: - false - type: boolean enum: - true maxRedundantSteps: type: number additionalProperties: false required: - expectedSteps - expectedToolCalls baseline: oneOf: - type: 'null' - type: object properties: behavior: oneOf: - type: string enum: - tool_use - type: string enum: - classification - type: string enum: - retrieval - type: string enum: - extraction - type: string enum: - multi_step_reasoning taskType: type: string stepDistribution: type: object properties: p50: type: number p75: type: number p90: type: number additionalProperties: false required: - p50 - p75 - p90 toolCallDistribution: type: object properties: p50: type: number p75: type: number additionalProperties: false required: - p50 - p75 durationDistribution: type: object properties: p50: type: number p75: type: number additionalProperties: false required: - p50 - p75 commonToolSequences: type: array items: type: array items: type: string redundancyProfile: type: object properties: mean: type: number p90: type: number additionalProperties: false required: - mean - p90 parallelToolGroups: type: array items: type: array items: type: string sampleSize: type: number updatedAt: type: string version: type: string model: type: string additionalProperties: false required: - behavior - stepDistribution - toolCallDistribution - durationDistribution - commonToolSequences - redundancyProfile - sampleSize - updatedAt evaluation: oneOf: - type: 'null' - type: object properties: schemaVersion: type: number trajectoryId: type: string behavior: oneOf: - type: string enum: - tool_use - type: string enum: - classification - type: string enum: - retrieval - type: string enum: - extraction - type: string enum: - multi_step_reasoning taskType: type: string valid: type: boolean score: oneOf: - type: 'null' - type: number baselineVersion: oneOf: - type: 'null' - type: string failureModes: type: array items: oneOf: - type: string enum: - inefficient_path - type: string enum: - unnecessary_tool_call - type: string enum: - missed_tool_call - type: string enum: - looping_behavior - type: string enum: - non_parallel_execution - type: string enum: - premature_termination metrics: oneOf: - type: 'null' - type: object properties: actualSteps: type: number actualToolCalls: type: number actualDurationMs: type: number redundancyRatio: type: number redundancySteps: type: number sequenceSimilarity: type: number efficiency: type: number toolUsage: type: number redundancy: type: number latency: type: number parallelizationPenalty: type: number parallelizationScore: type: number requiredToolsMissing: type: array items: type: string forbiddenToolsUsed: type: array items: type: string extraToolsUsed: type: array items: type: string selectedBaselineVersion: oneOf: - type: 'null' - type: string baselineStepP50: type: number baselineStepP75: type: number baselineToolCallP50: type: number baselineToolCallP75: type: number baselineDurationP50: type: number baselineDurationP75: type: number idealExpectedSteps: type: number idealExpectedToolCalls: type: number additionalProperties: false required: - actualSteps - actualToolCalls - actualDurationMs - redundancyRatio - redundancySteps - sequenceSimilarity - efficiency - toolUsage - redundancy - latency - parallelizationPenalty - parallelizationScore - requiredToolsMissing - forbiddenToolsUsed - extraToolsUsed additionalProperties: false required: - schemaVersion - valid - score - failureModes - metrics additionalProperties: false required: - testCaseId - status - trajectory additionalProperties: false required: - schemaVersion - entries startedAt: oneOf: - type: 'null' - type: string format: date-time completedAt: oneOf: - type: 'null' - type: string format: date-time idempotencyKey: oneOf: - type: 'null' - type: string totalCases: oneOf: - type: 'null' - type: number passedCases: oneOf: - type: 'null' - type: number failedCases: oneOf: - type: 'null' - type: number processedCount: oneOf: - type: 'null' - type: number traceLog: oneOf: - type: 'null' - type: object properties: messages: type: array items: type: object properties: role: oneOf: - type: string enum: - user - type: string enum: - system - type: string enum: - developer - type: string enum: - tool - type: string enum: - tool_result - type: string enum: - assistant content: type: string timestamp: type: string additionalProperties: false required: - role - content originalEvaluationId: type: number shadowEvalType: type: string resolvedTraceIds: type: array items: type: string jobId: type: number requestedAt: type: string enqueuedAt: type: string enqueueError: type: string lastError: type: string completedAt: type: string averageScore: type: number trajectoryCoverageRate: type: number trajectoryAverageScore: oneOf: - type: 'null' - type: number trajectoryFailureCounts: type: object additionalProperties: type: number error: type: string failedAt: type: string totalCases: type: number processedCount: type: number cancelledAt: oneOf: - type: string - type: string format: date-time traceIds: type: array items: type: string import: type: object properties: sourceTraceId: type: string sourceOrgId: type: string importedAt: type: string source: type: string checkReport: type: object additionalProperties: $ref: '#/components/schemas/JsonValue' gateCheckedAt: type: string additionalProperties: false type: type: string scoreImprovement: type: number dateRange: type: object properties: start: type: string end: type: string additionalProperties: false filters: type: object additionalProperties: $ref: '#/components/schemas/JsonValue' createdBy: type: string additionalProperties: false trajectoryMetrics: oneOf: - type: 'null' - type: object properties: schemaVersion: type: number totalResults: type: number evaluatedResults: type: number coverageRate: type: number averageTrajectoryScore: oneOf: - type: 'null' - type: number failureCounts: type: object properties: inefficient_path: type: number unnecessary_tool_call: type: number missed_tool_call: type: number looping_behavior: type: number non_parallel_execution: type: number premature_termination: type: number additionalProperties: false byTestCase: type: array items: type: object properties: testCaseId: type: number status: oneOf: - type: string enum: - failed - type: string enum: - passed trajectoryId: type: string behavior: oneOf: - type: string enum: - tool_use - type: string enum: - classification - type: string enum: - retrieval - type: string enum: - extraction - type: string enum: - multi_step_reasoning taskType: type: string score: oneOf: - type: 'null' - type: number baselineVersion: oneOf: - type: 'null' - type: string failureModes: type: array items: oneOf: - type: string enum: - inefficient_path - type: string enum: - unnecessary_tool_call - type: string enum: - missed_tool_call - type: string enum: - looping_behavior - type: string enum: - non_parallel_execution - type: string enum: - premature_termination metrics: oneOf: - type: 'null' - type: object properties: actualSteps: type: number actualToolCalls: type: number actualDurationMs: type: number redundancyRatio: type: number redundancySteps: type: number sequenceSimilarity: type: number efficiency: type: number toolUsage: type: number redundancy: type: number latency: type: number parallelizationPenalty: type: number parallelizationScore: type: number requiredToolsMissing: type: array items: type: string forbiddenToolsUsed: type: array items: type: string extraToolsUsed: type: array items: type: string selectedBaselineVersion: oneOf: - type: 'null' - type: string baselineStepP50: type: number baselineStepP75: type: number baselineToolCallP50: type: number baselineToolCallP75: type: number baselineDurationP50: type: number baselineDurationP75: type: number idealExpectedSteps: type: number idealExpectedToolCalls: type: number additionalProperties: false required: - actualSteps - actualToolCalls - actualDurationMs - redundancyRatio - redundancySteps - sequenceSimilarity - efficiency - toolUsage - redundancy - latency - parallelizationPenalty - parallelizationScore - requiredToolsMissing - forbiddenToolsUsed - extraToolsUsed additionalProperties: false required: - testCaseId - status - score - failureModes - metrics additionalProperties: false required: - schemaVersion - totalResults - evaluatedResults - coverageRate - averageTrajectoryScore - failureCounts - byTestCase baselineVersion: oneOf: - type: 'null' - type: string scoreProvenance: oneOf: - type: 'null' - type: object properties: scoringVersion: type: string assertionSetVersion: type: string judgeConfigHash: type: string promptTemplateHash: type: string aggregationVersion: type: string embeddingModel: type: string taskType: type: string behaviorVersion: type: string calibrationStudyId: type: string additionalProperties: false required: - scoringVersion - assertionSetVersion - taskType measurementStatus: oneOf: - type: 'null' - type: string measurementSummary: oneOf: - type: 'null' - type: object properties: version: type: string enum: - evalgate.measurement.v1 status: oneOf: - type: string enum: - valid - type: string enum: - pending - type: string enum: - failed - type: string enum: - complete - type: string enum: - queued - type: string enum: - partial - type: string enum: - invalid - type: string enum: - unstable - type: string enum: - insufficient sampleSize: type: number uncertainty: type: object properties: lower: type: number upper: type: number confidenceLevel: type: number method: type: string enum: - percentile-bootstrap resamples: type: number seed: type: number additionalProperties: false required: - lower - upper - confidenceLevel - method - resamples - seed metrics: type: object additionalProperties: oneOf: - type: 'null' - type: number warnings: type: array items: type: string computationHash: type: string additionalProperties: false required: - version - status - sampleSize - metrics - warnings - computationHash measurementCompletedAt: oneOf: - type: 'null' - type: string format: date-time activeMeasurementRevisionId: oneOf: - type: 'null' - type: string qualitySummary: oneOf: - type: 'null' - type: object properties: version: type: string enum: - evalgate.measurement.v1 status: oneOf: - type: string enum: - valid - type: string enum: - pending - type: string enum: - failed - type: string enum: - complete - type: string enum: - queued - type: string enum: - partial - type: string enum: - invalid - type: string enum: - unstable - type: string enum: - insufficient sampleSize: type: number uncertainty: type: object properties: lower: type: number upper: type: number confidenceLevel: type: number method: type: string enum: - percentile-bootstrap resamples: type: number seed: type: number additionalProperties: false required: - lower - upper - confidenceLevel - method - resamples - seed metrics: type: object additionalProperties: oneOf: - type: 'null' - type: number warnings: type: array items: type: string computationHash: type: string additionalProperties: false required: - version - status - sampleSize - metrics - warnings - computationHash qualitySummaryCompletedAt: oneOf: - type: 'null' - type: string format: date-time orchestrationGraph: oneOf: - type: 'null' - type: object properties: schemaVersion: type: number enum: - 1 rootNodeId: type: string nodes: type: array items: type: object properties: id: type: string type: oneOf: - type: string enum: - rejected - type: string enum: - candidate - type: string enum: - baseline - type: string enum: - winning - type: string enum: - knowledge label: type: string agentIndex: type: number strategyTrack: type: string passRate: type: number kept: oneOf: - type: boolean enum: - false - type: boolean enum: - true metadata: type: object additionalProperties: $ref: '#/components/schemas/JsonValue' additionalProperties: false required: - id - type - label edges: type: array items: type: object properties: from: type: string to: type: string label: type: string additionalProperties: false required: - from - to capturedAt: type: string gateDecisions: type: array items: type: object properties: timestamp: type: string passed: type: boolean exitCode: type: number reasonCode: type: string reasonMessage: oneOf: - type: 'null' - type: string policy: oneOf: - type: 'null' - type: string thresholds: type: object properties: minScore: type: number maxDrop: type: number warnDrop: type: number additionalProperties: false score: oneOf: - type: 'null' - type: number baselineScore: oneOf: - type: 'null' - type: number regressionDelta: oneOf: - type: 'null' - type: number baselineRunId: oneOf: - type: 'null' - type: number ciRunUrl: oneOf: - type: 'null' - type: string failedTestCaseIds: type: array items: type: number additionalProperties: false required: - timestamp - passed - exitCode - reasonCode - thresholds additionalProperties: false required: - schemaVersion - rootNodeId - nodes - edges - capturedAt playgroundId: oneOf: - type: 'null' - type: number variantId: oneOf: - type: 'null' - type: number promptVersionId: oneOf: - type: 'null' - type: string baselineVariantId: oneOf: - type: 'null' - type: number triggerSource: oneOf: - type: 'null' - type: string additionalProperties: false required: - status - evaluationId - id - createdAt - organizationId - environment - trajectory - startedAt - completedAt - idempotencyKey - totalCases - passedCases - failedCases - processedCount - traceLog - trajectoryMetrics - baselineVersion - scoreProvenance - measurementStatus - measurementSummary - measurementCompletedAt - activeMeasurementRevisionId - qualitySummary - qualitySummaryCompletedAt - orchestrationGraph - playgroundId - variantId - promptVersionId - baselineVariantId - triggerSource rows: type: array items: type: object properties: caseId: type: string input: type: string expected: type: string actual: type: string label: oneOf: - type: string enum: - pass - type: string enum: - fail failureMode: oneOf: - type: 'null' - type: string labeledAt: type: string metadata: type: object properties: behavior: type: string difficulty: type: string tags: type: array items: type: string sourceRunId: oneOf: - type: 'null' - type: number sourceTestCaseId: oneOf: - type: 'null' - type: number agentWorkflow: type: object properties: version: type: number enum: - 1 workflowClass: oneOf: - type: string enum: - approval_gated_mutation - type: string enum: - background_execution - type: string enum: - recovery_required - type: string enum: - policy_conflict - type: string enum: - handoff_heavy - type: string enum: - memory_sensitive - type: string enum: - parallel_tool_use autonomyLevel: oneOf: - type: string enum: - manual - type: string enum: - default_approvals - type: string enum: - bypass_approvals - type: string enum: - autopilot approvalMode: oneOf: - type: string enum: - human_review - type: string enum: - none - type: string enum: - policy_guided - type: string enum: - auto_with_audit riskLevel: oneOf: - type: string enum: - low - type: string enum: - medium - type: string enum: - high - type: string enum: - critical memoryMode: oneOf: - type: string enum: - session - type: string enum: - none - type: string enum: - persistent - type: string enum: - mixed backgroundExecution: type: boolean requiresCheckpoint: type: boolean expectedHandoff: type: boolean requiredHooks: type: array items: oneOf: - type: string enum: - session_start - type: string enum: - pre_plan - type: string enum: - pre_tool - type: string enum: - post_tool - type: string enum: - pre_write - type: string enum: - pre_handoff - type: string enum: - on_error - type: string enum: - session_end activeTools: type: array items: type: string permissionScope: type: object properties: filesystem: type: array items: type: string network: oneOf: - type: string enum: - open - type: string enum: - restricted - type: string enum: - none externalSystems: type: array items: type: string mutatesState: oneOf: - type: boolean enum: - false - type: boolean enum: - true additionalProperties: false expectedFailureModes: type: array items: type: string scenario: type: string provenance: type: object properties: source: oneOf: - type: string enum: - manual - type: string enum: - evaluation_run - type: string enum: - coverage_gap - type: string enum: - trace_failure evaluationId: type: number runId: type: number testCaseId: type: number traceId: oneOf: - type: 'null' - type: string additionalProperties: false required: - source additionalProperties: false required: - version - workflowClass - autonomyLevel - approvalMode - riskLevel - memoryMode - backgroundExecution - requiresCheckpoint - expectedHandoff - requiredHooks - activeTools - permissionScope - expectedFailureModes - scenario workflowExperimentRecipe: oneOf: - type: 'null' - type: object properties: version: type: number enum: - 1 title: type: string objective: type: string workflowClass: oneOf: - type: string enum: - approval_gated_mutation - type: string enum: - background_execution - type: string enum: - recovery_required - type: string enum: - policy_conflict - type: string enum: - handoff_heavy - type: string enum: - memory_sensitive - type: string enum: - parallel_tool_use source: oneOf: - type: string enum: - coverage_gap - type: string enum: - failure linkedFailureModes: type: array items: type: string linkedTestCaseIds: type: array items: type: number comparedVariants: type: array items: type: object properties: id: type: string label: type: string changes: type: array items: type: string autonomyLevel: oneOf: - type: string enum: - manual - type: string enum: - default_approvals - type: string enum: - bypass_approvals - type: string enum: - autopilot approvalMode: oneOf: - type: string enum: - human_review - type: string enum: - none - type: string enum: - policy_guided - type: string enum: - auto_with_audit memoryMode: oneOf: - type: string enum: - session - type: string enum: - none - type: string enum: - persistent - type: string enum: - mixed hooks: type: array items: oneOf: - type: string enum: - session_start - type: string enum: - pre_plan - type: string enum: - pre_tool - type: string enum: - post_tool - type: string enum: - pre_write - type: string enum: - pre_handoff - type: string enum: - on_error - type: string enum: - session_end expectedImpact: type: string additionalProperties: false required: - id - label - changes - expectedImpact successMetrics: type: array items: type: string guardrails: type: array items: type: string recommendedIterations: type: number rationale: type: string additionalProperties: false required: - version - title - objective - workflowClass - source - linkedFailureModes - linkedTestCaseIds - comparedVariants - successMetrics - guardrails - recommendedIterations - rationale additionalProperties: false additionalProperties: false required: - caseId - input - expected - actual - label - failureMode - labeledAt content: type: string total: type: number passed: type: number failed: type: number additionalProperties: false required: - run - rows - content - total - passed - failed OrganizationId: type: string format: uuid JsonValue: oneOf: - type: 'null' - type: boolean - type: number - type: string - type: array items: $ref: '#/components/schemas/JsonValue' - type: object additionalProperties: $ref: '#/components/schemas/JsonValue' ApiError: type: object properties: error: type: object properties: code: type: string enum: - UNAUTHORIZED - FORBIDDEN - NOT_FOUND - VALIDATION_ERROR - RATE_LIMITED - CONFLICT - INTERNAL_ERROR - SERVICE_UNAVAILABLE - QUOTA_EXCEEDED - NO_ORG_MEMBERSHIP - CROSS_ORG_REFERENCE - INCOMPLETE - MALFORMED message: type: string details: {} requestId: type: string format: uuid required: - code - message required: - error responses: ValidationError: description: Validation error content: application/json: schema: $ref: '#/components/schemas/ApiError' Unauthorized: description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/ApiError' Forbidden: description: Forbidden content: application/json: schema: $ref: '#/components/schemas/ApiError' NotFound: description: Resource not found content: application/json: schema: $ref: '#/components/schemas/ApiError' Conflict: description: Conflict content: application/json: schema: $ref: '#/components/schemas/ApiError' RateLimited: description: Rate limit exceeded content: application/json: schema: $ref: '#/components/schemas/ApiError' InternalError: description: Internal server error content: application/json: schema: $ref: '#/components/schemas/ApiError' securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: API Key or Session Token ````