> ## 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 experiments decision

> Requires scopes: eval:write



## OpenAPI

````yaml /api-reference/openapi.json post /api/experiments/{id}/decision
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/experiments/{id}/decision:
    post:
      tags:
        - experiments
      summary: Create experiments decision
      description: 'Requires scopes: eval:write'
      operationId: post_experiments_id_decision
      parameters:
        - name: id
          in: path
          required: true
          schema:
            type: integer
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/PostApiExperimentsIdDecisionRequest'
      responses:
        '200':
          description: Successful response
          content:
            application/json:
              schema:
                $ref: >-
                  #/components/schemas/PostApiExperimentsIdDecisionResponse200ApplicationJson
        '201':
          description: Successful response
          content:
            application/json:
              schema:
                $ref: >-
                  #/components/schemas/PostApiExperimentsIdDecisionResponse201ApplicationJson
        '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:
            - eval:write
components:
  schemas:
    PostApiExperimentsIdDecisionRequest:
      type: object
      properties:
        decision:
          oneOf:
            - type: string
              enum:
                - needs_review
            - type: string
              enum:
                - reject
            - type: string
              enum:
                - accept
        rationale:
          type: string
        idempotencyKey:
          type: string
        comparisonHash:
          oneOf:
            - type: 'null'
            - type: string
        winningVariantKey:
          oneOf:
            - type: 'null'
            - type: string
      additionalProperties: false
      required:
        - decision
        - rationale
        - idempotencyKey
    PostApiExperimentsIdDecisionResponse200ApplicationJson:
      type: object
      properties:
        idempotentReplay:
          type: boolean
        id:
          type: string
        organizationId:
          $ref: '#/components/schemas/OrganizationId'
        experimentId:
          type: string
        executionId:
          type: string
        decision:
          type: string
        winningVariantId:
          oneOf:
            - type: 'null'
            - type: string
        rationale:
          type: string
        comparisonHash:
          oneOf:
            - type: 'null'
            - type: string
        comparisonJson:
          oneOf:
            - type: 'null'
            - type: object
              properties:
                baselineVariantKey:
                  type: string
                candidateVariantKey:
                  type: string
                classification:
                  oneOf:
                    - type: string
                      enum:
                        - not_comparable
                    - type: string
                      enum:
                        - regression
                    - type: string
                      enum:
                        - inconclusive
                    - type: string
                      enum:
                        - improvement
                    - type: string
                      enum:
                        - tradeoff
                    - type: string
                      enum:
                        - tie
                decisionLogic:
                  type: array
                  items:
                    type: string
                comparable:
                  type: boolean
                comparisonHash:
                  type: string
                metrics:
                  type: object
                  properties:
                    quality:
                      type: object
                      properties:
                        baselinePassRate:
                          oneOf:
                            - type: 'null'
                            - type: number
                        candidatePassRate:
                          oneOf:
                            - type: 'null'
                            - type: number
                        delta:
                          oneOf:
                            - type: 'null'
                            - type: number
                        confidence95:
                          oneOf:
                            - type: 'null'
                            - type: object
                              properties:
                                low:
                                  type: number
                                high:
                                  type: number
                              additionalProperties: false
                              required:
                                - low
                                - high
                      additionalProperties: false
                      required:
                        - baselinePassRate
                        - candidatePassRate
                        - delta
                        - confidence95
                    scoreDistribution:
                      type: object
                      properties:
                        baseline:
                          type: array
                          items:
                            type: number
                        candidate:
                          type: array
                          items:
                            type: number
                        meanDelta:
                          oneOf:
                            - type: 'null'
                            - type: number
                      additionalProperties: false
                      required:
                        - baseline
                        - candidate
                        - meanDelta
                    cost:
                      type: object
                      properties:
                        baselineUsd:
                          oneOf:
                            - type: 'null'
                            - type: number
                        candidateUsd:
                          oneOf:
                            - type: 'null'
                            - type: number
                        deltaUsd:
                          oneOf:
                            - type: 'null'
                            - type: number
                        unknownBaselineRows:
                          type: number
                        unknownCandidateRows:
                          type: number
                      additionalProperties: false
                      required:
                        - baselineUsd
                        - candidateUsd
                        - deltaUsd
                        - unknownBaselineRows
                        - unknownCandidateRows
                    latency:
                      type: object
                      properties:
                        baselineP50Ms:
                          oneOf:
                            - type: 'null'
                            - type: number
                        candidateP50Ms:
                          oneOf:
                            - type: 'null'
                            - type: number
                        p50DeltaMs:
                          oneOf:
                            - type: 'null'
                            - type: number
                        baselineP95Ms:
                          oneOf:
                            - type: 'null'
                            - type: number
                        candidateP95Ms:
                          oneOf:
                            - type: 'null'
                            - type: number
                        p95DeltaMs:
                          oneOf:
                            - type: 'null'
                            - type: number
                      additionalProperties: false
                      required:
                        - baselineP50Ms
                        - candidateP50Ms
                        - p50DeltaMs
                        - baselineP95Ms
                        - candidateP95Ms
                        - p95DeltaMs
                    failures:
                      type: object
                      properties:
                        baseline:
                          type: object
                          additionalProperties:
                            type: number
                        candidate:
                          type: object
                          additionalProperties:
                            type: number
                        newRegressions:
                          type: number
                        fixedRegressions:
                          type: number
                        toolCallDelta:
                          type: number
                        toolErrorDelta:
                          type: number
                        policyBlockDelta:
                          type: number
                      additionalProperties: false
                      required:
                        - baseline
                        - candidate
                        - newRegressions
                        - fixedRegressions
                        - toolCallDelta
                        - toolErrorDelta
                        - policyBlockDelta
                  additionalProperties: false
                  required:
                    - quality
                    - scoreDistribution
                    - cost
                    - latency
                    - failures
                pairedRows:
                  type: array
                  items:
                    type: object
                    properties:
                      caseId:
                        type: number
                      baseline:
                        oneOf:
                          - type: 'null'
                          - type: object
                            properties:
                              variantKey:
                                type: string
                              caseId:
                                type: number
                              testResultId:
                                type: number
                              runId:
                                type: number
                              status:
                                type: string
                              output:
                                oneOf:
                                  - type: 'null'
                                  - type: string
                              score:
                                oneOf:
                                  - type: 'null'
                                  - type: number
                              durationMs:
                                oneOf:
                                  - type: 'null'
                                  - type: number
                              costUsd:
                                oneOf:
                                  - type: 'null'
                                  - type: number
                              costKnown:
                                type: boolean
                              failureMode:
                                oneOf:
                                  - type: 'null'
                                  - type: string
                              toolError:
                                type: boolean
                              toolCallCount:
                                type: number
                              policyBlocked:
                                type: boolean
                              judgeIdentity:
                                oneOf:
                                  - type: 'null'
                                  - type: string
                              traceId:
                                oneOf:
                                  - type: 'null'
                                  - type: number
                              modelCallId:
                                oneOf:
                                  - type: 'null'
                                  - type: string
                              evidenceComplete:
                                type: boolean
                            additionalProperties: false
                            required:
                              - variantKey
                              - caseId
                              - testResultId
                              - runId
                              - status
                              - output
                              - score
                              - durationMs
                              - costUsd
                              - costKnown
                              - failureMode
                              - toolError
                              - toolCallCount
                              - policyBlocked
                              - judgeIdentity
                              - traceId
                              - modelCallId
                              - evidenceComplete
                      candidate:
                        oneOf:
                          - type: 'null'
                          - type: object
                            properties:
                              variantKey:
                                type: string
                              caseId:
                                type: number
                              testResultId:
                                type: number
                              runId:
                                type: number
                              status:
                                type: string
                              output:
                                oneOf:
                                  - type: 'null'
                                  - type: string
                              score:
                                oneOf:
                                  - type: 'null'
                                  - type: number
                              durationMs:
                                oneOf:
                                  - type: 'null'
                                  - type: number
                              costUsd:
                                oneOf:
                                  - type: 'null'
                                  - type: number
                              costKnown:
                                type: boolean
                              failureMode:
                                oneOf:
                                  - type: 'null'
                                  - type: string
                              toolError:
                                type: boolean
                              toolCallCount:
                                type: number
                              policyBlocked:
                                type: boolean
                              judgeIdentity:
                                oneOf:
                                  - type: 'null'
                                  - type: string
                              traceId:
                                oneOf:
                                  - type: 'null'
                                  - type: number
                              modelCallId:
                                oneOf:
                                  - type: 'null'
                                  - type: string
                              evidenceComplete:
                                type: boolean
                            additionalProperties: false
                            required:
                              - variantKey
                              - caseId
                              - testResultId
                              - runId
                              - status
                              - output
                              - score
                              - durationMs
                              - costUsd
                              - costKnown
                              - failureMode
                              - toolError
                              - toolCallCount
                              - policyBlocked
                              - judgeIdentity
                              - traceId
                              - modelCallId
                              - evidenceComplete
                      qualityDelta:
                        oneOf:
                          - type: 'null'
                          - type: number
                      costDeltaUsd:
                        oneOf:
                          - type: 'null'
                          - type: number
                      latencyDeltaMs:
                        oneOf:
                          - type: 'null'
                          - type: number
                      classification:
                        oneOf:
                          - type: string
                            enum:
                              - regression
                          - type: string
                            enum:
                              - unchanged
                          - type: string
                            enum:
                              - missing
                          - type: string
                            enum:
                              - disagreement
                          - type: string
                            enum:
                              - improvement
                      warnings:
                        type: array
                        items:
                          type: string
                    additionalProperties: false
                    required:
                      - caseId
                      - baseline
                      - candidate
                      - qualityDelta
                      - costDeltaUsd
                      - latencyDeltaMs
                      - classification
                      - warnings
                warnings:
                  type: array
                  items:
                    type: string
                missingData:
                  type: array
                  items:
                    type: string
              additionalProperties: false
              required:
                - baselineVariantKey
                - candidateVariantKey
                - classification
                - decisionLogic
                - comparable
                - comparisonHash
                - metrics
                - pairedRows
                - warnings
                - missingData
        idempotencyKey:
          type: string
        decidedBy:
          type: string
        decidedAt:
          type: string
          format: date-time
      additionalProperties: false
      required:
        - idempotentReplay
        - id
        - organizationId
        - experimentId
        - executionId
        - decision
        - winningVariantId
        - rationale
        - comparisonHash
        - comparisonJson
        - idempotencyKey
        - decidedBy
        - decidedAt
    PostApiExperimentsIdDecisionResponse201ApplicationJson:
      type: object
      properties:
        idempotentReplay:
          type: boolean
        id:
          type: string
        organizationId:
          $ref: '#/components/schemas/OrganizationId'
        experimentId:
          type: string
        executionId:
          type: string
        decision:
          type: string
        winningVariantId:
          oneOf:
            - type: 'null'
            - type: string
        rationale:
          type: string
        comparisonHash:
          oneOf:
            - type: 'null'
            - type: string
        comparisonJson:
          oneOf:
            - type: 'null'
            - type: object
              properties:
                baselineVariantKey:
                  type: string
                candidateVariantKey:
                  type: string
                classification:
                  oneOf:
                    - type: string
                      enum:
                        - not_comparable
                    - type: string
                      enum:
                        - regression
                    - type: string
                      enum:
                        - inconclusive
                    - type: string
                      enum:
                        - improvement
                    - type: string
                      enum:
                        - tradeoff
                    - type: string
                      enum:
                        - tie
                decisionLogic:
                  type: array
                  items:
                    type: string
                comparable:
                  type: boolean
                comparisonHash:
                  type: string
                metrics:
                  type: object
                  properties:
                    quality:
                      type: object
                      properties:
                        baselinePassRate:
                          oneOf:
                            - type: 'null'
                            - type: number
                        candidatePassRate:
                          oneOf:
                            - type: 'null'
                            - type: number
                        delta:
                          oneOf:
                            - type: 'null'
                            - type: number
                        confidence95:
                          oneOf:
                            - type: 'null'
                            - type: object
                              properties:
                                low:
                                  type: number
                                high:
                                  type: number
                              additionalProperties: false
                              required:
                                - low
                                - high
                      additionalProperties: false
                      required:
                        - baselinePassRate
                        - candidatePassRate
                        - delta
                        - confidence95
                    scoreDistribution:
                      type: object
                      properties:
                        baseline:
                          type: array
                          items:
                            type: number
                        candidate:
                          type: array
                          items:
                            type: number
                        meanDelta:
                          oneOf:
                            - type: 'null'
                            - type: number
                      additionalProperties: false
                      required:
                        - baseline
                        - candidate
                        - meanDelta
                    cost:
                      type: object
                      properties:
                        baselineUsd:
                          oneOf:
                            - type: 'null'
                            - type: number
                        candidateUsd:
                          oneOf:
                            - type: 'null'
                            - type: number
                        deltaUsd:
                          oneOf:
                            - type: 'null'
                            - type: number
                        unknownBaselineRows:
                          type: number
                        unknownCandidateRows:
                          type: number
                      additionalProperties: false
                      required:
                        - baselineUsd
                        - candidateUsd
                        - deltaUsd
                        - unknownBaselineRows
                        - unknownCandidateRows
                    latency:
                      type: object
                      properties:
                        baselineP50Ms:
                          oneOf:
                            - type: 'null'
                            - type: number
                        candidateP50Ms:
                          oneOf:
                            - type: 'null'
                            - type: number
                        p50DeltaMs:
                          oneOf:
                            - type: 'null'
                            - type: number
                        baselineP95Ms:
                          oneOf:
                            - type: 'null'
                            - type: number
                        candidateP95Ms:
                          oneOf:
                            - type: 'null'
                            - type: number
                        p95DeltaMs:
                          oneOf:
                            - type: 'null'
                            - type: number
                      additionalProperties: false
                      required:
                        - baselineP50Ms
                        - candidateP50Ms
                        - p50DeltaMs
                        - baselineP95Ms
                        - candidateP95Ms
                        - p95DeltaMs
                    failures:
                      type: object
                      properties:
                        baseline:
                          type: object
                          additionalProperties:
                            type: number
                        candidate:
                          type: object
                          additionalProperties:
                            type: number
                        newRegressions:
                          type: number
                        fixedRegressions:
                          type: number
                        toolCallDelta:
                          type: number
                        toolErrorDelta:
                          type: number
                        policyBlockDelta:
                          type: number
                      additionalProperties: false
                      required:
                        - baseline
                        - candidate
                        - newRegressions
                        - fixedRegressions
                        - toolCallDelta
                        - toolErrorDelta
                        - policyBlockDelta
                  additionalProperties: false
                  required:
                    - quality
                    - scoreDistribution
                    - cost
                    - latency
                    - failures
                pairedRows:
                  type: array
                  items:
                    type: object
                    properties:
                      caseId:
                        type: number
                      baseline:
                        oneOf:
                          - type: 'null'
                          - type: object
                            properties:
                              variantKey:
                                type: string
                              caseId:
                                type: number
                              testResultId:
                                type: number
                              runId:
                                type: number
                              status:
                                type: string
                              output:
                                oneOf:
                                  - type: 'null'
                                  - type: string
                              score:
                                oneOf:
                                  - type: 'null'
                                  - type: number
                              durationMs:
                                oneOf:
                                  - type: 'null'
                                  - type: number
                              costUsd:
                                oneOf:
                                  - type: 'null'
                                  - type: number
                              costKnown:
                                type: boolean
                              failureMode:
                                oneOf:
                                  - type: 'null'
                                  - type: string
                              toolError:
                                type: boolean
                              toolCallCount:
                                type: number
                              policyBlocked:
                                type: boolean
                              judgeIdentity:
                                oneOf:
                                  - type: 'null'
                                  - type: string
                              traceId:
                                oneOf:
                                  - type: 'null'
                                  - type: number
                              modelCallId:
                                oneOf:
                                  - type: 'null'
                                  - type: string
                              evidenceComplete:
                                type: boolean
                            additionalProperties: false
                            required:
                              - variantKey
                              - caseId
                              - testResultId
                              - runId
                              - status
                              - output
                              - score
                              - durationMs
                              - costUsd
                              - costKnown
                              - failureMode
                              - toolError
                              - toolCallCount
                              - policyBlocked
                              - judgeIdentity
                              - traceId
                              - modelCallId
                              - evidenceComplete
                      candidate:
                        oneOf:
                          - type: 'null'
                          - type: object
                            properties:
                              variantKey:
                                type: string
                              caseId:
                                type: number
                              testResultId:
                                type: number
                              runId:
                                type: number
                              status:
                                type: string
                              output:
                                oneOf:
                                  - type: 'null'
                                  - type: string
                              score:
                                oneOf:
                                  - type: 'null'
                                  - type: number
                              durationMs:
                                oneOf:
                                  - type: 'null'
                                  - type: number
                              costUsd:
                                oneOf:
                                  - type: 'null'
                                  - type: number
                              costKnown:
                                type: boolean
                              failureMode:
                                oneOf:
                                  - type: 'null'
                                  - type: string
                              toolError:
                                type: boolean
                              toolCallCount:
                                type: number
                              policyBlocked:
                                type: boolean
                              judgeIdentity:
                                oneOf:
                                  - type: 'null'
                                  - type: string
                              traceId:
                                oneOf:
                                  - type: 'null'
                                  - type: number
                              modelCallId:
                                oneOf:
                                  - type: 'null'
                                  - type: string
                              evidenceComplete:
                                type: boolean
                            additionalProperties: false
                            required:
                              - variantKey
                              - caseId
                              - testResultId
                              - runId
                              - status
                              - output
                              - score
                              - durationMs
                              - costUsd
                              - costKnown
                              - failureMode
                              - toolError
                              - toolCallCount
                              - policyBlocked
                              - judgeIdentity
                              - traceId
                              - modelCallId
                              - evidenceComplete
                      qualityDelta:
                        oneOf:
                          - type: 'null'
                          - type: number
                      costDeltaUsd:
                        oneOf:
                          - type: 'null'
                          - type: number
                      latencyDeltaMs:
                        oneOf:
                          - type: 'null'
                          - type: number
                      classification:
                        oneOf:
                          - type: string
                            enum:
                              - regression
                          - type: string
                            enum:
                              - unchanged
                          - type: string
                            enum:
                              - missing
                          - type: string
                            enum:
                              - disagreement
                          - type: string
                            enum:
                              - improvement
                      warnings:
                        type: array
                        items:
                          type: string
                    additionalProperties: false
                    required:
                      - caseId
                      - baseline
                      - candidate
                      - qualityDelta
                      - costDeltaUsd
                      - latencyDeltaMs
                      - classification
                      - warnings
                warnings:
                  type: array
                  items:
                    type: string
                missingData:
                  type: array
                  items:
                    type: string
              additionalProperties: false
              required:
                - baselineVariantKey
                - candidateVariantKey
                - classification
                - decisionLogic
                - comparable
                - comparisonHash
                - metrics
                - pairedRows
                - warnings
                - missingData
        idempotencyKey:
          type: string
        decidedBy:
          type: string
        decidedAt:
          type: string
          format: date-time
      additionalProperties: false
      required:
        - idempotentReplay
        - id
        - organizationId
        - experimentId
        - executionId
        - decision
        - winningVariantId
        - rationale
        - comparisonHash
        - comparisonJson
        - idempotencyKey
        - decidedBy
        - decidedAt
    OrganizationId:
      type: string
      format: uuid
    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

````