> ## Documentation Index > Fetch the complete documentation index at: https://docs.roark.ai/llms.txt > Use this file to discover all available pages before exploring further. # Start an Autoimprove job > Commission Roark on an objective. It clones the agent into a staging shadow (or uses your designated staging agent), authors a validation suite of simulated callers, measures a baseline, changes the staging configuration, and re-tests until the objective metric passes its target. Production is never touched by the loop; verified changes wait for promotion. Requires an active provider integration (Vapi or Retell) with agent config writes enabled. One live job per agent: starting a second returns a conflict. The job runs asynchronously; poll GET /v1/autoimprove/job/{jobId} or watch it in the dashboard. When its status is NEEDS_INPUT, answer via the answer endpoint; when AWAITING_PROMOTE, promote or dismiss. ## OpenAPI ````yaml /api-reference/openapi.documented.json post /v1/autoimprove/job openapi: 3.1.0 info: title: Roark Analytics API description: >- The Roark Analytics API gives you access to the same API that powers the award winning Roark Analytics platform. version: 1.0.0 servers: - description: Production url: https://api.roark.ai security: - Bearer: [] tags: - name: Agent - name: Agent Endpoint - name: Call - name: Chat - name: Metric - name: Metric Policy - name: Metric Collection Job - name: Customer Flow - name: Customer Flow Edge Case - name: Simulation - name: Simulation Persona - name: Simulation Environment - name: Simulation Scenario - name: Simulation Run Plan - name: Simulation Template - name: Simulation Run Plan Job - name: Simulation Job - name: HTTP Request Definition - name: Webhook - name: Issue - name: Autoimprove - name: Knowledge Base - name: Config - name: CLI Auth - name: Call Analysis - name: Benchmark - name: Health paths: /v1/autoimprove/job: post: tags: - Autoimprove summary: Start an Autoimprove job description: >- Commission Roark on an objective. It clones the agent into a staging shadow (or uses your designated staging agent), authors a validation suite of simulated callers, measures a baseline, changes the staging configuration, and re-tests until the objective metric passes its target. Production is never touched by the loop; verified changes wait for promotion. Requires an active provider integration (Vapi or Retell) with agent config writes enabled. One live job per agent: starting a second returns a conflict. The job runs asynchronously; poll GET /v1/autoimprove/job/{jobId} or watch it in the dashboard. When its status is NEEDS_INPUT, answer via the answer endpoint; when AWAITING_PROMOTE, promote or dismiss. operationId: postV1AutoimproveJob requestBody: content: application/json: schema: $ref: '#/components/schemas/CreateAutoimproveJobInput' responses: '201': description: The job was created and its loop started. content: application/json: schema: type: object properties: data: $ref: '#/components/schemas/AutoimproveJob' required: - data '400': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' description: Validation error example: type: validation code: invalid_parameter message: The request was invalid param: email description: Bad Request '401': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' description: Authentication error example: type: authentication code: unauthorized message: Authentication required description: Unauthorized '403': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' description: Permission error example: type: forbidden code: permission_denied message: You do not have permission to access this resource description: The integration does not allow agent config writes '404': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' description: Not found error example: type: not_found code: resource_not_found message: The requested resource could not be found description: Not Found '409': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' description: Conflict error example: type: conflict code: resource_in_use message: The resource is in use and cannot be deleted description: A job is already live for this agent '429': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' description: Rate limit error example: type: rate_limit code: too_many_requests message: Rate limit exceeded description: Too Many Requests '500': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' description: Server error example: type: internal code: internal_error message: Internal server error description: Internal Server Error x-codeSamples: - lang: JavaScript source: |- import Roark from '@roarkanalytics/sdk'; const client = new Roark({ bearerToken: process.env['ROARK_API_BEARER_TOKEN'], // This is the default and can be omitted }); const autoimproveJob = await client.autoimproveJob.create({ agentId: 'b3b0c8e2-4c1d-4f6a-9e2b-1a2b3c4d5e6f', objectiveLabel: 'Consent collection should pass', objectiveMetricDefinitionId: 'f2f0c8e2-4c1d-4f6a-9e2b-1a2b3c4d5e6f', }); console.log(autoimproveJob.data); - lang: Python source: |- import os from roark_analytics import Roark client = Roark( bearer_token=os.environ.get("ROARK_API_BEARER_TOKEN"), # This is the default and can be omitted ) autoimprove_job = client.autoimprove_job.create( agent_id="b3b0c8e2-4c1d-4f6a-9e2b-1a2b3c4d5e6f", objective_label="Consent collection should pass", objective_metric_definition_id="f2f0c8e2-4c1d-4f6a-9e2b-1a2b3c4d5e6f", ) print(autoimprove_job.data) components: schemas: CreateAutoimproveJobInput: type: object properties: agentId: type: string format: uuid description: >- The production agent to improve. It is never modified until you promote. example: b3b0c8e2-4c1d-4f6a-9e2b-1a2b3c4d5e6f objectiveMetricDefinitionId: type: string format: uuid description: >- The metric that defines success: a pass/fail metric, or a threshold variant of a scale metric (for example "PII Handling >= 4"). Roark measures the pass rate of this metric across simulated calls. example: f2f0c8e2-4c1d-4f6a-9e2b-1a2b3c4d5e6f objectiveLabel: type: string minLength: 1 maxLength: 200 description: >- Human-readable label for the objective, shown everywhere the job appears. example: Consent collection should pass targetValue: type: number minimum: 1 maximum: 100 default: 90 description: The pass-rate percentage that counts as fixed. Defaults to 90. example: 90 stagingAgentId: type: string format: uuid description: >- An existing agent to stage changes on instead of the default shadow clone. Must be a different agent from agentId, on the same provider. customerIntegrationId: type: string format: uuid description: >- The provider integration whose credentials Roark uses. Omit to use the project's active integration for the agent's provider. The integration must have agent config writes enabled. validationRunPlanId: type: string format: uuid description: >- An existing simulation run plan to validate with. Omit to let Roark author its own suite. maxIterations: type: integer minimum: 1 maximum: 100 description: Cap on decision turns. Defaults to 50. maxSimCalls: type: integer minimum: 1 maximum: 2000 description: Cap on simulated calls dialed. Defaults to 200. required: - agentId - objectiveMetricDefinitionId - objectiveLabel AutoimproveJob: type: object properties: id: type: string format: uuid organizationId: type: string format: uuid projectId: type: string format: uuid agentId: type: string format: uuid stagingAgentId: type: string format: uuid stagingKind: type: string enum: - DESIGNATED - SHADOW customerIntegrationId: type: string format: uuid objectiveMetricDefinitionId: type: string format: uuid objectiveLabel: type: string targetValue: type: number baselineValue: type: - number - 'null' currentValue: type: - number - 'null' trigger: type: string enum: - ISSUE - RUN_THRESHOLD_FAILED - USER - DEGRADATION issueId: type: - string - 'null' format: uuid objectiveId: type: - string - 'null' format: uuid validationRunPlanId: type: - string - 'null' format: uuid status: type: string enum: - RUNNING - NEEDS_INPUT - PAUSED - AWAITING_PROMOTE - PROMOTED - NO_FIX - CANCELLED - FAILED workingMemory: type: - string - 'null' finalReport: type: - string - 'null' maxIterations: type: integer maxSimCalls: type: integer iterationCount: type: integer simCallsUsed: type: integer initiatedByUserId: type: - string - 'null' format: uuid concludedAt: type: - string - 'null' description: When the job reached a terminal status (ISO 8601). createdAt: type: string description: When the job was created (ISO 8601). updatedAt: type: string description: When the job last changed (ISO 8601). required: - id - organizationId - projectId - agentId - stagingAgentId - stagingKind - customerIntegrationId - objectiveMetricDefinitionId - objectiveLabel - targetValue - baselineValue - currentValue - trigger - issueId - objectiveId - validationRunPlanId - status - workingMemory - finalReport - maxIterations - maxSimCalls - iterationCount - simCallsUsed - initiatedByUserId - concludedAt - createdAt - updatedAt description: >- One Autoimprove job: Roark autonomously improving one agent toward one objective metric. Roark only ever changes the staging agent (a shadow clone by default); production changes exactly once, when verified changes are promoted. ErrorResponse: type: object properties: type: type: string enum: - validation - authentication - forbidden - not_found - conflict - payment_required - rate_limit - internal description: The error type category examples: - validation - authentication code: type: string description: Machine-readable error code identifier examples: - invalid_parameter - missing_required_field - unauthorized message: type: string description: Human-readable error message examples: - The request was invalid - Authentication required param: type: string description: The parameter that caused the error (if applicable) examples: - email - user_id details: description: Additional error context information required: - type - code - message securitySchemes: Bearer: type: http scheme: bearer bearerFormat: JWT ````