> ## Documentation Index > Fetch the complete documentation index at: https://docs.labelbox.com/llms.txt > Use this file to discover all available pages before exploring further. # Get an automation run's result > Returns where one automation run stands and, once it is finished, its verdict: passed, completed, failed, needs_attention, cancelled or error, with a reason code, the graded outcome, the structured JSON result, the agent's final message and the files its session saved. Pass waitSeconds to hold the request while the run is not finished, up to 20 seconds; repeat the request until state is finished. A finished run reads running again when its session continues: when someone acts on it, or on its own when a browser hand-off (awaiting_human) passes its deadline or credits are bought for a session paused out of credit. A run of a Slack trigger that continues a thread shares its session with the thread's other runs and has no result of its own: it is refused with automation_run_session_shared. ## OpenAPI ````yaml /recursion/openapi.yaml get /managed-agents/v1/automation-runs/{automationRunId}/result openapi: 3.1.0 info: title: Managed Agents API version: 0.15.0 description: >- The Recursion Managed Agents REST API. Authenticate with a Recursion API key as a bearer token. An organization-scoped key acts in its own organization and needs nothing else; a tenant-scoped key must also send `x-organization-id` with an organization id or `default`. Field names follow each operation's published schema. servers: - url: https://api.recursion.labelbox.com security: - bearerAuth: [] paths: /managed-agents/v1/automation-runs/{automationRunId}/result: get: tags: - Automations summary: Get an automation run's result description: >- Returns where one automation run stands and, once it is finished, its verdict: passed, completed, failed, needs_attention, cancelled or error, with a reason code, the graded outcome, the structured JSON result, the agent's final message and the files its session saved. Pass waitSeconds to hold the request while the run is not finished, up to 20 seconds; repeat the request until state is finished. A finished run reads running again when its session continues: when someone acts on it, or on its own when a browser hand-off (awaiting_human) passes its deadline or credits are bought for a session paused out of credit. A run of a Slack trigger that continues a thread shares its session with the thread's other runs and has no result of its own: it is refused with automation_run_session_shared. operationId: managedAgentsGetAutomationRunResult parameters: - description: >- Hold the request up to this many seconds while the run is not finished, and answer as soon as it finishes. 0 answers at once. At most 20; repeat the request to keep waiting. in: query name: waitSeconds schema: default: 0 description: >- Hold the request up to this many seconds while the run is not finished, and answer as soon as it finishes. 0 answers at once. At most 20; repeat the request to keep waiting. maximum: 20 minimum: 0 type: integer - description: Stable canonical automation-run identifier. in: path name: automationRunId required: true schema: description: Stable canonical automation-run identifier. format: uuid type: string - $ref: '#/components/parameters/RecursionTenantId' - $ref: '#/components/parameters/RecursionOrganizationId' responses: '200': content: application/json: schema: $ref: '#/components/schemas/AutomationRunResultResponse' description: >- Where an automation run stands and, once it is finished, its verdict, outcome, structured result, final message and saved files. headers: recursion-organization-id: $ref: '#/components/headers/RecursionOrganizationId' recursion-tenant-id: $ref: '#/components/headers/RecursionTenantId' '400': description: Bad Request. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiErrorInvalidRequest' x-recursion-error-codes: - invalid_request headers: recursion-organization-id: $ref: '#/components/headers/RecursionOrganizationId' recursion-tenant-id: $ref: '#/components/headers/RecursionTenantId' '401': description: Unauthorized. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiErrorUnauthorized' x-recursion-error-codes: - unauthorized headers: recursion-organization-id: $ref: '#/components/headers/RecursionOrganizationId' recursion-tenant-id: $ref: '#/components/headers/RecursionTenantId' '403': description: Forbidden. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiErrorForbidden' x-recursion-error-codes: - forbidden headers: recursion-organization-id: $ref: '#/components/headers/RecursionOrganizationId' recursion-tenant-id: $ref: '#/components/headers/RecursionTenantId' '404': description: Not Found. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiErrorNotFound' x-recursion-error-codes: - not_found headers: recursion-organization-id: $ref: '#/components/headers/RecursionOrganizationId' recursion-tenant-id: $ref: '#/components/headers/RecursionTenantId' '413': description: Payload Too Large. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiErrorPayloadTooLarge' x-recursion-error-codes: - payload_too_large headers: recursion-organization-id: $ref: '#/components/headers/RecursionOrganizationId' recursion-tenant-id: $ref: '#/components/headers/RecursionTenantId' '422': description: Unprocessable Entity. content: application/json: schema: $ref: >- #/components/schemas/ManagedAgentsApiErrorAutomationRunSessionShared x-recursion-error-codes: - automation_run_session_shared headers: recursion-organization-id: $ref: '#/components/headers/RecursionOrganizationId' recursion-tenant-id: $ref: '#/components/headers/RecursionTenantId' '429': headers: Retry-After: description: When to retry, as delay seconds or an HTTP date. schema: type: string recursion-organization-id: $ref: '#/components/headers/RecursionOrganizationId' recursion-tenant-id: $ref: '#/components/headers/RecursionTenantId' description: Too Many Requests. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiErrorRateLimitExceeded' x-recursion-error-codes: - rate_limit_exceeded '500': description: Internal Server Error. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiErrorInternalError' x-recursion-error-codes: - internal_error headers: recursion-organization-id: $ref: '#/components/headers/RecursionOrganizationId' recursion-tenant-id: $ref: '#/components/headers/RecursionTenantId' '502': description: A dependent service returned an invalid response. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiErrorDependencyFailure' x-recursion-error-codes: - bad_gateway headers: recursion-organization-id: $ref: '#/components/headers/RecursionOrganizationId' recursion-tenant-id: $ref: '#/components/headers/RecursionTenantId' '503': description: Service Unavailable. content: application/json: schema: oneOf: - $ref: >- #/components/schemas/ManagedAgentsApiErrorAutomationRunsUnconfigured - $ref: >- #/components/schemas/ManagedAgentsApiErrorManagedAgentsUnavailable - $ref: >- #/components/schemas/ManagedAgentsApiErrorServiceUnavailable discriminator: propertyName: code mapping: automation_runs_unconfigured: >- #/components/schemas/ManagedAgentsApiErrorAutomationRunsUnconfigured managed_agents_unavailable: >- #/components/schemas/ManagedAgentsApiErrorManagedAgentsUnavailable service_unavailable: >- #/components/schemas/ManagedAgentsApiErrorServiceUnavailable x-recursion-error-codes: - automation_runs_unconfigured - managed_agents_unavailable - service_unavailable headers: recursion-organization-id: $ref: '#/components/headers/RecursionOrganizationId' recursion-tenant-id: $ref: '#/components/headers/RecursionTenantId' '504': headers: Retry-After: description: When to retry, as delay seconds or an HTTP date. schema: type: string recursion-organization-id: $ref: '#/components/headers/RecursionOrganizationId' recursion-tenant-id: $ref: '#/components/headers/RecursionTenantId' description: A dependent service timed out. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiErrorDependencyTimeout' x-recursion-error-codes: - gateway_timeout components: parameters: RecursionTenantId: name: x-tenant-id in: header required: false description: >- Optional tenant consistency check. When present, it must name the tenant bound to the API key, including when x-organization-id is `default`. schema: type: string minLength: 1 RecursionOrganizationId: name: x-organization-id in: header required: false description: >- Organization in which to act. Required for a tenant-scoped API key. Optional for an organization-scoped key, where it must name that same organization. The value may be an organization id or `default`. schema: type: string minLength: 1 schemas: AutomationRunResultResponse: additionalProperties: false description: >- Where an automation run stands and, once it is finished, its verdict, outcome, structured result, final message and saved files. properties: artifacts: description: >- Files the run's session saved, sorted by path, at most 100. Download one with GET /managed-agents/v1/files/{fileId}/content. Empty until state is finished. items: $ref: '#/components/schemas/AutomationRunResultArtifact' maxItems: 100 type: array artifactsTruncated: description: True when the session saved more files than artifacts lists. type: boolean automationId: description: The automation that started the run. format: uuid type: string automationRunId: description: The run this result describes. format: uuid type: string finalMessage: $ref: '#/components/schemas/AutomationRunResultFinalMessage' description: >- The text of the agent's last message. Present only when state is finished and the agent wrote one. finishedAt: description: >- When the run reached its verdict. Present only when state is finished. format: date-time type: string outcome: $ref: '#/components/schemas/AutomationRunResultOutcome' description: >- The session's newest outcome and its last grading pass. Present only when state is finished and the session was graded. output: $ref: '#/components/schemas/AutomationRunResultOutput' description: >- The run's structured JSON result. Present only when state is finished, and then when the automation declares runDefaults.output, or otherwise when the final message holds JSON. reason: description: >- Stable code explaining the verdict, such as outcome_satisfied, outcome_unmet, max_iterations, end_turn, requires_action, budget_reached, output_missing, output_invalid, run_skipped, run_failed: or session_failed:. Present only when state is finished. type: string reasonMessage: description: >- Short human explanation of the verdict. Present only when state is finished. type: string run: $ref: '#/components/schemas/AutomationRunResultRun' description: The run's own status. session: $ref: '#/components/schemas/AutomationRunResultSession' description: >- A summary of the run's session, once it has one. Read the session for everything else. sessionId: description: >- The session the run started. Absent until the run starts one, and for runs that never do. format: uuid type: string state: description: >- pending: the run has not started its session yet. running: the session is still working. finished: there is nothing left to wait for; read verdict. enum: - pending - running - finished type: string verdict: description: >- How the run ended. Present only when state is finished. passed: the outcome was graded and met. completed: the session finished and nothing graded it. failed: the outcome was graded and not met. needs_attention: the session stopped where only a person can carry it on. cancelled: the session was cancelled. error: the run or session failed, the outcome could not be graded, or the declared result file is missing or not valid JSON. enum: - passed - completed - failed - needs_attention - cancelled - error type: string required: - automationRunId - automationId - state - run - artifacts type: object ManagedAgentsApiErrorInvalidRequest: type: object properties: code: type: string minLength: 1 description: Stable machine-readable error code. enum: - invalid_request message: type: string minLength: 1 description: Human-readable error message. details: $ref: '#/components/schemas/ManagedAgentsApiErrorDetails' description: >- Optional structured error details. Reserved transport fields are typed; code-specific fields remain forward compatible. required: - code - message additionalProperties: false description: Standard flat error response. ManagedAgentsApiErrorUnauthorized: type: object properties: code: type: string minLength: 1 description: Stable machine-readable error code. enum: - unauthorized message: type: string minLength: 1 description: Human-readable error message. details: $ref: '#/components/schemas/ManagedAgentsApiErrorDetails' description: >- Optional structured error details. Reserved transport fields are typed; code-specific fields remain forward compatible. required: - code - message additionalProperties: false description: Standard flat error response. ManagedAgentsApiErrorForbidden: type: object properties: code: type: string minLength: 1 description: Stable machine-readable error code. enum: - forbidden message: type: string minLength: 1 description: Human-readable error message. details: $ref: '#/components/schemas/ManagedAgentsApiErrorDetails' description: >- Optional structured error details. Reserved transport fields are typed; code-specific fields remain forward compatible. required: - code - message additionalProperties: false description: Standard flat error response. ManagedAgentsApiErrorNotFound: type: object properties: code: type: string minLength: 1 description: Stable machine-readable error code. enum: - not_found message: type: string minLength: 1 description: Human-readable error message. details: $ref: '#/components/schemas/ManagedAgentsApiErrorDetails' description: >- Optional structured error details. Reserved transport fields are typed; code-specific fields remain forward compatible. required: - code - message additionalProperties: false description: Standard flat error response. ManagedAgentsApiErrorPayloadTooLarge: type: object properties: code: type: string minLength: 1 description: Stable machine-readable error code. enum: - payload_too_large message: type: string minLength: 1 description: Human-readable error message. details: $ref: '#/components/schemas/ManagedAgentsApiErrorDetails' description: >- Optional structured error details. Reserved transport fields are typed; code-specific fields remain forward compatible. required: - code - message additionalProperties: false description: Standard flat error response. ManagedAgentsApiErrorAutomationRunSessionShared: type: object properties: code: type: string minLength: 1 description: Stable machine-readable error code. enum: - automation_run_session_shared message: type: string minLength: 1 description: Human-readable error message. details: $ref: '#/components/schemas/ManagedAgentsApiErrorDetails' description: >- Optional structured error details. Reserved transport fields are typed; code-specific fields remain forward compatible. required: - code - message additionalProperties: false description: Standard flat error response. ManagedAgentsApiErrorRateLimitExceeded: type: object properties: code: type: string minLength: 1 description: Stable machine-readable error code. enum: - rate_limit_exceeded message: type: string minLength: 1 description: Human-readable error message. details: $ref: '#/components/schemas/ManagedAgentsApiErrorDetails' description: >- Optional structured error details. Reserved transport fields are typed; code-specific fields remain forward compatible. required: - code - message additionalProperties: false description: Standard flat error response. ManagedAgentsApiErrorInternalError: type: object properties: code: type: string minLength: 1 description: Stable machine-readable error code. enum: - internal_error message: type: string minLength: 1 description: Human-readable error message. details: $ref: '#/components/schemas/ManagedAgentsApiErrorDetails' description: >- Optional structured error details. Reserved transport fields are typed; code-specific fields remain forward compatible. required: - code - message additionalProperties: false description: Standard flat error response. ManagedAgentsApiErrorDependencyFailure: type: object properties: code: type: string minLength: 1 description: Stable machine-readable error code. enum: - bad_gateway message: type: string minLength: 1 description: Human-readable error message. details: $ref: '#/components/schemas/ManagedAgentsApiErrorDetails' description: >- Optional structured error details. Reserved transport fields are typed; code-specific fields remain forward compatible. required: - code - message additionalProperties: false description: Standard flat error response. ManagedAgentsApiErrorAutomationRunsUnconfigured: type: object properties: code: type: string minLength: 1 description: Stable machine-readable error code. enum: - automation_runs_unconfigured message: type: string minLength: 1 description: Human-readable error message. details: $ref: '#/components/schemas/ManagedAgentsApiErrorDetails' description: >- Optional structured error details. Reserved transport fields are typed; code-specific fields remain forward compatible. required: - code - message additionalProperties: false description: Standard flat error response. ManagedAgentsApiErrorManagedAgentsUnavailable: type: object properties: code: type: string minLength: 1 description: Stable machine-readable error code. enum: - managed_agents_unavailable message: type: string minLength: 1 description: Human-readable error message. details: $ref: '#/components/schemas/ManagedAgentsApiErrorDetails' description: >- Optional structured error details. Reserved transport fields are typed; code-specific fields remain forward compatible. required: - code - message additionalProperties: false description: Standard flat error response. ManagedAgentsApiErrorServiceUnavailable: type: object properties: code: type: string minLength: 1 description: Stable machine-readable error code. enum: - service_unavailable message: type: string minLength: 1 description: Human-readable error message. details: $ref: '#/components/schemas/ManagedAgentsApiErrorDetails' description: >- Optional structured error details. Reserved transport fields are typed; code-specific fields remain forward compatible. required: - code - message additionalProperties: false description: Standard flat error response. ManagedAgentsApiErrorDependencyTimeout: type: object properties: code: type: string minLength: 1 description: Stable machine-readable error code. enum: - gateway_timeout message: type: string minLength: 1 description: Human-readable error message. details: $ref: '#/components/schemas/ManagedAgentsApiErrorDetails' description: >- Optional structured error details. Reserved transport fields are typed; code-specific fields remain forward compatible. required: - code - message additionalProperties: false description: Standard flat error response. AutomationRunResultArtifact: additionalProperties: false description: A file an automation run's session saved. properties: byteSize: description: Size of the file in bytes. format: int64 minimum: 0 type: integer maximum: 9007199254740991 createdAt: description: When the file was saved. format: date-time type: string downloadable: description: Whether the file's content can be downloaded. type: boolean fileId: description: >- The file; download it with GET /managed-agents/v1/files/{fileId}/content. type: string filename: description: The file's name. type: string mediaType: description: The file's media type. type: string path: description: >- Where the agent saved the file, relative to the session's outputs directory. type: string sha256: description: SHA-256 of the file's contents, for checking a download. type: string required: - fileId - path - filename - mediaType - byteSize - createdAt - downloadable type: object AutomationRunResultFinalMessage: additionalProperties: false description: The last message the agent of an automation run wrote. properties: eventId: description: The session event that holds the whole message. type: string text: description: The text of the agent's last message, cut at 64 KiB. type: string truncated: description: True when text was cut. type: boolean required: - text - truncated - eventId type: object AutomationRunResultOutcome: additionalProperties: false description: The graded outcome of an automation run's session. properties: criteria: description: >- Each criterion's verdict from the newest grading pass, in rubric order. items: $ref: '#/components/schemas/AutomationRunResultCriterion' type: array explanation: description: >- Why the outcome ended: the evaluator's final explanation, or why it could not be graded. type: string iterations: description: Grading passes that reached a verdict. minimum: 0 type: integer maximum: 9007199254740991 status: description: Where the outcome is in grading; terminal once grading finished. enum: - pending - running - evaluating - terminal type: string terminalResult: description: >- The outcome's final result, once terminal. not_applicable means no criterion applied and is not success. enum: - satisfied - max_iterations_reached - not_applicable - not_evaluable - failed type: string required: - status - iterations type: object AutomationRunResultOutput: additionalProperties: false description: The structured JSON result of an automation run. properties: error: description: Why the result could not be used, when valid is false. type: string fileId: description: >- The saved result file. Present when source is file and the file was saved. type: string json: $ref: '#/components/schemas/PlatformSafeJsonValue' description: >- The parsed result: any JSON value other than null, numbers as written. Present exactly when valid is true. path: description: The declared path of the result file. Present when source is file. type: string source: description: >- file: read from the file the automation declares in runDefaults.output. final_message: found in the agent's last message, either the whole message or its last json code block. enum: - file - final_message type: string truncated: description: True when the result file is larger than the 1 MiB that is read. type: boolean valid: description: Whether the result is a single JSON value other than null. type: boolean required: - source - valid type: object AutomationRunResultRun: additionalProperties: false description: The status of an automation run itself, apart from its session. properties: error: $ref: '#/components/schemas/AutomationRunResultRunError' description: >- Why the run could not start its session. Present only when status is failed. status: description: >- pending: not started yet. created: the run started its session. failed: the run could not start its session. skipped: the trigger's AI filter decided the event does not wake the agent. enum: - pending - created - failed - skipped type: string required: - status type: object AutomationRunResultSession: additionalProperties: false description: A summary of the session an automation run started. properties: costUsd: description: >- Billed cost of the session as an exact decimal USD string. Absent when it cannot be read. examples: - '1.234567' type: string createdAt: description: When the session started. format: date-time type: string executionState: description: Where the session's agent loop is. enum: - provisioning - queued - running - idle - completed type: string failure: $ref: '#/components/schemas/AutomationRunResultSessionFailure' description: Why the session failed. Present only when status is failed. lastActivityAt: description: When the session's agent last made progress or changed state. format: date-time type: string status: $ref: '#/components/schemas/SessionStatus' description: The session's status. stopReason: description: Why the agent loop is not running, when it is idle or completed. type: string required: - status - createdAt type: object ManagedAgentsApiErrorDetails: type: object properties: field: description: >- Request field or header responsible for the error, when one can be identified. type: string issues: description: >- Boundary-validation failures as path-prefixed human-readable messages. type: array items: type: string requestId: description: Request correlation identifier for support and log lookup. type: string retryable: description: >- Server advice about failure transience. `true` means transient, `false` means non-transient, and absence gives no advice. Automatic replay is allowed only when this field is not `false` and the operation-specific retry and idempotency contract permits replay. type: boolean additionalProperties: $ref: '#/components/schemas/PlatformSafeJsonValue' description: >- Optional structured error details. Reserved transport fields are typed; code-specific fields remain forward compatible. AutomationRunResultCriterion: additionalProperties: false description: One criterion and the evaluator's verdict on it. properties: criterionId: description: >- Identifier of the criterion, stable across grading passes of the same rubric. type: string criterionKey: description: The criterion's key in the outcome's rubric, when it has one. type: string rationale: description: The evaluator's reasoning for the verdict. type: string text: description: The criterion as written. type: string verdict: description: >- The evaluator's judgment: pass, fail, or not_applicable when the criterion did not apply. type: string required: - criterionId - text - verdict type: object PlatformSafeJsonValue: description: >- A JSON value whose integer members stay within the exact ECMAScript safe-integer range at every nesting level. oneOf: - type: 'null' - type: boolean - type: string - type: integer minimum: -9007199254740991 maximum: 9007199254740991 - type: number not: type: integer - type: array items: $ref: '#/components/schemas/PlatformSafeJsonValue' - additionalProperties: $ref: '#/components/schemas/PlatformSafeJsonValue' type: object AutomationRunResultRunError: additionalProperties: false description: Why an automation run could not start its session. properties: code: description: Stable machine-readable failure code. type: string message: description: Human-readable failure detail. type: string retryable: description: >- Whether running the automation again may succeed without changing it. type: boolean required: - code - message - retryable type: object AutomationRunResultSessionFailure: additionalProperties: false description: Why an automation run's session failed. properties: code: description: Stable machine-readable failure code. type: string message: description: Human-readable failure detail. type: string retryable: description: Whether the same request may succeed on its own if tried again. type: boolean required: - code - message - retryable type: object SessionStatus: description: Coarse session state shared by Managed Agents and imported RL rollouts. enum: - active - awaiting_human - completed - failed - cancelled type: string headers: RecursionOrganizationId: description: Organization id resolved for this request. schema: type: string minLength: 1 RecursionTenantId: description: Tenant id resolved for this request. schema: type: string minLength: 1 securitySchemes: bearerAuth: type: http scheme: bearer description: A Recursion API key, created in the console under API keys. ````