> ## 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. # Test an AI filter on a sample message > Asks the AI filter the given question about a sample message, its text and up to four screenshots, and returns the answer, every answer's probability, and whether the agent would wake. Nothing is saved and no run starts. The model call is billed to the organization like a filter evaluation on a real message. ## OpenAPI ````yaml /recursion/openapi.yaml post /managed-agents/v1/automation-classifier-tests 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-classifier-tests: post: tags: - Automations summary: Test an AI filter on a sample message description: >- Asks the AI filter the given question about a sample message, its text and up to four screenshots, and returns the answer, every answer's probability, and whether the agent would wake. Nothing is saved and no run starts. The model call is billed to the organization like a filter evaluation on a real message. operationId: managedAgentsRunAutomationClassifierTest parameters: - $ref: '#/components/parameters/RecursionTenantId' - $ref: '#/components/parameters/RecursionOrganizationId' requestBody: content: application/json: schema: $ref: '#/components/schemas/AutomationClassifierTestRequest' required: true responses: '200': content: application/json: schema: $ref: '#/components/schemas/AutomationClassifierTestResponse' description: What the AI filter decided for the sample message. headers: recursion-organization-id: $ref: '#/components/headers/RecursionOrganizationId' recursion-tenant-id: $ref: '#/components/headers/RecursionTenantId' '400': description: Bad Request. content: application/json: schema: oneOf: - $ref: '#/components/schemas/ManagedAgentsApiErrorInvalidJson' - $ref: '#/components/schemas/ManagedAgentsApiErrorInvalidRequest' discriminator: propertyName: code mapping: invalid_json: '#/components/schemas/ManagedAgentsApiErrorInvalidJson' invalid_request: '#/components/schemas/ManagedAgentsApiErrorInvalidRequest' x-recursion-error-codes: - invalid_json - 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' '415': description: Unsupported Media Type. content: application/json: schema: $ref: '#/components/schemas/ManagedAgentsApiErrorUnsupportedMediaType' x-recursion-error-codes: - unsupported_media_type 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/ManagedAgentsApiErrorAutomationClassifierUnconfigured - $ref: >- #/components/schemas/ManagedAgentsApiErrorManagedAgentsUnavailable - $ref: >- #/components/schemas/ManagedAgentsApiErrorServiceUnavailable discriminator: propertyName: code mapping: automation_classifier_unconfigured: >- #/components/schemas/ManagedAgentsApiErrorAutomationClassifierUnconfigured managed_agents_unavailable: >- #/components/schemas/ManagedAgentsApiErrorManagedAgentsUnavailable service_unavailable: >- #/components/schemas/ManagedAgentsApiErrorServiceUnavailable x-recursion-error-codes: - automation_classifier_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: AutomationClassifierTestRequest: additionalProperties: false description: >- An AI filter and a sample message to test it on. Nothing is saved and no run starts; the model call is billed like any other. properties: classifier: $ref: '#/components/schemas/AutomationSlackClassifier' description: The AI filter to test, as it would be saved on the trigger. message: $ref: '#/components/schemas/AutomationClassifierTestMessage' description: 'A sample message: its text and up to four screenshots.' required: - classifier - message type: object AutomationClassifierTestResponse: additionalProperties: false description: What the AI filter decided for the sample message. properties: decision: $ref: '#/components/schemas/AutomationDefinitionRunClassifierDecision' description: The filter's decision, as a run would record it. wouldWake: description: >- Whether this message would wake the agent with the filter saved as given. In preview mode the agent always wakes; this says what mode on would do. type: boolean required: - wouldWake - decision type: object ManagedAgentsApiErrorInvalidJson: type: object properties: code: type: string minLength: 1 description: Stable machine-readable error code. enum: - invalid_json 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. 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. ManagedAgentsApiErrorUnsupportedMediaType: type: object properties: code: type: string minLength: 1 description: Stable machine-readable error code. enum: - unsupported_media_type 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. ManagedAgentsApiErrorAutomationClassifierUnconfigured: type: object properties: code: type: string minLength: 1 description: Stable machine-readable error code. enum: - automation_classifier_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. AutomationSlackClassifier: additionalProperties: false description: >- An AI filter: one question about each message, the answers it may give, and when it wakes the agent or skips the message. examples: - answers: - description: A problem, a question, or a request for action. value: active_issue - description: A status update or FYI with no ask. value: informational mode: preview question: Does this message report a problem or ask for help? rule: conditions: - answer: active_issue atLeastPercent: 80 when: wake send: text_and_images properties: answers: description: The answers the model chooses between. items: $ref: '#/components/schemas/AutomationSlackClassifierAnswer' maxItems: 10 minItems: 2 type: array mode: description: >- preview evaluates every message and records what the filter would have done, but always wakes the agent; on applies the rule, waking the agent or skipping the message. enum: - preview - 'on' type: string question: description: The question the model answers about each message. maxLength: 1000 minLength: 1 type: string rule: $ref: '#/components/schemas/AutomationSlackClassifierRule' description: When the filter wakes the agent or skips the message. send: description: >- What the model sees: the message text with its PNG and JPEG attachments, or the text alone. enum: - text_and_images - text type: string required: - mode - question - answers - rule - send type: object AutomationClassifierTestMessage: additionalProperties: false description: A sample message as the filter would see it. properties: images: description: PNG or JPEG screenshots, at most four and 10 MiB together. items: $ref: '#/components/schemas/AutomationClassifierTestImage' maxItems: 4 type: array x-recursion-omission: strategy: absent text: description: The message text, with any forwarded text appended. maxLength: 40000 type: string x-recursion-omission: strategy: absent type: object AutomationDefinitionRunClassifierDecision: additionalProperties: false description: What a trigger's AI filter decided for one run. properties: answer: description: The most likely answer's value, when the model answered. type: string billedAmountNanos: description: >- Billed cost of the classifier call in nano-USD, as an exact base-10 integer string. type: string decidedAt: description: Time the decision was made. format: date-time type: string imageCount: description: Images sent with the text. minimum: 0 type: integer maximum: 9007199254740991 inputTokens: description: Input tokens the provider reported. minimum: 0 type: integer maximum: 9007199254740991 latencyMs: description: Round trip to the model in milliseconds. format: int64 minimum: 0 type: integer maximum: 9007199254740991 matchedAnswer: description: The answer of the condition that held, if one did. type: string mode: description: The filter mode the run was evaluated under. enum: - preview - 'on' type: string model: description: The model that answered. type: string outcome: description: >- skipped: the run was skipped. would_skip: preview mode; on would have skipped it. wake: a wake condition held, or no skip condition did. fail_open: the filter could not decide (error, refusal, timeout, unreadable content), so the agent woke. enum: - skipped - would_skip - wake - fail_open type: string probabilities: additionalProperties: format: double type: number description: Every answer's probability, by value. type: object reason: description: >- Bounded code explaining the outcome when no condition held or the filter could not decide, such as mentions_agent, below_threshold, timeout, refused or content_incomplete. type: string rule: $ref: '#/components/schemas/AutomationSlackClassifierRule' description: The rule the decision applied. Present when the model answered. required: - mode - outcome - imageCount - billedAmountNanos - decidedAt 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: $ref: '#/components/schemas/PlatformSafeJsonValue' description: >- Optional structured error details. Reserved transport fields are typed; code-specific fields remain forward compatible. AutomationSlackClassifierAnswer: additionalProperties: false description: One answer an AI filter may choose. properties: description: description: What this answer means, as the model reads it. maxLength: 500 minLength: 1 type: string value: description: Stable code for this answer, recorded on the run. pattern: ^[a-z0-9_]{1,32}$ type: string required: - value - description type: object AutomationSlackClassifierRule: additionalProperties: false description: >- An AI filter's rule: wake the agent, or skip the message, when any condition holds. properties: conditions: description: >- The conditions, any one of which is enough. Each names a different answer. items: $ref: '#/components/schemas/AutomationSlackClassifierCondition' maxItems: 10 minItems: 1 type: array when: description: >- What the filter does when any condition holds. wake wakes the agent and skips the message otherwise, so a message no condition is sure about is skipped. skip skips the message and wakes the agent otherwise, so such a message wakes the agent. enum: - wake - skip type: string required: - when - conditions type: object AutomationClassifierTestImage: additionalProperties: false description: One screenshot of a sample message. properties: data: description: The image bytes, base64-encoded. minLength: 1 type: string mediaType: description: The image format. enum: - image/png - image/jpeg type: string required: - mediaType - data 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: $ref: '#/components/schemas/PlatformSafeJsonValue' type: object AutomationSlackClassifierCondition: additionalProperties: false description: One condition of an AI filter's rule. properties: answer: description: The answer value the condition looks at. pattern: ^[a-z0-9_]{1,32}$ type: string atLeastPercent: description: >- Holds when the model gives the answer at least this probability, in whole percent from 5 to 95. maximum: 95 minimum: 5 type: integer required: - answer - atLeastPercent type: object 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. ````