> ## Documentation Index > Fetch the complete documentation index at: https://docs.avidoai.com/llms.txt > Use this file to discover all available pages before exploring further. # Get a single task by ID > Retrieves detailed information about a specific task. ## OpenAPI ````yaml https://app.stainless.com/api/spec/documented/avido/openapi.documented.yml get /v0/tasks/{id} openapi: 3.1.1 info: title: Avido API description: >- Avido's API for LLM usage events, tool calls, trace management, webhook validation, and more. See each endpoint's request/response schema for details. version: 0.1.0 contact: name: Avido Support email: support@avidoai.com url: https://avidoai.com/support servers: - url: https://api.avidoai.com description: Production API security: - ApiKey: [] ApplicationId: [] paths: /v0/tasks/{id}: get: tags: - Tasks summary: Get a single task by ID description: Retrieves detailed information about a specific task. operationId: getTask parameters: - in: path name: id schema: type: string format: uuid pattern: >- ^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$ description: The unique identifier of the task example: 123e4567-e89b-12d3-a456-426614174000 required: true description: The unique identifier of the task responses: '200': description: Successfully retrieved task content: application/json: schema: $ref: '#/components/schemas/TaskWithMetricsResponse' examples: success: summary: A sample successful single-task response value: task: id: 123e4567-e89b-12d3-a456-426614174000 createdAt: '2024-01-01T00:00:00.000Z' modifiedAt: '2024-01-01T00:00:00.000Z' title: Credit Card Block description: Wants to block their credit card baseline: 0.5 application: id: app_123 title: Support Bot slug: support-bot description: '' context: '' type: CHATBOT environment: DEV createdAt: '2024-01-01T00:00:00.000Z' modifiedAt: '2024-01-01T00:00:00.000Z' topic: id: topic_abc title: Banking Issues baseline: null createdAt: '2024-01-05T12:34:56.789Z' modifiedAt: '2024-01-05T12:34:56.789Z' metadata: customerId: '1' priority: high '400': description: bad request content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '401': description: unauthorized content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '403': description: forbidden content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '404': description: Task not found content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: notFound: summary: Task does not exist value: message: Task not found '422': description: invalid input content: application/json: schema: $ref: '#/components/schemas/ValidationErrorResponse' '500': description: internal server error content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' x-codeSamples: - lang: JavaScript source: >- import Avido from 'avido'; const client = new Avido({ apiKey: process.env['AVIDO_API_KEY'], // This is the default and can be omitted applicationID: process.env['AVIDO_APPLICATION_ID'], // This is the default and can be omitted }); const task = await client.tasks.retrieve('123e4567-e89b-12d3-a456-426614174000'); console.log(task.task); - lang: Python source: |- import os from avido import Avido client = Avido( api_key=os.environ.get("AVIDO_API_KEY"), # This is the default and can be omitted application_id=os.environ.get("AVIDO_APPLICATION_ID"), # This is the default and can be omitted ) task = client.tasks.retrieve( "123e4567-e89b-12d3-a456-426614174000", ) print(task.task) components: schemas: TaskWithMetricsResponse: type: object properties: task: type: object properties: id: type: string format: uuid pattern: >- ^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$ description: The unique identifier of the task example: 123e4567-e89b-12d3-a456-426614174000 createdAt: description: When the task was created example: '2024-01-05T12:34:56.789Z' type: string format: date-time pattern: >- ^(?:(?:\d\d[2468][048]|\d\d[13579][26]|\d\d0[48]|[02468][048]00|[13579][26]00)-02-29|\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\d|30)|(?:02)-(?:0[1-9]|1\d|2[0-8])))T(?:(?:[01]\d|2[0-3]):[0-5]\d(?::[0-5]\d(?:\.\d+)?)?(?:Z))$ modifiedAt: description: When the task was last modified example: '2024-01-05T12:34:56.789Z' type: string format: date-time pattern: >- ^(?:(?:\d\d[2468][048]|\d\d[13579][26]|\d\d0[48]|[02468][048]00|[13579][26]00)-02-29|\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\d|30)|(?:02)-(?:0[1-9]|1\d|2[0-8])))T(?:(?:[01]\d|2[0-3]):[0-5]\d(?::[0-5]\d(?:\.\d+)?)?(?:Z))$ title: type: string description: The title of the task example: Credit Card Block description: type: string description: The task description example: Wants to block their credit card type: type: string enum: - STATIC - NORMAL description: >- The type of task. Normal tasks have a dynamic user prompt, while adversarial tasks have a fixed user prompt. example: NORMAL default: NORMAL status: $ref: '#/components/schemas/TaskStatus' description: >- The status of the task. DEDUCED tasks are created from unmatched traces, DRAFT tasks are user-facing drafts, and ACTIVE tasks are production tasks. default: ACTIVE traceId: description: >- The ID of the trace this task was deduced from (only for DEDUCED tasks) example: 123e4567-e89b-12d3-a456-426614174000 type: string format: uuid pattern: >- ^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$ parentId: description: The ID of the parent task (for DEDUCED tasks linked to a DRAFT) example: 456e7890-e89b-12d3-a456-426614174000 type: string format: uuid pattern: >- ^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$ lastTest: description: The date and time this task was last tested example: '2024-01-01T00:00:00.000Z' type: string format: date-time pattern: >- ^(?:(?:\d\d[2468][048]|\d\d[13579][26]|\d\d0[48]|[02468][048]00|[13579][26]00)-02-29|\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\d|30)|(?:02)-(?:0[1-9]|1\d|2[0-8])))T(?:(?:[01]\d|2[0-3]):[0-5]\d(?::[0-5]\d(?:\.\d+)?)?(?:Z))$ inputExamples: type: array items: type: string description: Example inputs for the task example: - I want to block my credit card metadata: type: object propertyNames: type: string additionalProperties: {} description: >- Optional metadata associated with the task. Returns null when no metadata is stored. example: customerId: '1' priority: high simulatedPromptSchema: description: >- JSON schema that defines the structure for user prompts that should be generated for tests example: type: object properties: intent: type: string urgency: type: string enum: - low - medium - high required: - intent type: object propertyNames: type: string additionalProperties: {} topicId: description: The ID of the topic this task belongs to example: 789e4567-e89b-12d3-a456-426614174000 type: string format: uuid pattern: >- ^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$ isVerified: type: boolean description: Whether the task has been verified example: false passRate: anyOf: - type: number - type: 'null' description: >- Deprecated: use synthetic.passRate instead. The 30 day pass rate for the task measured in percentage (excludes monitoring runs). Null when no tests have been run. example: 66 deprecated: true monitoringPassRate: anyOf: - type: number - type: 'null' description: >- Deprecated: use monitoring.passRate instead. The 30 day pass rate for monitoring runs only, measured in percentage. Null when no monitoring runs exist. example: 80 deprecated: true evalDefinitions: type: array items: type: object properties: evalDefinition: $ref: '#/components/schemas/EvalDefinitionOutput' config: type: object properties: expected: anyOf: - type: string - type: array items: type: string required: - expected additionalProperties: false required: - evalDefinition additionalProperties: false taskSchedule: type: object properties: taskId: type: string format: uuid pattern: >- ^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$ applicationId: type: string format: uuid pattern: >- ^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$ criticality: type: string enum: - LOW - MEDIUM - HIGH cron: type: string nextRunAt: type: string format: date-time pattern: >- ^(?:(?:\d\d[2468][048]|\d\d[13579][26]|\d\d0[48]|[02468][048]00|[13579][26]00)-02-29|\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\d|30)|(?:02)-(?:0[1-9]|1\d|2[0-8])))T(?:(?:[01]\d|2[0-3]):[0-5]\d(?::[0-5]\d(?:\.\d+)?)?(?:Z))$ lastRunAt: type: string format: date-time pattern: >- ^(?:(?:\d\d[2468][048]|\d\d[13579][26]|\d\d0[48]|[02468][048]00|[13579][26]00)-02-29|\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\d|30)|(?:02)-(?:0[1-9]|1\d|2[0-8])))T(?:(?:[01]\d|2[0-3]):[0-5]\d(?::[0-5]\d(?:\.\d+)?)?(?:Z))$ required: - taskId - applicationId - criticality - cron additionalProperties: false title: TaskSchedule description: Task schedule schema synthetic: $ref: '#/components/schemas/TaskMetricsOutput' description: Metrics for synthetic (controlled test) runs. monitoring: $ref: '#/components/schemas/TaskMetricsOutput' description: Metrics for monitoring (production traffic) runs. breakdown: $ref: '#/components/schemas/TaskBreakdownByBucketOutput' description: >- Per-eval-definition breakdown by run-type bucket. Present on detail endpoint only. required: - id - createdAt - modifiedAt - title - description - type - status - inputExamples - metadata - isVerified - passRate - monitoringPassRate - evalDefinitions - synthetic - monitoring additionalProperties: false required: - task additionalProperties: false title: Task With Metrics Response description: Successful response containing the task data with metrics ErrorResponse: type: object properties: message: type: string description: A human-readable error message explaining the error. example: Resource not found required: - message additionalProperties: false title: ErrorResponse description: Standard error format for failed API operations. ValidationErrorResponse: type: object properties: message: type: string description: A human-readable error message indicating what went wrong. example: Invalid request data issues: type: array items: type: object properties: code: type: string message: type: string path: type: array items: type: string required: - code - message - path additionalProperties: false description: Array of detailed validation error objects. example: - code: invalid_string message: Invalid UUID path: - id required: - message - issues additionalProperties: false title: ValidationErrorResponse description: Details about validation errors in incoming requests. TaskStatus: type: string enum: - DEDUCED - DRAFT - ACTIVE - ARCHIVED description: The status of the task example: ACTIVE EvalDefinitionOutput: type: object properties: id: type: string format: uuid pattern: >- ^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$ createdAt: description: When the eval definition was created example: '2024-01-05T12:34:56.789Z' type: string format: date-time pattern: >- ^(?:(?:\d\d[2468][048]|\d\d[13579][26]|\d\d0[48]|[02468][048]00|[13579][26]00)-02-29|\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\d|30)|(?:02)-(?:0[1-9]|1\d|2[0-8])))T(?:(?:[01]\d|2[0-3]):[0-5]\d(?::[0-5]\d(?:\.\d+)?)?(?:Z))$ modifiedAt: description: When the eval definition was last modified example: '2024-01-05T12:34:56.789Z' type: string format: date-time pattern: >- ^(?:(?:\d\d[2468][048]|\d\d[13579][26]|\d\d0[48]|[02468][048]00|[13579][26]00)-02-29|\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\d|30)|(?:02)-(?:0[1-9]|1\d|2[0-8])))T(?:(?:[01]\d|2[0-3]):[0-5]\d(?::[0-5]\d(?:\.\d+)?)?(?:Z))$ type: $ref: '#/components/schemas/EvalType' name: type: string globalConfig: anyOf: - type: object properties: criterion: type: string minLength: 1 description: >- The criterion describes what our evaluation LLM must look for in the response. Remember that the answer to the criterion must be as a pass/fail. required: - criterion additionalProperties: false - oneOf: - $ref: '#/components/schemas/OutputMatchStringConfigOutput' - $ref: '#/components/schemas/OutputMatchListConfigOutput' type: object discriminator: propertyName: type mapping: string: $ref: '#/components/schemas/OutputMatchStringConfigOutput' list: $ref: '#/components/schemas/OutputMatchListConfigOutput' styleGuideId: anyOf: - type: string format: uuid pattern: >- ^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$ - type: 'null' application: anyOf: - $ref: '#/components/schemas/ApplicationOutput' - type: 'null' topics: description: Topic IDs this eval definition is linked to (for topic-scoped evals) example: - 456e4567-e89b-12d3-a456-426614174000 type: array items: type: string format: uuid pattern: >- ^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$ required: - id - createdAt - modifiedAt - type - name additionalProperties: false TaskMetricsOutput: type: object properties: evaluations: type: integer minimum: 0 maximum: 9007199254740991 description: Total number of evaluations in this bucket. example: 247 passed: type: integer minimum: 0 maximum: 9007199254740991 description: Number of evaluations that passed in this bucket. example: 233 tests: type: integer minimum: 0 maximum: 9007199254740991 description: Total number of tests in this bucket. example: 82 testsPassed: type: integer minimum: 0 maximum: 9007199254740991 description: Number of tests that passed in this bucket. example: 78 passRate: anyOf: - type: number minimum: 0 maximum: 100 - type: 'null' description: Pass rate as a percentage (0-100). Null when no tests exist. example: 95.1 confidence: type: object properties: level: $ref: '#/components/schemas/ConfidenceLevel' halfWidth: type: number minimum: 0 maximum: 100 description: >- Half-width of the 95% confidence interval around the pass rate (percentage points). example: 3.4 interval: type: object properties: lower: type: number minimum: 0 maximum: 100 description: Lower bound of the 95% confidence interval (0-100). example: 90.8 upper: type: number minimum: 0 maximum: 100 description: Upper bound of the 95% confidence interval (0-100). example: 97.6 required: - lower - upper additionalProperties: false required: - level - halfWidth - interval additionalProperties: false title: Confidence description: >- Statistical confidence in the pass rate based on a Wilson 95% interval. stability: type: object properties: level: $ref: '#/components/schemas/StabilityLevel' stddev: anyOf: - type: number - type: 'null' description: >- Sample standard deviation of evaluation scores. Null when fewer than 2 evaluations exist. example: 0.08 required: - level - stddev additionalProperties: false title: Stability description: >- Score stability based on the standard deviation of evaluation scores. recommendedAdditionalEvaluations: type: integer minimum: 0 maximum: 9007199254740991 description: Number of additional tests recommended to reach High confidence. example: 0 healthScore: anyOf: - type: number minimum: 0 maximum: 100 - type: 'null' description: >- Overall health score (0-100) combining pass rate (60%), confidence (20%), and stability (20%). Null when confidence is LOW (unreliable measurement with >15pp margin of error). Green: 90-100, Yellow: 60-89, Red: 0-59. example: 87.5 required: - evaluations - passed - tests - testsPassed - passRate - confidence - stability - recommendedAdditionalEvaluations - healthScore additionalProperties: false title: TaskMetrics description: >- Aggregated evaluation metrics for a single run-type bucket (synthetic, monitoring, or combined). TaskBreakdownByBucketOutput: type: object properties: synthetic: type: array items: $ref: '#/components/schemas/EvalDefinitionBreakdownOutput' description: Per-eval-definition breakdown for synthetic (controlled test) runs. monitoring: type: array items: $ref: '#/components/schemas/EvalDefinitionBreakdownOutput' description: >- Per-eval-definition breakdown for monitoring (production traffic) runs. required: - synthetic - monitoring additionalProperties: false title: TaskBreakdownByBucket description: Per-eval-definition metric breakdowns grouped by run-type bucket. EvalType: type: string enum: - NATURALNESS - STYLE - RECALL - CUSTOM - OUTPUT_MATCH OutputMatchStringConfigOutput: type: object properties: type: type: string const: string extract: $ref: '#/components/schemas/OutputMatchExtractConfigOutput' required: - type additionalProperties: false OutputMatchListConfigOutput: type: object properties: type: type: string const: list matchMode: type: string enum: - exact_unordered - contains scoreMetric: type: string enum: - f1 - precision - recall passThreshold: type: number minimum: 0 maximum: 1 extract: $ref: '#/components/schemas/OutputMatchExtractConfigOutput' required: - type - matchMode additionalProperties: false ApplicationOutput: type: object properties: id: type: string format: uuid pattern: >- ^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$ description: Unique identifier of the application example: 123e4567-e89b-12d3-a456-426614174000 orgId: type: string description: Organization ID that owns this application example: org_123456 title: type: string minLength: 1 description: Title of the application example: Customer Support Bot slug: type: string minLength: 1 description: URL-friendly slug for the application example: customer-support-bot description: type: string description: Description of the application example: AI assistant for customer support inquiries context: type: string description: Context/instructions for the application example: You are a helpful customer support assistant... language: default: en description: Language of the application. example: en type: string enum: - da - de - en - es - fr - it - nl - pt - sv type: type: string enum: - CHATBOT - AGENT description: Type of the application. Valid values are CHATBOT or AGENT. example: CHATBOT environment: default: DEV description: Environment of the application. Defaults to DEV. example: DEV type: string enum: - DEV - PROD humanAnnotationEnabled: type: boolean description: Whether human annotation is enabled for this application example: false createdAt: description: When the application was created example: '2024-01-05T12:34:56.789Z' type: string format: date-time pattern: >- ^(?:(?:\d\d[2468][048]|\d\d[13579][26]|\d\d0[48]|[02468][048]00|[13579][26]00)-02-29|\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\d|30)|(?:02)-(?:0[1-9]|1\d|2[0-8])))T(?:(?:[01]\d|2[0-3]):[0-5]\d(?::[0-5]\d(?:\.\d+)?)?(?:Z))$ modifiedAt: description: When the application was last modified example: '2024-01-05T12:34:56.789Z' type: string format: date-time pattern: >- ^(?:(?:\d\d[2468][048]|\d\d[13579][26]|\d\d0[48]|[02468][048]00|[13579][26]00)-02-29|\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\d|30)|(?:02)-(?:0[1-9]|1\d|2[0-8])))T(?:(?:[01]\d|2[0-3]):[0-5]\d(?::[0-5]\d(?:\.\d+)?)?(?:Z))$ required: - id - orgId - title - slug - description - context - language - type - environment - humanAnnotationEnabled - createdAt - modifiedAt additionalProperties: false title: Application description: Application configuration and metadata ConfidenceLevel: type: string enum: - HIGH - MEDIUM - LOW title: ConfidenceLevel description: >- Statistical confidence level based on the width of the 95% confidence interval around the pass rate. example: HIGH StabilityLevel: type: string enum: - HIGH - MEDIUM - LOW title: StabilityLevel description: >- Score stability level based on the standard deviation of evaluation scores. example: HIGH EvalDefinitionBreakdownOutput: type: object properties: evalDefinitionId: type: string format: uuid pattern: >- ^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$ description: ID of the eval definition. example: a0000000-0000-4000-8000-000000000001 evalDefinitionName: type: string description: Display name of the eval definition. example: Accuracy metrics: $ref: '#/components/schemas/TaskMetricsOutput' required: - evalDefinitionId - evalDefinitionName - metrics additionalProperties: false title: EvalDefinitionBreakdown description: >- Evaluation metrics broken down by a single eval definition within a run-type bucket. OutputMatchExtractConfigOutput: type: object properties: pattern: type: string minLength: 1 flags: type: string pattern: ^[gimsuy]*$ group: anyOf: - type: integer minimum: 0 maximum: 9007199254740991 - minItems: 1 type: array items: type: integer minimum: 0 maximum: 9007199254740991 required: - pattern - flags - group additionalProperties: false securitySchemes: ApiKey: type: apiKey in: header name: x-api-key description: Your unique Avido API key ApplicationId: type: apiKey in: header name: x-application-id description: Your unique Avido Application ID ````