> ## Documentation Index > Fetch the complete documentation index at: https://docs.coreweave.com/llms.txt > Use this file to discover all available pages before exploring further. # Create or replace task Automation > Starts a run from task traffic or an existing dataset. Replacement is rejected after an active run passes collection. ## OpenAPI ````yaml /openapi/model-distillation/management.openapi.yaml put /tasks/{alias}/automation openapi: 3.1.0 info: title: Model Distillation Management API version: 1.0.0 description: | Manage providers, tasks, routing versions, datasets, relabeling, fine-tunes, evaluations, analytics, and closed-loop training Automation. This is the same API used by Model Distillation Studio. servers: - url: https://distillation.training.wandb.ai/v1 description: Production security: - WandbApiKey: [] tags: - name: Providers description: OpenAI-compatible endpoints, credentials, model catalogs, and pricing. - name: Tasks description: Stable task identity and task-level information. - name: Routing description: Versioned model targets, weights, and request parameters. - name: Datasets description: >- Reproducible data snapshots, entries, relabeling, and reusable model outputs. - name: Fine-tunes description: Supervised fine-tuning jobs and hosted model artifacts. - name: Evaluations description: Head-to-head, exact-match, and categorization evaluations. - name: Automation description: Closed-loop dataset, sweep, evaluation, and promotion runs. - name: Analytics description: Task traffic, token, error, and estimated-cost read models. - name: Studio preferences description: Per-task display preferences used by Studio. paths: /tasks/{alias}/automation: parameters: - $ref: '#/components/parameters/WandbEntity' - $ref: '#/components/parameters/TaskAlias' put: tags: - Automation summary: Create or replace task Automation description: >- Starts a run from task traffic or an existing dataset. Replacement is rejected after an active run passes collection. operationId: putAutomation requestBody: required: true content: application/json: schema: type: object properties: teacher: type: string pattern: ^[a-z0-9][a-z0-9_-]{0,63}\/\S+$ dataset: anyOf: - type: object properties: source: type: string const: task task_version: type: integer exclusiveMinimum: 0 maximum: 2147483647 after: 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|([+-](?:[01]\d|2[0-3]):[0-5]\d)))$ before: 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|([+-](?:[01]\d|2[0-3]):[0-5]\d)))$ min_train_examples: type: integer exclusiveMinimum: 0 maximum: 9007199254740991 sampling: type: object properties: strategy: type: string const: random limit: type: integer exclusiveMinimum: 0 maximum: 100000 required: - strategy - limit additionalProperties: false split: type: object properties: val: type: number exclusiveMinimum: 0 exclusiveMaximum: 1 by: type: string const: trace required: - val - by additionalProperties: false relabel: anyOf: - type: object properties: model_ref: type: string pattern: ^[a-z0-9][a-z0-9_-]{0,63}\/\S+$ use_original_output: default: false type: boolean const: false required: - model_ref additionalProperties: false - type: object properties: model_ref: type: string pattern: ^[a-z0-9][a-z0-9_-]{0,63}\/\S+$ use_original_output: type: boolean const: true instructions: default: >- Treat the original output as correct unless it contains a clear, material error. If needed, make the smallest correction while preserving its intent, style, structure, and tool-use decision. type: string minLength: 1 maxLength: 20000 reference_conversation_count: default: 10 type: integer minimum: 0 maximum: 50 required: - model_ref - use_original_output additionalProperties: false publish_to_weave: type: boolean publish_relabel_to_weave: type: boolean required: - source - after - before additionalProperties: false - type: object properties: source: type: string const: existing dataset_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)$ relabel_run_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)$ relabel: anyOf: - type: object properties: model_ref: type: string pattern: ^[a-z0-9][a-z0-9_-]{0,63}\/\S+$ use_original_output: default: false type: boolean const: false required: - model_ref additionalProperties: false - type: object properties: model_ref: type: string pattern: ^[a-z0-9][a-z0-9_-]{0,63}\/\S+$ use_original_output: type: boolean const: true instructions: default: >- Treat the original output as correct unless it contains a clear, material error. If needed, make the smallest correction while preserving its intent, style, structure, and tool-use decision. type: string minLength: 1 maxLength: 20000 reference_conversation_count: default: 10 type: integer minimum: 0 maximum: 50 required: - model_ref - use_original_output additionalProperties: false publish_to_weave: type: boolean publish_relabel_to_weave: type: boolean required: - source - dataset_id additionalProperties: false models: minItems: 1 maxItems: 32 type: array items: type: object properties: model_name: type: string base_model: type: string minLength: 1 model_config: type: object properties: max_examples: type: integer exclusiveMinimum: 0 maximum: 9007199254740991 config: type: object properties: batch_size: anyOf: - type: string const: auto - type: integer exclusiveMinimum: 0 maximum: 9007199254740991 learning_rate: anyOf: - type: number exclusiveMinimum: 0 - type: array minItems: 1 items: type: number minimum: 0 assistant_turns: type: string enum: - all - last metric_logging: type: object propertyNames: type: string additionalProperties: {} additionalProperties: false experimental_config: type: object propertyNames: type: string additionalProperties: {} additionalProperties: false required: - base_model additionalProperties: false eval: type: object properties: spec: type: object properties: type: type: string const: h2h_judge judge_model_ref: type: string pattern: ^[a-z0-9][a-z0-9_-]{0,63}\/\S+$ judge_prompt: type: string minLength: 1 reference_conversation_count: type: integer minimum: 0 maximum: 50 required: - type additionalProperties: false sample_size: type: integer exclusiveMinimum: 0 maximum: 9007199254740991 export_eval: type: boolean additionalProperties: false rollout: type: object properties: task_version: type: integer exclusiveMinimum: 0 maximum: 2147483647 min_win_rate: type: number minimum: 0 maximum: 1 winner_traffic: type: number exclusiveMinimum: 0 maximum: 1 additionalProperties: false required: - dataset - models additionalProperties: false responses: '200': description: Collecting configuration was replaced and a new run started. content: application/json: schema: $ref: '#/components/schemas/Automation' '201': description: Automation was created and its first run started. content: application/json: schema: $ref: '#/components/schemas/Automation' default: $ref: '#/components/responses/Error' components: parameters: WandbEntity: name: Wandb-Entity in: header required: false description: >- Accessible personal or team entity. Omit to use the API key's default entity. schema: type: string TaskAlias: name: alias in: path required: true schema: type: string pattern: ^[a-z0-9-]{1,64}$ schemas: Automation: type: object additionalProperties: true required: - config - revision - started_by - created_at - updated_at properties: config: $ref: '#/components/schemas/JsonObject' revision: type: integer started_by: type: string run: oneOf: - type: object additionalProperties: true properties: id: type: string format: uuid status: type: string enum: - collecting - building_dataset - training - evaluating - promoting - promoted - rejected - failed - cancelled dataset_id: type: - string - 'null' format: uuid eval_id: type: - string - 'null' format: uuid error: type: - string - 'null' - type: 'null' created_at: type: string format: date-time updated_at: type: string format: date-time JsonObject: type: object additionalProperties: true ErrorResponse: type: object required: - error properties: error: type: object required: - message - type properties: message: type: string type: type: string example: error: message: Task 'missing' not found in entity 'your-team' type: not_found responses: Error: description: Request failed. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' securitySchemes: WandbApiKey: type: http scheme: bearer bearerFormat: W&B API key description: A personal or service-account W&B API key. ````