> ## Documentation Index > Fetch the complete documentation index at: https://penseapp.vercel.app/docs/llms.txt > Use this file to discover all available pages before exploring further. # Bulk create tests > Create many test cases at once and link them to your agents ## OpenAPI ````yaml /api-reference/openapi.json post /tests/bulk openapi: 3.1.0 info: title: Calibrate Public API version: 0.1.0 description: Programmatic API for CI/automation. Pass your key in the `X-API-Key` header. servers: - url: https://api.calibrate.artpark.ai description: Production security: [] paths: /tests/bulk: post: tags: - tests summary: Bulk create tests description: Create many test cases at once and link them to your agents operationId: bulk_upload_tests_tests_bulk_post requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/BulkTestUpload' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/BulkTestUploadResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - ApiKeyAuth: [] components: schemas: BulkTestUpload: properties: type: type: string enum: - response - tool_call - conversation title: Type description: |- What the test judges: - `response`: judges the generated reply - `tool_call`: diffs the generated tool calls - `conversation`: judges the full conversation Applied to every test in the batch tests: items: $ref: '#/components/schemas/BulkTestItem' type: array title: Tests description: >- Test items to create, at most 500 per request, with names unique within the batch agent_uuids: anyOf: - items: type: string type: array - type: 'null' title: Agent Uuids description: IDs of agents to link every created test to. Omit to link none examples: - - a3b2c1d0-e5f4-3210-abcd-ef1234567890 language: anyOf: - type: string - type: 'null' title: Language description: >- Language written to each test's `config.settings.language`. Omit to leave unset type: object required: - type - tests title: BulkTestUpload BulkTestUploadResponse: properties: uuids: items: type: string type: array title: Uuids description: IDs of the created tests, in request order examples: - - b1c2d3e4-f5a6-7890-bcde-f12345678901 count: type: integer title: Count description: Number of tests created message: type: string title: Message description: Confirmation message warnings: anyOf: - items: type: string type: array - type: 'null' title: Warnings description: Non-fatal issues, such as agents some tests could not be linked to type: object required: - uuids - count - message title: BulkTestUploadResponse HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError BulkTestItem: properties: name: type: string title: Name description: Name of the test, unique within the workspace and within the batch conversation_history: items: $ref: '#/components/schemas/ChatMessage' type: array title: Conversation History description: Ordered messages ending at the user turn the agent should answer evaluators: anyOf: - items: $ref: '#/components/schemas/routers__tests__EvaluatorRef' type: array - type: 'null' title: Evaluators description: Evaluators to link. Used by `response` and `conversation` tests tool_calls: anyOf: - items: $ref: '#/components/schemas/ExpectedToolCall' type: array - type: 'null' title: Tool Calls description: Expected tool calls. **Required for `tool_call` batches** type: object required: - name - conversation_history title: BulkTestItem ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type type: object required: - loc - msg - type title: ValidationError ChatMessage: properties: role: type: string enum: - user - assistant - tool title: Role description: Message author role in the conversation history content: anyOf: - type: string - type: 'null' title: Content description: >- Message text. Omit for assistant messages that only carry `tool_calls` tool_calls: anyOf: - items: additionalProperties: true type: object type: array - type: 'null' description: Tool calls issued by the assistant. Omit for plain text turns tool_call_id: anyOf: - type: string - type: 'null' title: Tool Call Id description: >- ID of the tool call this message responds to. **Required for `role=tool`** name: anyOf: - type: string - type: 'null' title: Name description: Tool name for `role=tool` messages. Omit otherwise type: object required: - role title: ChatMessage routers__tests__EvaluatorRef: properties: evaluator_uuid: type: string maxLength: 36 minLength: 36 title: Evaluator Uuid description: Evaluator to attach to the test examples: - f47ac10b-58cc-4372-a567-0e02b2c3d479 variable_values: anyOf: - additionalProperties: true type: object - type: 'null' description: >- Values for the evaluator's `{{placeholder}}` variables, pinned on this test. Omit to inherit the evaluator version's defaults examples: - criteria: The reply must cite the refund window additionalProperties: false type: object required: - evaluator_uuid title: EvaluatorRef ExpectedToolCall: properties: tool: type: string title: Tool description: Name of the tool the agent is expected to call arguments: anyOf: - additionalProperties: true type: object - type: 'null' description: >- Expected argument values, diffed against the generated call. Omit to expect no arguments accept_any_arguments: type: boolean title: Accept Any Arguments description: >- When `true`, only the tool name must match and `arguments` is ignored default: false type: object required: - tool title: ExpectedToolCall securitySchemes: ApiKeyAuth: type: apiKey in: header name: X-API-Key description: API key for authentication ````