> ## Documentation Index > Fetch the complete documentation index at: https://docs.usetuner.ai/llms.txt > Use this file to discover all available pages before exploring further. # Create Eval > Create an eval for an agent. Evals are the criteria used to grade calls after analysis. `scoring_type` is either `PASS_FAIL` for a boolean check or `SCORE_1_5` for a rating, and `rule_logic` describes what to evaluate. An agent needs at least one `PASS_FAIL` eval before it can run simulations. ## OpenAPI ````yaml https://api.usetuner.ai/public/openapi.json post /api/v1/workspaces/{workspace_id}/agents/{agent_id}/settings/evals openapi: 3.1.0 info: title: My Public API version: 1.0.0 servers: - url: https://api.usetuner.ai security: [] tags: - name: calls x-group: Calls - name: workspaces x-group: Workspaces - name: agent-settings x-group: Agent Settings - name: agents x-group: Agents - name: simulation x-group: Simulation - name: providers x-group: Providers paths: /api/v1/workspaces/{workspace_id}/agents/{agent_id}/settings/evals: post: tags: - agent-settings summary: Create Eval description: >- Create an eval for an agent. Evals are the criteria used to grade calls after analysis. `scoring_type` is either `PASS_FAIL` for a boolean check or `SCORE_1_5` for a rating, and `rule_logic` describes what to evaluate. An agent needs at least one `PASS_FAIL` eval before it can run simulations. operationId: >- create_eval_api_v1_workspaces__workspace_id__agents__agent_id__settings_evals_post parameters: - name: agent_id in: path required: true schema: type: integer description: Tuner's internal numeric ID for the agent. title: Agent Id description: Tuner's internal numeric ID for the agent. - name: workspace_id in: path required: true schema: type: integer description: Workspace ID. Find this in Workspace > General Settings. title: Workspace Id description: Workspace ID. Find this in Workspace > General Settings. requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/EvalInput' responses: '201': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/EvalResponse' '401': description: Missing or invalid API key. content: application/json: example: detail: Not authenticated schema: $ref: '#/components/schemas/ErrorResponse' '403': description: You do not have access to this workspace. content: application/json: example: detail: User does not have access to workspace 42 schema: $ref: '#/components/schemas/ErrorResponse' '404': description: Agent not found. content: application/json: example: detail: Agent with ID 17 not found schema: $ref: '#/components/schemas/ErrorResponse' '409': description: An eval with this name already exists for the agent. content: application/json: example: detail: >- Eval with name 'Verified caller identity' already exists for this agent schema: $ref: '#/components/schemas/ErrorResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - Bearer: [] components: schemas: EvalInput: properties: name: type: string maxLength: 200 minLength: 1 title: Name scoring_type: type: string pattern: ^(PASS_FAIL|SCORE_1_5)$ title: Scoring Type description: >- `PASS_FAIL` for a yes/no check, `SCORE_1_5` for a 1–5 rating. Simulations require at least one `PASS_FAIL` eval. rule_logic: type: string minLength: 1 title: Rule Logic description: >- Instruction the AI applies to each call. For `PASS_FAIL`, phrase it so that passing is unambiguous. order: anyOf: - type: integer minimum: 0 - type: 'null' title: Order inputs_used: items: type: string type: array title: Inputs Used type: object required: - name - scoring_type - rule_logic title: EvalInput description: Input schema for creating/updating an eval. EvalResponse: properties: id: type: integer title: Id description: Unique identifier for the eval. examples: - 12 name: type: string title: Name description: Name of the eval. examples: - Verified caller identity scoring_type: type: string enum: - PASS_FAIL - SCORE_1_5 title: Scoring Type description: >- `PASS_FAIL` for a yes/no check, `SCORE_1_5` for a 1–5 rating. Simulations require at least one `PASS_FAIL` eval. examples: - PASS_FAIL rule_logic: type: string title: Rule Logic description: >- Instruction the AI applies to each call. For `PASS_FAIL`, phrasing is written so that passing is unambiguous. examples: - The agent confirmed the caller's name and date of birth. is_system_added: type: boolean title: Is System Added description: >- Whether this eval was added automatically as a system default rather than created by a user. examples: - false is_removable: type: boolean title: Is Removable description: >- Whether this eval can be deleted. System defaults may be marked non-removable; attempting to delete a non-removable eval returns a 403. examples: - true order: type: integer title: Order description: Display order relative to other evals for the agent. examples: - 0 inputs_used: items: type: string type: array title: Inputs Used description: >- The inputs the AI considers when evaluating this eval, e.g. "system_prompt", "tools", "allowed_capabilities", "workflow", or "metadata." for a specific metadata field. examples: - - system_prompt - tools type: object required: - id - name - scoring_type - rule_logic - is_system_added - is_removable - order - inputs_used title: EvalResponse description: Response schema for an eval. ErrorResponse: properties: detail: type: string title: Detail description: Human-readable description of what went wrong. type: object required: - detail title: ErrorResponse description: Error body returned when a request fails. HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type input: title: Input ctx: type: object title: Context type: object required: - loc - msg - type title: ValidationError securitySchemes: Bearer: type: http description: >- Use Tuner API key (tr_api_...) or user session token. Find your API key in Workspace Settings > API Keys. scheme: bearer ````