> ## 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 Call Outcome > Create a call outcome for an agent. Call outcomes are the end-states a call can be classified into after analysis — "resolved", "escalated", "no answer". Each carries an `outcome_type` of success or failure, which drives the success rate on your dashboards. ## OpenAPI ````yaml https://api.usetuner.ai/public/openapi.json post /api/v1/workspaces/{workspace_id}/agents/{agent_id}/settings/call-outcomes 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/call-outcomes: post: tags: - agent-settings summary: Create Call Outcome description: >- Create a call outcome for an agent. Call outcomes are the end-states a call can be classified into after analysis — "resolved", "escalated", "no answer". Each carries an `outcome_type` of success or failure, which drives the success rate on your dashboards. operationId: >- create_call_outcome_api_v1_workspaces__workspace_id__agents__agent_id__settings_call_outcomes_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/CallOutcomeInput' responses: '201': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/CallOutcomeResponse' '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' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - Bearer: [] components: schemas: CallOutcomeInput: properties: label: type: string maxLength: 200 minLength: 1 title: Label description: Display name for this outcome, shown on call records and dashboards. prompt_definition: type: string minLength: 1 title: Prompt Definition description: 'Instruction the AI uses to decide whether a call ended this way. ' outcome_type: type: string enum: - success - failure title: Outcome Type description: >- Whether this outcome counts as a success or a failure. Drives the success rate on dashboards and alerts. stop_analysis: type: boolean title: Stop Analysis description: >- Skip the remaining analysis steps when a call matches this outcome. Use for outcomes where further grading isn't meaningful, such as a call that never connected. default: false type: object required: - label - prompt_definition - outcome_type title: CallOutcomeInput description: Input schema for call outcome. CallOutcomeResponse: properties: id: type: integer title: Id description: Unique identifier for the call outcome. examples: - 5 label: type: string title: Label description: Display name for this outcome, shown on call records and dashboards. examples: - Resolved ui_description: anyOf: - type: string - type: 'null' title: Ui Description description: Optional longer description of the outcome, shown in the UI. examples: - The caller's issue was fully resolved on this call. prompt_definition: type: string title: Prompt Definition description: Instruction the AI uses to decide whether a call ended this way. examples: - >- The caller confirmed their issue was resolved before ending the call. outcome_type: type: string enum: - success - failure title: Outcome Type description: >- Whether this outcome counts as a success or a failure. Drives the success rate on dashboards and alerts. examples: - success stop_analysis: type: boolean title: Stop Analysis description: >- Skip the remaining analysis steps when a call matches this outcome. Use for outcomes where further grading isn't meaningful, such as a call that never connected. examples: - false type: object required: - id - label - prompt_definition - outcome_type - stop_analysis title: CallOutcomeResponse description: Response schema for call outcome. 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 ````