> ## 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. # Create agent > Create an agent to test inside Calibrate or connect your existing agent to Calibrate ## OpenAPI ````yaml /api-reference/openapi.json post /agents 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: /agents: post: tags: - agents summary: Create agent description: >- Create an agent to test inside Calibrate or connect your existing agent to Calibrate operationId: create_agent_endpoint_agents_post requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/AgentCreate' examples: agent_within_calibrate: summary: Agent within Calibrate description: >- Build a voice/chat agent inside Calibrate. This config is the managed defaults spelled out. Override only the keys you want to change; omitted keys still inherit the defaults. value: name: Support Agent type: agent config: system_prompt: You are a helpful assistant. llm: model: google/gemini-2.5-flash stt: provider: google tts: provider: google settings: agent_speaks_first: false max_assistant_turns: 10 openai_compatible_connection: summary: Connect OpenAI-compatible agent description: >- Connect your own agent over an OpenAI-compatible HTTP endpoint. `config.agent_url` is required; `agent_headers` carries the auth token the endpoint expects. value: name: My Hosted Agent type: connection config: agent_url: https://api.example.com/v1/chat/completions agent_headers: Authorization: Bearer benchmark_provider: openrouter responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/AgentCreateResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - ApiKeyAuth: [] x-codeSamples: - lang: curl label: Agent within Calibrate source: |- curl --request POST \ --url https://api.calibrate.artpark.ai/agents \ --header 'Content-Type: application/json' \ --header 'X-API-Key: ' \ --data '{ "name": "Support Agent", "type": "agent", "config": { "system_prompt": "You are a helpful assistant.", "llm": { "model": "google/gemini-2.5-flash" }, "stt": { "provider": "google" }, "tts": { "provider": "google" }, "settings": { "agent_speaks_first": false, "max_assistant_turns": 10 } } }' - lang: curl label: Connect OpenAI-compatible agent source: |- curl --request POST \ --url https://api.calibrate.artpark.ai/agents \ --header 'Content-Type: application/json' \ --header 'X-API-Key: ' \ --data '{ "name": "My Hosted Agent", "type": "connection", "config": { "agent_url": "https://api.example.com/v1/chat/completions", "agent_headers": { "Authorization": "Bearer " }, "benchmark_provider": "openrouter" } }' components: schemas: AgentCreate: properties: name: type: string title: Name description: Agent name, unique within the workspace type: type: string enum: - agent - connection title: Type description: |- - `agent`: built inside Calibrate - `connection`: your existing agent connected to Calibrate default: agent config: anyOf: - additionalProperties: true type: object - type: 'null' description: >- Agent behavioral config. The keys depend on `type`. **`type=agent`**, built inside Calibrate: - `system_prompt`: the agent's instructions - `llm.model`: `provider/model`, e.g. `openai/gpt-4.1` or `google/gemini-2.5-flash` - `stt.provider`: `deepgram`, `openai`, `cartesia`, `elevenlabs`, `google`, `sarvam`, or `smallest` - `tts.provider`: `cartesia`, `openai`, `google`, `elevenlabs`, `sarvam`, or `smallest` - `settings.agent_speaks_first`, `settings.max_assistant_turns` - `system_tools.end_call`: let the agent end the call - `data_extraction_fields`: `[{name, type, description, required}]` ```json { "system_prompt": "You are a helpful support agent.", "llm": {"model": "openai/gpt-4.1"}, "stt": {"provider": "deepgram"}, "tts": {"provider": "elevenlabs"}, "settings": {"agent_speaks_first": true, "max_assistant_turns": 50} } ``` **`type=connection`**, your own HTTP endpoint: - `agent_url`: public HTTP(S) endpoint your agent is called at - `agent_headers`: headers sent on each request, e.g. auth - `benchmark_provider`: `openrouter` by default. Other values: `openai`, `google`, `anthropic`, `meta-llama`, `mistralai`, `deepseek`, `x-ai`, `cohere`, `qwen`, or `ai21` ```json { "agent_url": "https://api.example.com/agent", "agent_headers": {"Authorization": "Bearer "}, "benchmark_provider": "openrouter" } ``` For `type=agent`, omitted keys inherit managed defaults. Omit `config` entirely to use all defaults. For `type=connection`, `config` is stored as-is and must contain `agent_url` type: object required: - name title: AgentCreate AgentCreateResponse: properties: uuid: type: string maxLength: 36 minLength: 36 title: Uuid description: ID of the newly created agent examples: - f47ac10b-58cc-4372-a567-0e02b2c3d479 message: type: string title: Message description: Confirmation message type: object required: - uuid - message title: AgentCreateResponse 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 type: object required: - loc - msg - type title: ValidationError securitySchemes: ApiKeyAuth: type: apiKey in: header name: X-API-Key description: API key for authentication ````