Create Agent

Create Agent allows you to create a new AI chatbot agent inside a specific project.

This endpoint is used when you want to programmatically create a chatbot that can later be configured, trained with knowledge sources, embedded into a website, connected with WhatsApp, or used through the chat APIs.

The created agent can be used for customer support, lead capture, booking flows, internal knowledge assistants, website chat widgets, and other conversational AI use cases.

Endpoint

Path Parameters

Field	Type	Required	Description
`projectId`	integer	Yes	Unique identifier of the project where the chatbot agent should be created.

Request Body

{
  "name": "Customer Support Bot",
  "description": "AI chatbot for answering customer support questions.",
  "type": 2,
  "access_type": 0,
  "avatar_url": "https://example.com/assets/support-bot.png",
  "llm_source": 0,
  "language": "en"
}

Request Parameters

Field	Type	Required	Description
`name`	string	Yes	Name of the chatbot agent. This is used to identify the agent inside the project.
`description`	string	No	Short description of the chatbot agent and its purpose.
`type`	integer	No	Type of agent to create. Use the value supported by your Robofy configuration.
`access_type`	integer	No	Access level of the chatbot agent. Use the value supported by your Robofy configuration.
`avatar_url`	string	No	Public URL of the image used as the chatbot avatar.
`llm_source`	integer	No	LLM source or provider used by the chatbot. Use the value supported by your Robofy configuration.
`language`	string	Yes	Default language for the chatbot. Example: `en`.

Success Response

{
  "message": "Chatbot created successfully",
  "data": "agent_12345"
}

Response Fields

Field	Type	Description
`message`	string	Status message describing the result of the request.
`data`	string	Unique identifier of the newly created chatbot agent.

Error Responses

400 Bad Request

Returned when the request body is invalid or required fields are missing.

{
  "message": "Bad Request",
  "error": {
    "code": "BAD_REQUEST",
    "detail": "Invalid request body or missing required fields."
  }
}

401 Unauthorized

Returned when the request does not include a valid bearer token.

{
  "message": "Unauthorized",
  "error": {
    "code": "UNAUTHORIZED",
    "detail": "Authentication token is missing or invalid."
  }
}

403 Forbidden

Returned when the authenticated user does not have permission to create an agent in the specified project.

{
  "message": "Forbidden",
  "error": {
    "code": "FORBIDDEN",
    "detail": "You do not have permission to access this project."
  }
}

404 Not Found

Returned when the specified project does not exist.

{
  "message": "Not Found",
  "error": {
    "code": "PROJECT_NOT_FOUND",
    "detail": "Project not found."
  }
}

500 Internal Server Error

Returned when an unexpected server error occurs.

{
  "message": "Internal Server Error",
  "error": {
    "code": "INTERNAL_SERVER_ERROR",
    "detail": "Something went wrong. Please try again later."
  }
}

Notes

The projectId must belong to an existing project that the authenticated user can access.

The name field is required and should clearly describe the chatbot’s purpose.

The avatar_url should be a valid public image URL if the chatbot avatar needs to be displayed in a widget or external interface.

After the chatbot is created, you can use the returned data value as the chatbot ID in other APIs such as Retrieve Agent, Add Website, List Linked Assets, Send Message, and Send WhatsApp Message.

Provide your bearer token in the

Authorization

header when making requests to protected resources.

Example:

Authorization: Bearer ********************

curl --location 'https://agents.robofy.ai/v1/ai-agent/chatbot/' \ --header 'Authorization: Bearer <token>' \ --header 'Content-Type: application/json' \ --data '{ "name": "string", "description": "string", "type": 0, "access_type": 0, "avatar_url": "string", "llm_source": 0, "language": "string" }'

Endpoint#

Path Parameters#

Request Body#

Request Parameters#

Success Response#

Response Fields#

Error Responses#

400 Bad Request#

401 Unauthorized#

403 Forbidden#

404 Not Found#

500 Internal Server Error#

Notes#

Request

Responses