> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tabbly.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Create Agent

> Create a new voice AI agent programmatically

<ApiMethod method="post" path="/create-agent">
  Create a new voice AI agent with specified configuration. The agent can be customized with prompts, voice settings, and conversation flows.
</ApiMethod>

## Request

<ParamField body="organization_id" type="integer" required>
  Your organization ID
</ParamField>

<ParamField body="api_key" type="string" required>
  Your organization API key
</ParamField>

<ParamField body="agent_name" type="string" required>
  Name for the agent
</ParamField>

<ParamField body="agent_description" type="string">
  Description of the agent's purpose
</ParamField>

<ParamField body="base_prompt" type="string" required>
  Base prompt/instructions for the agent's behavior
</ParamField>

<ParamField body="voice_id" type="integer" required>
  ID of the voice to use (from Get Voices endpoint)
</ParamField>

<ParamField body="language" type="string" default="en">
  Primary language code (e.g., "en", "es", "hi")
</ParamField>

<ParamField body="greeting" type="string">
  Custom greeting message
</ParamField>

<ParamField body="conversation_goal" type="string">
  Primary goal of the agent (e.g., "schedule\_appointment", "qualify\_lead")
</ParamField>

## Examples

<CodeGroup>
  ```bash cURL theme={null}
  curl -X POST 'https://www.tabbly.io/dashboard/agents/endpoints/create-agent' \
  -H 'Content-Type: application/json' \
  -d '{
      "organization_id": 244,
      "api_key": "your_api_key",
      "agent_name": "Customer Support Agent",
      "agent_description": "Handles customer support inquiries",
      "base_prompt": "You are a helpful customer support agent...",
      "voice_id": 5,
      "language": "en",
      "greeting": "Hello! How can I help you today?",
      "conversation_goal": "customer_support"
  }'
  ```

  ```python Python theme={null}
  import requests

  data = {
      'organization_id': 244,
      'api_key': 'your_api_key',
      'agent_name': 'Customer Support Agent',
      'agent_description': 'Handles customer support inquiries',
      'base_prompt': 'You are a helpful customer support agent...',
      'voice_id': 5,
      'language': 'en',
      'greeting': 'Hello! How can I help you today?',
      'conversation_goal': 'customer_support'
  }

  response = requests.post(
      'https://www.tabbly.io/dashboard/agents/endpoints/create-agent',
      json=data
  )

  print(response.json())
  ```

  ```javascript Node.js theme={null}
  const axios = require('axios');

  const data = {
      organization_id: 244,
      api_key: 'your_api_key',
      agent_name: 'Customer Support Agent',
      agent_description: 'Handles customer support inquiries',
      base_prompt: 'You are a helpful customer support agent...',
      voice_id: 5,
      language: 'en',
      greeting: 'Hello! How can I help you today?',
      conversation_goal: 'customer_support'
  };

  axios.post('https://www.tabbly.io/dashboard/agents/endpoints/create-agent', data)
      .then(response => console.log(response.data))
      .catch(error => console.error(error));
  ```
</CodeGroup>

## Response

<ResponseField name="success" type="boolean">
  Indicates if the agent was successfully created
</ResponseField>

<ResponseField name="agent_id" type="integer">
  ID of the newly created agent
</ResponseField>

<ResponseField name="agent_name" type="string">
  Name of the created agent
</ResponseField>

<ResponseField name="status" type="string">
  Status of the agent (active, draft)
</ResponseField>

### Success Response (200 OK)

```json theme={null}
{
    "success": true,
    "agent_id": 45,
    "agent_name": "Customer Support Agent",
    "status": "draft"
}
```

## Error Responses

<ResponseField name="400" type="object">
  Missing required fields or invalid parameters
</ResponseField>

<ResponseField name="404" type="object">
  Organization not found or invalid voice\_id
</ResponseField>

<ResponseField name="500" type="object">
  Server error
</ResponseField>