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

# Create Agent

## Description

Create a new AI agent.

## Authentication

Required (API key or JWT token)

## Request Body

<ParamField body="name" type="string" required>
  Agent name
</ParamField>

<ParamField body="description" type="string">
  Agent description
</ParamField>

<ParamField body="systemPrompt" type="string">
  System prompt defining agent behavior
</ParamField>

<ParamField body="model" type="string">
  AI model to use (e.g., "gpt-4", "claude-3-opus")
</ParamField>

## Response

<ResponseField name="agent" type="object">
  Created agent object
</ResponseField>

## Example Request

```bash theme={null}
curl -X POST \
  -H "Authorization: Bearer conv_YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Customer Support Bot",
    "description": "Helps customers with support questions",
    "systemPrompt": "You are a helpful support agent...",
    "model": "gpt-4"
  }' \
  https://api.convosphere.site/api/agents
```

## Example Response

```json theme={null}
{
  "agent": {
    "id": "agent_123",
    "name": "Customer Support Bot",
    "description": "Helps customers with support questions",
    "systemPrompt": "You are a helpful support agent...",
    "model": "gpt-4",
    "status": "active",
    "createdAt": "2024-01-15T10:00:00Z"
  }
}
```

## Error Responses

<ResponseField name="403" type="object">
  Agent limit reached for current plan
</ResponseField>