Update agent configuration settings.
This endpoint allows partial updates to an agent’s configuration. You can update any combination of settings including name, description, model, temperature, instructions, and demonstrations. Only the fields provided in the request body will be updated.
Path Parameters:
agent_id: Unique identifier of the agent to updateRequest Body:
The request accepts a partial update with any of the following optional fields:
agent_name: New name for the agentagent_description: Updated description of the agent’s purposemodel: Base model to use (must be from available models list)temperature: Sampling temperature (0.0 to 1.0)max_token: Maximum tokens in responseinstructions: System instructions for the agentdemonstrations: Example conversations for few-shot learningReturns:
data: Updated agent object with all current configurationRaises:
404: If agent not found or doesn’t belong to user400: If invalid model specified or validation failsExample Request:
PATCH /api/v3/agents/agent-123
Headers: {"Authorization": "Bearer <api_key>"}
Body: {
"agent_name": "updated_support_bot",
"agent_description": "Enhanced customer support assistant",
"temperature": 0.7,
"instructions": "You are a helpful customer support agent. Always be polite and professional."
}
Example Response:
{
"data": {
"id": "agent-123",
"name": "updated_support_bot",
"description": "Enhanced customer support assistant",
"base_model": "nugen-flash-instruct",
"temperature": 0.7,
"instructions": "You are a helpful customer support agent. Always be polite and professional.",
"demonstrations": [],
"status": "Active",
"created_date": "2024-01-15T10:30:00Z",
"updated_date": "2024-02-25T14:20:00Z",
"endpoint": "https://api.nugen.in/api/v3/agents/run-agents/updated_support_bot/run",
"usage_count": 42,
"last_used": "2024-01-20T15:45:00Z"
}
}
Notes:
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Name of the agent
"Customer Support Agent"
Description of the agent
"An agent designed to handle customer support queries"
Base model identifier
"nugen-flash-instruct"
max token for inference request
1000
Temperature for model responses
0.7
System prompt for the agent
"You are a helpful customer support assistant."
Training demonstrations
Returns the updated details of the agent after applying the requested configuration changes