Agents
Create Agent Endpoint
Create new AI agent
POST
/
api
/
v3
/
agents
/
create
/
Copy
curl --request POST \
--url https://api.nugen.in/api/v3/agents/create/ \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"agent_name": "<string>",
"agent_description": "<string>",
"model": "<string>",
"temperature": 0.7,
"instructions": "<string>",
"demonstrations": [
{}
]
}'
Copy
{
"data": {
"id": "<string>",
"name": "<string>",
"description": "<string>",
"baseModel": "<string>",
"baseModelName": "<string>",
"createdDate": "<string>",
"status": "<string>",
"creator": "<string>",
"endpoint": "<string>",
"usageCount": 123,
"lastUsed": "<string>",
"performanceMetrics": {
"averageUncertainty": 123,
"humanInterventions": 123,
"averageResponseTime": 123,
"userSatisfactionScore": 123
},
"systemPrompt": "<string>",
"uncertaintyThreshold": 123
}
}
Authorizations
Bearer authentication header of the form Bearer <token>
, where <token>
is your auth token.
Body
application/json
Request model for creating a new agent - matches frontend exactly
Response
200
application/json
Successful Response
Response model for agent creation endpoint.
Was this page helpful?
Copy
curl --request POST \
--url https://api.nugen.in/api/v3/agents/create/ \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"agent_name": "<string>",
"agent_description": "<string>",
"model": "<string>",
"temperature": 0.7,
"instructions": "<string>",
"demonstrations": [
{}
]
}'
Copy
{
"data": {
"id": "<string>",
"name": "<string>",
"description": "<string>",
"baseModel": "<string>",
"baseModelName": "<string>",
"createdDate": "<string>",
"status": "<string>",
"creator": "<string>",
"endpoint": "<string>",
"usageCount": 123,
"lastUsed": "<string>",
"performanceMetrics": {
"averageUncertainty": 123,
"humanInterventions": 123,
"averageResponseTime": 123,
"userSatisfactionScore": 123
},
"systemPrompt": "<string>",
"uncertaintyThreshold": 123
}
}
Assistant
Responses are generated using AI and may contain mistakes.