Aicado Agent API Integration
This document explains how to use the call-an-agent endpoint to invoke an Aicado agent via API and get a response based on user input.
📌 Endpoint Information
Method:
POST
URL:
<https://run.aicado.ai/api/1.1/wf/call-an-agent?api_token=access_token>
Content-Type:
application/json
🔑 URL Parameters
access_token
Özel API erişim anahtarı
Final URL format:
<https://run.aicado.ai/api/1.1/wf/call-an-agent?api_token=YOUR_ACCESS_TOKEN>
🧾 Request Body (JSON)
{
"agent_id": "AGENT_ID",
"user_input": "Kullanıcıdan gelen mesaj",
"system_instructions": "Agent için sistem talimatları",
"response_webhook_url": ""
}
Field Descriptions:
agent_id
The unique ID of the agent defined in Aicado. It can be found in the Aicado agent editor.
user_input
Natural language input from the user.
system_instructions
System-level instructions that shape the agent’s behavior and response style. If left empty, the instructions defined in the Aicado Agent Editor will be used.
response_webhook_url
(Optional) The webhook URL where the response will be posted. This is useful when using asynchronous tools. If left empty, the response will be returned directly.
✅ Response Structure
Aicado will return a response in the following structure:
{
"call": {
"call_id": "1749027897108x743874372478867000",
"call_status": "success",
"call_error": null,
"creation_date": 1749027897114,
"completion_date": 1749027897143
},
"tool": {
"tool_status": "",
"tool_name": "",
"tool_error": null
},
"agent": {
"agent_id": "1749023792510x127939515425357090",
"agent_status": "completed",
"agent_output": "{\\"a_points\\": 0, \\"r_points\\": 0, \\"t_points\\": 0, \\"i_points\\": 0, \\"a_report\\": \\"No input provided for analysis.\\", \\"r_report\\": \\"No data to assess for relevance.\\", \\"t_report\\": \\"No testable information supplied.\\", \\"i_report\\": \\"No item to interpret.\\"}"
},
"usage": {
"agent_expense": 0.28734,
"tool_expense": null,
"total_expense": 0.28734
},
"credit": 643.758554,
"error": null
}
⚠️ Security and Tips
Keep your
access_token
secure and never expose it on the client side.Use
system_instructions
to maintain control over the agent's behavior and ensure consistent responses.If you want responses delivered to a webhook, make sure to provide the
response_webhook_url
parameter.
Last updated
Was this helpful?