Generate reply

Generates an AI response for a customer message using your assistant. Conversations are automatically created or resumed based on the customer_identifier, making this ideal for integrating AI replies into external platforms, CRMs, or custom messaging interfaces.

This endpoint is rate-limited to 5 requests per minute per API token.

Endpoint

POST /user/ai/generate-reply

Request

integer

required

ID of the assistant to use. Must belong to your account.

string

required

A unique identifier for the customer. Used to maintain conversation context across multiple messages. Examples: phone number, email, CRM contact ID, Facebook user ID. Maximum 255 characters.

string

required

The customer’s message to respond to.

object

Optional context variables to pass to the assistant. Merged with any existing conversation variables.

Response

boolean

Whether the request was successful.

string

UUID of the conversation. Use this to reference the conversation later.

string

The customer identifier provided in the request.

string

The AI-generated response.

array

Functions the assistant executed while processing the message.

Show Function call properties

string

Name of the function called.

object

Arguments passed to the function.

object

Result returned by the function.

boolean

Whether AI responses are disabled for this conversation (e.g., due to manual takeover).

Example

curl -X POST "https://portal.intellixent.ai/api/user/ai/generate-reply" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "assistant_id": 123,
    "customer_identifier": "+14155551234",
    "message": "Hi, I would like to schedule an appointment",
    "variables": {
      "customer_name": "John Smith",
      "source": "whatsapp"
    }
  }'

const response = await fetch('https://portal.intellixent.ai/api/user/ai/generate-reply', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    assistant_id: 123,
    customer_identifier: '+14155551234',
    message: 'Hi, I would like to schedule an appointment',
    variables: {
      customer_name: 'John Smith',
      source: 'whatsapp'
    }
  })
});

const data = await response.json();
console.log(data.reply);

200 Success

{
  "success": true,
  "conversation_id": "7c9e6679-7425-40de-944b-e07fc1f90ae7",
  "customer_identifier": "+14155551234",
  "reply": "Hi John! I'd be happy to help you schedule an appointment. What day and time work best for you?",
  "function_calls": [],
  "ai_disabled": false
}

404 Assistant not found

{
  "success": false,
  "error": "Assistant not found or does not belong to you",
  "error_code": "ASSISTANT_NOT_FOUND"
}

402 Insufficient balance

{
  "success": false,
  "error": "Insufficient balance. Please top up your account.",
  "error_code": "INSUFFICIENT_BALANCE"
}

429 Rate limited

{
  "message": "Too Many Attempts.",
  "retry_after": 60
}

Conversation persistence

Conversations are automatically persisted by assistant_id + customer_identifier:

Same identifier: Messages are added to the existing conversation, maintaining full context.
New identifier: A new conversation is created.
Variables merge: Variables provided in the request are merged with existing conversation variables.

Use consistent identifier formats (e.g., always E.164 format for phone numbers) to ensure conversation continuity across requests.

Overview

Assistants

Calls

Campaigns & Leads

Conversations

Messaging

Phone Numbers

Knowledge & Tools

Webhooks

Endpoint

Request

Response

Example

Conversation persistence

​Endpoint

​Request

​Response

​Example

​Conversation persistence

Endpoint

Request

Response

Example

Conversation persistence