Real-time monitoring

​

Turn it on

1. Open the agent, then Settings → Advanced.
2. In the Monitoring card, turn on Monitoring.
3. Under Events, choose what a monitor receives.
4. Choose Save.

​

Connect

wss://app.cntillion.com/api/v2/agents/{agent_id}/conversations/{conversation_id}/monitor

import WebSocket from "ws";

const socket = new WebSocket(
  `wss://app.cntillion.com/api/v2/agents/${agentId}/conversations/${conversationId}/monitor`,
  { headers: { "X-API-Key": process.env.CENTILLION_API_KEY } }
);

socket.on("message", (data) => {
  const event = JSON.parse(data);
  console.log(event.event_id, event.type);
});

import asyncio
import json
import os

import websockets


async def monitor(agent_id, conversation_id):
    url = (
        "wss://app.cntillion.com/api/v2/agents/"
        f"{agent_id}/conversations/{conversation_id}/monitor"
    )
    headers = {"X-API-Key": os.environ["CENTILLION_API_KEY"]}
    async with websockets.connect(url, additional_headers=headers) as socket:
        async for message in socket:
            event = json.loads(message)
            print(event["event_id"], event["type"])

​

Find a conversation

curl 'https://app.cntillion.com/api/v2/agents/YOUR_AGENT_ID/conversations?monitorable=true' \
  -H "Authorization: Bearer $CENTILLION_API_KEY"

​

Events

{
  "type": "user_transcript",
  "event_id": 12,
  "conversation_id": "conversation-id",
  "timestamp": "2026-10-31T12:00:00.000Z",
  "user_transcription_event": { "user_transcript": "Where is my order?" }
}

• On a step that can take a sensitive value, you get the events but not the words: user_transcript, agent_response, corrections and full tool results read •••, and tool arguments are empty. This covers every Collect step, a keypad step, and a step whose way out stores a sensitive value, for as long as the conversation is on that step. The conversation’s stored transcript keeps its usual text.
• Every other step is sent as usual, with stored values masked wherever they appear. In a chat, the customer’s message reaches you with the agent’s reply, and a turn that stores a value shows ••• for that turn.

​

Control commands

​

End the conversation

{ "command_type": "end_call" }

​

Transfer to a phone number

{
  "command_type": "transfer_to_number",
  "parameters": { "phone_number": "+15551234567" }
}

​

Add context

{
  "command_type": "contextual_update",
  "parameters": { "contextual_update": "This customer is on the Premium plan." }
}

​

Take over a chat

{ "command_type": "enable_human_takeover" }

​

Send a message as a person

{
  "command_type": "send_human_message",
  "parameters": { "text": "Hi, this is Sam. How can I help?" }
}

​

Give the chat back to the AI

{ "command_type": "disable_human_takeover" }

​

Results

{
  "type": "command_result",
  "event_id": 31,
  "conversation_id": "conversation-id",
  "timestamp": "2026-10-31T12:00:00.000Z",
  "command_result_event": {
    "command_id": "my-id",
    "command_type": "transfer_to_number",
    "status": "failed",
    "code": "transfer_failed"
  }
}

​

Staying connected

wss://app.cntillion.com/api/v2/agents/{agent_id}/conversations/{conversation_id}/monitor?after=42

​

Limits

• About the last 100 events of a conversation are available. Earlier ones are gone for a monitor, though the stored conversation keeps its messages.
• Each conversation takes 10 connections, and each key 50.
• Each connection takes 20 commands in 10 seconds, and connecting counts toward the key’s rate limit.
• A conversation must already be in progress on an agent with monitoring on. You cannot connect before it starts or after it ends.
• Events carry text and metadata, never audio.