The Questions feature helps you find explicit questions or requests for information that come up during the conversation. Whether answered or not, all questions are recognized. You can extract questions from a conversation using the Conversations API.

Example questions extracted from a conversation:

  • “What features are most relevant for our use case?”
  • “How are we planning to design the systems?”

Some features of the Questions feature:

  • Recognizes questions directed to someone, such as "Does Ken know more about this issue?"
  • Recognizes implicit questions, such as "do you think" or "would you rather" with no person mentioned.
  • Recognizes questions that are actionable in nature, such as "Should Ken resolve this customer issue?"
  • Ignores chit-chat and casual small talk which may include questions but are not part of the larger conversation.


This request requires an access token, as described in Authenticate.

Get questions

This section describes how to get questions from a conversation. This request requires a conversation ID. You receive a conversation ID when you process a conversation with the APIs.

To get questions, use the GET <><CONVERSATION_ID>/questions operation:


Try our interactive examples!

We provide interactive versions of these code samples: curl, Node.js, Python

To get started with our code samples, see Set Up Your Test Environment.


curl --request GET \
  --url "$CONVERSATION_ID/questions" \
  --header "Authorization: Bearer $ACCESS_TOKEN" \
  --header "Content-Type: application/json"
import fetch from 'node-fetch';

const accessToken = '<ACCESS_TOKEN>';
const conversationId = '<CONVERSATION_ID>';

const fetchResponse = await fetch(`${conversationId}/questions`, {
  method: 'get',
  headers: {
    'Authorization': `Bearer ${accessToken}`,
    'Content-Type': 'application/json'

const responseBody = await fetchResponse.json();

console.log(JSON.stringify(responseBody, null, 2));
import json
import requests

access_token = "<ACCESS_TOKEN>"
conversation_id = "<CONVERSATION_ID>"

headers = {
  "Authorization": "Bearer " + access_token,
  "Content-Type": "application/json"

response = requests.request(
  url="" + conversation_id + "/questions",

print(json.dumps(response.json(), indent=2))


For additional reference information, see Retrieve questions by conversation ID.

Example response

  "questions": [
      "id": "6436599888871424",
      "text": "Could you let me know what time works for you?",
      "type": "question",
      "score": 0.994485148696813,
      "messageIds": [
      "from": {}
      "id": "6719329281245184",
      "text": "How may I help you today?",
      "type": "question",
      "score": 0.9834683553122807,
      "messageIds": [
      "from": {}