{"id":1120800,"date":"2026-10-15T20:30:00","date_gmt":"2026-10-16T03:30:00","guid":{"rendered":"https:\/\/www.questionpro.com\/blog\/?p=1120800"},"modified":"2026-10-15T01:16:33","modified_gmt":"2026-10-15T08:16:33","slug":"ai-probing-in-surveys","status":"publish","type":"post","link":"https:\/\/www.questionpro.com\/blog\/ai-probing-in-surveys\/","title":{"rendered":"\u201cFine\u201d is not an answer: How Moderated Chat gets survey respondents to tell you"},"content":{"rendered":"\n

Your survey already knows what people chose. Now it can ask them why, one short conversation at a time. Your survey already knows what people chose. Now it can ask them why through AI probing in surveys, one short conversation at a time.<\/em><\/p>\n\n\n\n\n\n

Quick game: guess the reason behind the 6<\/strong><\/h2>\n\n\n\n

Here\u2019s a row you\u2019ve probably seen a hundred times.<\/p>\n\n\n\n

A customer rated you 6 out of 10. In the comment box underneath, they typed one word: \u201cfine.\u201d<\/p>\n\n\n\n

Now guess why. Pick one:<\/p>\n\n\n\n

    \n
  1. Delivery took longer than promised.<\/li>\n\n\n\n
  2. The price went up last month.<\/li>\n\n\n\n
  3. A competitor\u2019s ad caught their eye.<\/li>\n\n\n\n
  4. Nothing is wrong. They just never give anyone a 9.<\/li>\n<\/ol>\n\n\n\n

    Trick question. You can\u2019t know. Neither can the analyst building the deck. The score tells you what happened. The comment box was supposed to explain why, but it gave you a shrug.<\/p>\n\n\n\n

    That\u2019s what usually happens when you ask \u201cwhy\u201d in a text box with nobody on the other side. And \u201cfine\u201d can\u2019t be clarified because no one is there to ask, \u201cFine compared to what?\u201d<\/p>\n\n\n\n

    Moderated chat puts someone there. It\u2019s a question type in QuestionPro that adds a short, AI-led text interview to your survey. You pick the moment and decide what you want to learn. Powered by QuestionPro AI, it asks the follow-up a good moderator would ask of every respondent who reaches the question.<\/p>\n\n\n\n

    So you stop guessing at the reason. You read it.<\/p>\n\n\n\n

    Learn More:<\/strong> Explore the moderated chat question type<\/a><\/p>\n\n\n\n

    What is moderated chat?<\/strong><\/h2>\n\n\n\n

    Moderated chat is a question type in QuestionPro surveys that runs a short, AI-led text interview. Place it right after a question you want to understand better, or anywhere you want to open a conversation. When the chat ends, the respondent carries on with the rest of your survey.<\/p>\n\n\n\n

    You\u2019ll find it in the survey editor under the advanced question types, inside the interview question type. Chat is the first format of that question type, with voice and video planned for upcoming releases.<\/p>\n\n\n\n

    It isn\u2019t a bigger comment box. A comment box waits for whatever the respondent types, while moderated chat reads the reply and asks a follow-up when it\u2019s vague. It isn\u2019t a script either. You write the goal, not every question. And it isn\u2019t a separate study. The conversation happens inside the survey your respondent is already taking.<\/p>\n\n\n\n

    Short answers aren\u2019t your respondents\u2019 fault<\/strong><\/h2>\n\n\n\n

    Mostly, they\u2019re doing exactly what the survey asked. A text box doesn\u2019t say what a good answer looks like, and it doesn\u2019t react when the answer is thin. So people write the minimum and move on. You\u2019d probably do the same.<\/p>\n\n\n\n

    A live moderator fixes this almost by accident. They hear \u201ctoo expensive\u201d and ask: too expensive for what you got, or more than you\u2019d planned to spend? Two questions later, you know whether you have a value problem or a budget problem. Those are very different meetings.<\/p>\n\n\n\n

    The catch is that live interviews take weeks to recruit, schedule, moderate, and transcribe. Moderated chat borrows the moderator\u2019s best habit, the follow-up question, and brings it to every respondent who reaches the question. If you\u2019re weighing the two approaches, our guide to AI-moderated interviews<\/a> compares them with human-led ones.<\/p>\n\n\n\n

    Two ways to start the conversation<\/strong><\/h2>\n\n\n\n

    Every moderated chat question<\/a> starts in one of two modes. The choice depends on whether you need an answer explained or a topic explored.<\/p>\n\n\n\n

    Follow-up mode: start from what they just said<\/h3>\n\n\n\n

    Pick a source question the respondent has already answered, and the interview opens from that answer. You can even quote it back. A respondent who chose a particular brand sees an opening question that names that brand. It feels like being listened to, because it is.<\/p>\n\n\n\n

    This is the mode for ratings, preferred brands, and reasons for leaving.<\/p>\n\n\n\n

    Independent mode: start from a question you write<\/h3>\n\n\n\n

    There\u2019s no source question here. You write an opening question that introduces a topic, and the conversation starts there. Use it for first reactions to a new concept, or for how people describe a category in their own words. Anywhere you\u2019d open a focus group with \u201ctell me about…\u201d<\/p>\n\n\n\n

    A simple rule: if there\u2019s an answer you need explained, use follow-up mode. If there\u2019s a topic you need explored, use independent mode.<\/p>\n\n\n\n

    The three dials you control<\/strong><\/h2>\n\n\n\n

    Think of these as the brief you\u2019d hand a human moderator before a session.<\/p>\n\n\n\n