Skip to main content
AI Follow-Up Questions let you dig deeper automatically by generating a follow-up open text question to an existing question, based directly on each respondent’s answer. This helps you capture richer context and clearer detail without manually programming additional probes.
244fa6c494fa88e64f0b3c4ff72dee269270765eddbb07ddf4b5089d2bd99a2d AI Follow Up Final
Ask a smart, automatic follow-up the moment a respondent answers, so vague feedback turns into specific, actionable insight without adding researcher workload.

​
Key features

  • Attaches to most question types (see Supported question types below), not just open text.
  • Generates a short, neutral follow-up question in your study’s primary language as soon as the respondent submits their answer.
  • Skips automatically if a safe and relevant question cannot be generated quickly, protecting survey quality.
  • Runs alongside skip logic on the same parent question (new in this release). You no longer have to choose one or the other.

​
Supported question types

Enable AI follow-ups on:
  • Open text
  • Rating scale (number, smiley, and star)
  • Multiple choice, single select
  • Multiple choice, multi-select
  • NPS
  • Matrix
  • Rank order
Not available for: Video/voice, Recorded task, Legal consent, Text/URL prompt, and MaxDiff.

​
Why use AI follow-up questions?

  • Probe for clarity, examples, and root causes so you capture the “why” behind a response, not just the rating or selection.
  • Mimic a live interviewer at scale, improving response quality without adding researcher workload.

​
How to use

  1. In the study builder, open any supported question and turn on the AI Follow-Up toggle.
  2. (Optional) Add a prompt to guide the AI output.
  3. The AI generates a single follow-up focused on clarification, impact, sentiment, or depth.
To generate a relevant question, the AI draws on:
  • Agent Context (if provided): keeps the follow-up aligned with your research objectives.
  • The respondent’s prior questions and answers: broadens contextual understanding.
  • Signals from the response itself: intent, sentiment, topics, and entities.
  • Your prompt inputs (if applied).
Test the AI output any time in preview mode before launching your study.

​
Using skip logic with AI follow-up

You can now enable skip logic on a parent question that also has an AI follow-up turned on. Skip logic runs after the parent question. If a response matches a rule, the AI follow-up is skipped and the respondent routes to the designated question (or the survey ends). For example: when the parent answer is “Not applicable,” skip the follow-up entirely; when it is a specific value, route to a designated question or end the survey. When AI follow-up is available for a question type, the skip logic tooltip calls out this behavior. The AI Follow-Up tooltip is unchanged.

​
Results

View both the AI-generated probe and the respondent’s answer in the Results tab.

​
Best Practice

Use 1–2 AI Follow-Up questions per survey to balance deeper insights with respondent experience.

​
Prompt Examples

There are endless ways to configure AI-Follow Up prompts to ensure high quality questions are asked to your respondents. A few common prompts are listed below.
Note that you can test the AI output at any time in preview mode prior to launching your study.
  1. Ask the respondent to share a specific example that illustrates their previous answer.
  2. If the previous answer was vague or short (for example, “it’s fine” or “good”), ask what specifically makes them feel that way.
  3. If the respondent expressed frustration or a negative sentiment, ask what would have made the experience better. Do not ask them to rate the severity on a scale.
  4. Ask why the respondent chose that answer, but do not ask them to compare it to competitors or other products.

​
CSV File Export

The AI Follow-ups feature stores follow-up prompts and responses that were generated by AI for a respondent’s original answers. The CSV format for bulk export/import of AI follow-ups
  • Q1a_Question_Text
  • Q1a_Response
  • Q1b_AI_Followup_Question_Text
  • Q1b_Response
The Q1a/b refers to the parent question and response. Q2 a/b refers to the child question and response.

​
API Endpoint Updates

/responses endpoint: The only difference is the addition of parentQuestionId 
      {
            "visitorId": 0,
            "surveyId": 31064,
            "questionId": 241190,
            "updatedAt": "2026-01-29T18:14:18.167Z",
            "createdAt": "2026-01-29T18:14:18.167Z",
            "responseGroupUid": "d9bb8e7f-a0c5-4844-bf2f-01c6a14993fb",
            "response": "payments was confusing",
            "questionText": "can you clarify your response?",
            "parentQuestionId": 241188,
            "externalUserId": "",
            "partnerAnonymousId": "",
            "visitorUuid": "dfe1361a-0055-40f7-ab50-0e2bda8a6f06",
            "questionType": "AIDYNAMICFOLLOWUP"
        },
/surveys endpoint: The only addition is parentId, and of course the type now can also include AIDYNAMICFOLLOWUP 
              {
                    "id": 242496,
                    "type": "AIDYNAMICFOLLOWUP",
                    "order": 2,
                    "options": [],
                    "parentId": 242495,
                    "questionText": "Dynamic follow-up placeholder",
                    "routingOptions": [],
                    "optionsProperties": {
                        "required": false,
                        "conceptUrl": null
                    }
                }
/themes endpoint No change