How AI interviews work

Understanding AI-driven conversational surveys.

Explains the mechanics of AI interviews: adaptive follow-ups, prompt engineering, context preservation across turns, and how the AI moderates across languages. Also covers privacy and moderation considerations.

aiinterviewsconversational10-30 minutesIntermediateResearchersProduct managers

Steps

  1. Add an AI Interview question
    In the survey editor, click + Add and choose AI Interview (text-based) or AI Audio Interview (voice-based). Write the interview topic or question as the prompt.
  2. Configure the AI interviewer
    Set the AI interviewer name, personality description, and system prompt. You can customize the tone, depth, and follow-up behavior. Add example questions to guide the style.
  3. Set the question mode
    Choose how the AI decides when to stop asking follow-ups: Fixed count (set an exact number of follow-up questions), AI decides (the AI stops when it has enough depth, guided by min/max limits and your stopping criteria), or Time-based (interview runs for a set duration).
  4. Choose a model
    Select the AI model for the interview. The default is Claude Haiku 4.5 (fast, economical). You can also choose Sonnet 4.6 (balanced), Opus 4.6 (deepest follow-ups), or 130+ models from OpenAI (GPT-5.4, o3/o4 series), Google (Gemini 3.x), Meta (Llama 4), Mistral, DeepSeek, and 10 other providers. See Choosing a model for trade-offs.
  5. Pick a thinking speed
    Set the Thinking speed for how follow-ups are generated. Fast (default) generates a single question in one step — the most responsive option. Slow generates five candidate follow-ups, grades each with personality-specific criteria, then picks the highest-ranked one — higher quality for important interviews, at the cost of latency. When you enable AI follow-ups on a text question, Fast thinking is used by default.
  6. Add reference sources (optional)
    Click Reference Sources to let the AI access answers from earlier questions during the interview. The AI can use these references to ask more contextual follow-ups. You can also add per-respondent context that feeds into the interview dynamically.
  7. Monitor and review
    After launch, review AI interview transcripts in the Results tab. Each conversation shows the full exchange between the AI and the respondent.

AI interviews dynamically adapt follow-ups based on participant answers. The system probes for clarity and depth to produce higher-quality qualitative data than traditional open-text fields.

The AI preserves context across conversation turns, so follow-up questions reference what the respondent has already said. This creates a natural, interview-like experience.

Three question modes control interview length: fixed count (exact number of follow-ups), AI decides (AI stops when it has enough depth, with configurable min/max and stopping guidance), and time-based (runs for a set duration).

Thinking speed controls how follow-ups are produced. Fast thinking (default) generates a single question in one step and is best when responsiveness matters. Slow thinking generates five candidate questions, grades each with personality-specific criteria, and picks the highest-ranked one — best for high-stakes interviews where question quality matters most.

AI interviews work across 140+ languages. The AI detects the respondent's language and adapts automatically, while maintaining the interview goals you defined.

Reference sources let the AI access answers from earlier questions in the survey, so follow-ups can build on what the respondent already shared in previous sections. Per-respondent context can also be injected dynamically.

All AI conversations are transparent: you can see the full system prompt, edit it, and review every exchange in the response data.

QuestionPunk