Skip to main content
The AI interviewer is the conversational moderator that runs your study: it asks your questions, listens, probes with follow-ups, and keeps the conversation on track. Everything about its behavior is configurable in Settings → AI Interviewer.
The AI Interviewer tab is hidden for studies using the Survey engine, since surveys don’t have conversational questions.

​
Interviewer mode

​
Personality & guidelines

  • Description (up to 900 characters) — the interviewer’s persona: tone, role, and style. For example, a warm UX researcher, or a neutral market-research moderator.
  • Guidelines (up to 3,000 characters) — behavioral rules for the whole interview. When set, your guidelines replace Versive’s defaults, so include everything you care about (probing style, what to avoid, how to handle off-topic answers).

​
Question rephrasing

By default the AI may rephrase the next question so it flows naturally from the conversation (“You mentioned onboarding was confusing — walk me through what happened when…”). You can:
  • Turn rephrasing off entirely if exact wording matters (e.g. standardized instruments).
  • Add rephrasing instructions (up to 300 characters) to constrain how questions may be reworded.

​
Follow-ups

Follow-up behavior is configured per question — see the AI Question settings for follow-up limits, instructions, and duration targets.

​
Transcription keywords

Under Advanced → Keywords, add domain-specific terms — company names, product names, industry jargon — to improve voice transcription accuracy.

​
Voice settings

For realtime voice-to-voice studies, tune the silence threshold (0.5–5 seconds, default 1.5) that controls how long the AI waits after the participant stops speaking before responding.