AI-Moderated Interview (plugin type mini_idi) replaces a fixed list of sub-questions with a short, AI-guided interview: you set objectives and a discussion guide, and the AI moderator conducts the conversation, adapting follow-ups the way a live moderator would. It's wizard-driven.
What respondents see#
The same greeting-and-microphone flow as Guided Story, but instead of a fixed prompt list, the AI moderator asks an opening question and then generates follow-ups based on what the respondent says — up to a maximum number of questions and a target interview length you set. A live transcript appears as they talk.
When to use it#
- Replacing a scheduled in-depth interview (IDI) with an always-on, scaled equivalent.
- Exploratory research, concept testing, or jobs-to-be-done studies where a live moderator would normally adapt questions in real time.
- Any study where a single fixed question list can't capture the range of follow-ups a real interview would need.
Configuring it in the builder#
Drag AI-Moderated Interview from the StorySync AI Qual group onto your canvas — the wizard opens with Questions, Display Settings, and Text for Alerts steps. The Questions step is the most distinctive of any StorySync type:
- Show Image/Video in Question — optionally show up to 4 images (grid/collage), a video, or a camera video stimulus (the respondent records their own video response instead of just voice) at the top of the question, with its own front/rear Camera Facing control when Camera Video is chosen.
- Initial Instructions — introductory text shown before the interview begins.
- Opening Question — the first question the AI moderator asks to start the interview.
- Target Interview Length — desired length in minutes (1–30).
- Moderator Guidance slider — from "stick closely to the script" to "be flexible and explore openly within the stated objectives."
- Moderator Style slider — from "friendly and informal" to "strictly neutral and professional."
- Objectives — a free-text field describing what you want to achieve and the type of study (exploratory, validation, concept testing, jobs-to-be-done, etc.).
- Discussion Guide — either a list of separate guide questions (Question Format) or one free-form document the AI splits by paragraph (Document Format).
- Guardrails — topics the AI should avoid steering toward.
Settings reference#
| Setting | What it controls | Default |
|---|---|---|
| Show Image/Video in Question | Reveals the media fields (Media Type, image URLs 1–4, video URL, camera facing) for a stimulus at the top of the question | Off |
| Media Type | Image, video, or camera video (respondent records a video response) | Image |
| Camera Facing | Front or rear camera (when Media Type is Camera Video) | Front |
| Initial Instructions | Introductory text before the interview begins; supports piped text | Seeded example prompt |
| Opening Question | The first question the AI moderator asks | Seeded example question |
| Target Interview Length | Desired interview length in minutes | 10 (range 1–30) |
| Moderator Guidance | Script-adherence vs. open exploration | 5 (range 0–10) |
| Moderator Style | Informal vs. professional tone | 5 (range 0–10) |
| Objectives | What the study should achieve — study type, business goals | Seeded placeholder text |
| Discussion Guide | Question Format (separate fields) or Document Format (free text split by paragraph) | Document Format |
| Is Loaded from Iframe | Marks the question as embedded in an iframe inside an external survey | Off |
| Voice Mandatory | Voice input required, no text fallback | Off |
| Honor voice-permission globals | Follow survey-level voice/mic-permission setting | On (recommended) |
| Default to Voice | Voice recording is the default input method | On |
| Enable Transcription | Live transcript while the respondent talks | On |
| Enable Voice Attribute Detection | Detect speaker gender/age/language/accent/human-vs-AI | On |
| Tap to Zoom Image | Let respondents tap the concept image to zoom in | Off |
| Enable Image Scrolling | Let respondents scroll through multiple images | Off |
| Enable Auto Probing | Let the AI generate follow-ups beyond the discussion guide | Off |
| Use Whole Conversation | Feed the entire prior conversation into AI-generated probes | Off |
| Max Questions To Be Asked | Ceiling on how many questions the AI can ask | 5 (range 3–100) |
| Request Voice or Text Preference | Ask respondents whether they'd rather record or type (only when voice isn't mandatory) | Off |
| Concept Image Height | Height of the stimulus image as % of screen | 50% (range 30–70) |
| Question Font Size | Font size for question/instruction text | 17px (range 10–40) |
| Maximum Recording Duration | Cap per response | 5 minutes (range 3–60) |
| Select Language | Speech-recognition language | English (+ 6 others) |
| Select Text Direction | LTR or RTL layout | Left to Right |
| Button Color | Primary action-button color | #34ac8b |
Logic support#
Stores an open-ended, multi-turn conversational response — condition operators are limited to Answered / Not answered. See Logic, Flow & Conditions.
Good to know#
- Objectives and Discussion Guide together are what steer the AI moderator — a vague objective produces vague follow-ups, so treat this field like a brief you'd hand a real moderator.
- Max Questions To Be Asked is a hard ceiling independent of Target Interview Length; set both consistently or respondents may hit the question cap well before the target time.
Related guides#
- Question Types — overview and when-to-use table
- Guided Story — the fixed-question voice format this extends
- StorySync AI Qual — all 9 StorySync formats
- Logic, Flow & Conditions — operators and condition builder
Was this page helpful?