← Insights & Guides · Updated · 12 min read

AI-Moderated Interview Discussion Guide: Design Tips

By

An AI-moderated interview discussion guide defines the research decision, relevant participant experience, topic priorities, opening questions, and rules for follow-up. It gives the moderator direction while leaving room to explore what the participant actually says. The researcher approves the guide and checks whether completed interviews supply useful evidence.

Use the editable AI interview guide worksheet alongside the examples below. It is a Markdown text file that can be edited directly or copied into your planning document. To inspect the output before designing a study, listen to the published sample interviews.

What Makes an AI-Moderated Discussion Guide Different?


Human moderators commonly use semi-structured guides rather than reading a rigid script. Those guides often include:

  • Exact question wording for each topic
  • Pre-written follow-up probes
  • Transition language between topics
  • Time allocations per section
  • Moderator notes on what to listen for

Both approaches need a clear research question, participant context, and priorities. A human moderator can interpret shorthand and ask a colleague for clarification; an AI guide benefits from explicit instructions about what to pursue, avoid, and leave unresolved.

In AI-moderated research, the guide is a framework. It includes:

  • Research objectives — what the study needs to learn
  • Topic areas — 5-8 themes to explore
  • Opening prompts — 1-2 questions per topic that initiate the conversation thread
  • Probing directives — what kinds of depth the AI should pursue (motivations, comparisons, emotions, trade-offs)
  • Methodological parameters — laddering depth, non-leading language constraints, time allocation

The AI generates follow-up questions and manages the conversation, but the researcher still needs to inspect its behavior. Clear instructions reduce ambiguity; they do not guarantee neutral questions, complete coverage, or a particular depth in every session.

What Is the 5-7 Level Laddering Framework?


Laddering is the core technique that separates depth interviews from surveys. It’s a structured approach to probing progressively deeper into a participant’s reasoning:

Level 1-2: Surface response (What happened)

  • “I switched from Brand A to Brand B”
  • “I liked the new feature”

Level 3-4: Functional and emotional drivers (Why it matters)

  • “Brand B saves me time on my morning routine” (functional)
  • “I felt frustrated that Brand A kept changing their formula” (emotional)

Level 5-7: Core values and identity (What it means)

  • “Being efficient in the morning means I can spend that time with my kids before school” (value)
  • “I’m the kind of person who does research before buying — brands that change without telling me feel disrespectful” (identity)

Use this ladder as a way to think about possible follow-ups, not a mandatory seven-step sequence. A practical purchasing decision may have no deeper identity explanation. AI-moderated interviews can adapt to responses, but useful depth must be assessed from the evidence each conversation produces.

How the AI Ladders

The following is an illustrative probe sequence, not a transcript or a set of questions to ask regardless of the answer. If someone says “I switched to Brand B because it is cheaper,” begin with the decision context and follow only the threads their responses support:

  1. “What made the price difference noticeable to you?” (Context)
  2. “What did you compare before deciding?” (Alternatives)
  3. “What did you expect from each option?” (Expectation)
  4. “What happened after you switched?” (Experience)
  5. “How did that compare with what you expected?” (Interpretation)
  6. “What would Brand A need to do for you to consider coming back?” (Action threshold)

Ask one follow-up at a time and adapt it to the response. Do not assume disappointment, distrust, or an unmet expectation unless the participant has described it. If they cannot recall the event, record that limit rather than repeatedly asking them to reconstruct it.

How Do You Design Your Opening Questions?


Opening questions set the direction for each topic area. They need to be:

Open-ended — no yes/no questions. “Tell me about…” or “Walk me through…” instead of “Did you…” or “Do you prefer…”

Non-leading — don’t suggest the answer. “How did you decide which product to buy?” instead of “What made you choose our product?”

Experiential — anchor in concrete experience rather than abstract opinion. “Think about the last time you made a purchase in this category. What happened?” instead of “What do you think about this category?”

Singular — one question at a time. Don’t combine: “Tell me about your experience and what you’d change.” Split into two separate opening prompts.

Examples of Strong Opening Questions

Brand perception research:

  • “Think about the last time you heard someone mention [Brand]. What was the context?”
  • “If [Brand] were a person at a dinner party, how would you describe them?”
  • “Walk me through the last time you considered buying from [Brand]. What was going through your mind?”

UX discovery research:

  • “Show me the last thing you tried to accomplish in [product]. Walk me through exactly what happened.”
  • “Think about a time when [product] frustrated you. What were you trying to do?”
  • “If you could change one thing about how [product] works, what would it be and why?”

Churn research:

  • “Take me back to the moment you decided to cancel. What was happening?”
  • “Before you cancelled, did anything almost make you stay? What was it?”
  • “If a friend asked you about [product] today, what would you tell them?”

Writing Probe Sequences


You don’t script individual probes for AI-moderated interviews — the AI generates them dynamically. Instead, you provide probing directives that tell the AI what kinds of depth to pursue:

Motivation probes

“When the participant describes a behavior or choice, probe for the underlying motivation. What triggered the decision? What alternatives were considered? What would have changed the outcome?”

Emotional probes

“When the participant expresses positive or negative sentiment, probe for the emotional experience. How did it make them feel? What was at stake emotionally? How does this connect to their broader life or work?”

Comparison probes

“When the participant mentions alternatives, competitors, or past experiences, probe for comparison dimensions. What’s better, what’s worse, and what’s different? What would need to change for their preference to shift?”

Consequence probes

“When the participant describes a problem or unmet need, probe for downstream effects. What happened as a result? How did it affect other decisions? Who else was impacted?”

These directives give the AI a framework for generating relevant follow-up probes without scripting the exact questions. The AI applies the appropriate probe type based on what the participant actually says.

Annotated example from a published interview

In the W30 phone-replacement interview, the participant explains that their old phone broke and describes buying a replacement. Listen to the full audio alongside the transcript. This is an example of moderation to review, not an endorsement of every prompt.

Actual moment in the published transcriptWhat a researcher can learnChange to test in the next guide
The moderator asks what made the participant look for a new phone that dayAn event-based opening establishes the triggerKeep the event anchor; it provides context before opinions
The participant mentions features and friends’ recommendationsThe answer opens several possible decision threadsExplore one thread at a time and ask what was compared
The moderator says, “Sounds like you knew exactly what you want” before asking about the phoneThe preface assumes certainty that the preceding answer may not establishTry: “What were you considering at that point?”
The moderator later asks why the participant chose Walmart rather than another store or onlineIt distinguishes retailer choice from handset choiceKeep that distinction; record whether alternatives were considered or only introduced by the question

The revised wording in the final column is our suggested design improvement. It is not part of the recorded interview. That distinction matters when a client wants to trace a finding back to a participant’s actual words.

Write the learning goal as “Understand the sequence and trade-offs behind a recent replacement purchase.” A useful probe directive is “Separate the reason for replacing the item, the reason for choosing a product, and the reason for choosing a seller. Ask about alternatives without assuming they were considered.” This is more testable than “probe deeply into emotions.”

The sample presentation shows the downstream evidence and limitations a guide should make possible. Before launch, work backward from the client decision: which claim could this guide support, what would contradict it, and what would remain unknown?

Branching Logic: How AI Adapts in Real-Time


Traditional branching logic is pre-programmed: “If participant says X, ask Y. If participant says Z, ask W.” This works for surveys but produces rigid, unnatural conversations.

AI-moderated branching is adaptive. The AI detects themes, emotions, and unexpected directions in real-time and adjusts its probing strategy:

Unexpected competitor mention: If a participant spontaneously mentions a competitor you didn’t include in the guide, the AI probes that competitive thread — because unprompted competitor mentions are often more valuable than prompted comparisons.

Strong emotional response: If a participant’s language signals frustration, excitement, or conflict, the AI shifts into emotional probing mode — exploring the experience behind the emotion rather than moving to the next topic.

Contradiction detection: If a participant says “I love the product” but later describes avoiding key features, the AI gently explores the contradiction — “Earlier you mentioned enjoying the product, but it sounds like you don’t use [feature]. Help me understand that.”

Depth vs. breadth management: If a participant is providing deep, rich responses on a topic, the AI spends more time there — even if it means covering fewer topics. Depth on 4 topics beats surface responses on 8.

Common Mistakes in AI Discussion Guide Design


1. Over-scripting

Writing 40 specific questions with exact follow-ups. This turns the AI into a survey bot. Instead: 5-8 topic areas with 1-2 opening questions each.

2. Leading questions in opening prompts

“What do you love about our new feature?” assumes they love it. Instead: “Tell me about your experience with our new feature.”

3. Front-loading too many topics

Trying to cover 12 topics in 30 minutes. No topic gets depth. Instead: 5-6 topics with full laddering. Cut topics ruthlessly.

4. Neglecting warm-up

Jumping straight into research questions. Participants need 2-3 minutes of rapport-building to feel comfortable sharing honest, deep responses. Include a warm-up prompt: “Before we dive in, tell me a bit about your role and what a typical day looks like.”

5. Designing for breadth instead of depth

“Let’s cover product, pricing, brand, competitors, support, and loyalty.” Instead: “Let’s deeply understand the purchase decision, including everything that influenced it.” Five deep topics consistently outperform fifteen shallow ones.

Voice vs. Video vs. Chat: How Guide Design Changes by Modality


The core methodology — 5-7 level laddering, non-leading language, adaptive probing — stays the same across modalities. But guide design adapts to how participants process information:

Voice interviews:

  • Ask one short, clear question at a time; participants cannot reread a spoken prompt
  • Warm-up is especially important — voice creates intimacy that requires trust
  • Probing can reference “what I heard you say” patterns effectively
  • Best for: emotional topics, narrative-heavy research, complex B2B decisions

Chat interviews:

  • Opening questions should be shorter and simpler — text requires concise prompts
  • Multiple follow-ups can feel rapid-fire — pace probing with transitional language
  • Participants often write more candidly in text than they speak
  • Best for: sensitive topics, large-scale studies, international research in 80+ languages

Video customer interviews:

  • Can incorporate visual stimuli — show concepts, packaging, interfaces
  • Non-verbal cues add richness (though AI moderation focuses on verbal content)
  • Opening questions should reference what’s being shown: “Looking at this packaging design, what’s your first impression?”
  • Best for: concept testing, design research, product demonstrations

Interview depth varies with the question, participant, moderator behavior, and modality. Choose the format for the research task and participant access, then pilot it. Do not infer emotional meaning from a transcript alone when the relevant tone is missing.

Template: Brand Perception Study


Here’s a ready-to-use framework for a brand perception study:

Objective: Understand how target consumers perceive [Brand] relative to alternatives

Warm-up (2-3 min): Opening: “Tell me a bit about yourself and how [category] fits into your life.”

Topic 1: Category context (5 min) Opening: “When you think about [category], what brands come to mind first? Walk me through what each one means to you.” Probe directive: Ladder into why these brands occupy top-of-mind position. What experiences shaped the association?

Topic 2: Brand encounter (7 min) Opening: “Think about the last time you encountered [Brand] — whether you bought it, saw an ad, or heard someone mention it. What happened?” Probe directive: Explore the full context. Where were they? What triggered the interaction? How did they feel?

Topic 3: Brand meaning (7 min) Opening: “If [Brand] were a person, how would you describe their personality?” Probe directive: Ladder from surface descriptors to values. What kind of person uses this brand? What does choosing it say about someone?

Topic 4: Competitive comparison (5 min) Opening: “If you couldn’t buy [Brand], what would you choose instead? What would you gain and lose?” Probe directive: Explore switching barriers and drivers. What’s irreplaceable about [Brand]? What’s better elsewhere?

Topic 5: Future relationship (4 min) Opening: “Looking ahead, do you see yourself using [Brand] more, less, or about the same? What would change that?” Probe directive: Ladder into what would strengthen or weaken the relationship. What’s the brand’s biggest risk?

Template: UX Discovery Study


Objective: Identify friction points, unmet needs, and opportunities in [product] experience

Warm-up (2-3 min): Opening: “Tell me about your role and how [product] fits into your workflow.”

Topic 1: Typical usage (5 min) Opening: “Walk me through the last time you used [product]. Start from when you opened it — what were you trying to accomplish?” Probe directive: Map the complete journey. Where did things flow smoothly? Where did they slow down or confuse?

Topic 2: Friction point deep-dive (8 min) Opening: “Think about a time when [product] frustrated you. What were you trying to do, and what went wrong?” Probe directive: Ladder deeply into the consequences. What did they do instead? How much time was lost? How did it affect their work or the people depending on their output?

Topic 3: Workarounds (5 min) Opening: “Are there things you use other tools for that you wish [product] could handle? Walk me through an example.” Probe directive: Explore the gap between expectation and reality. What would the ideal experience look like?

Topic 4: Feature priorities (5 min) Opening: “If you could wave a magic wand and change one thing about [product], what would it be?” Probe directive: Ladder into why this change matters most. What would it enable that isn’t possible today?

Topic 5: Delight moments (5 min) Opening: “Has [product] ever surprised you in a good way? Tell me about that moment.” Probe directive: Understand what creates positive experiences. What made it memorable? How does it affect their overall perception?

Iterating Your Guide Across Study Waves


Discussion guides improve with use. Here’s how to iterate:

Pilot: Start with a small number of interviews covering the key audience differences. Review each complete conversation before expanding. Check whether the participant could answer, prompts stayed neutral, concrete examples emerged, and the planned topics fit the available time.

Between waves: Refine opening questions that produced shallow responses. Add probing directives for themes that emerged unexpectedly. Remove topics that didn’t generate useful depth.

Next wave: Run the revised guide and check the same criteria. Record the version, changed wording, reason for the change, and which interviews used each version. Changes to prompts or eligibility can affect comparability; report that rather than treating every wave as identical.

Ongoing: Every study refines your understanding of what produces depth with your specific audience. Guides for recurring research (quarterly brand tracking, ongoing UX research) improve continuously. And every conversation feeds into the intelligence hub, building compounding knowledge across waves.

The best discussion guides aren’t written once — they’re evolved through iterative learning about what questions, in what sequence, with what probing frameworks, produce the deepest understanding of your customers.

Ready to design your first AI-moderated study? Start on the platform or explore our complete guide to AI-moderated interviews for methodology deep-dives.

Note from the User Intuition Team

User Intuition provides AI-moderated qualitative research for agencies, consulting firms, and research teams. Keep your methodology and discussion guide, bring your own sample or use our 4M participant panel, and review recordings, transcripts, and evidence-linked findings. Your researchers connect the evidence to the client decision and prepare the final recommendations.

Inspect complete sample calls and a readout, then test your own brief. Starter voice interviews cost $30 with your sample or $60 with standard panel recruitment, with no monthly fee. Specialty audiences are quoted separately; incentives you arrange for your own sample are additional. See pricing or try 3 free voice interviews with your own participants.

Frequently Asked Questions

Both human and AI moderators can use flexible semi-structured guides. An AI guide must make objectives, topic priorities, neutral follow-up rules, and stopping conditions explicit enough for the system to follow. Researchers remain responsible for approving the method and reviewing what happened in actual interviews.

Laddering is a qualitative technique that probes progressively deeper into motivations. Level 1-2 captures surface responses (what happened). Level 3-4 uncovers functional and emotional drivers (why it matters). Level 5-7 reaches core values and identity-level motivations (what it means to them). The useful depth depends on the participant and topic. Do not force a fixed number of probes or assume every answer has an identity-level explanation.

Start with a small set of prioritized topics and one opening prompt per topic. Treat timings as planning assumptions, then use pilot calls to check coverage and fatigue. Remove lower-priority topics when meaningful follow-up needs more time.

AI moderators detect themes, emotions, and unexpected directions in participant responses and adjust probing accordingly. If a participant mentions a competitor unprompted, the AI probes that thread. If someone expresses strong emotion, the AI explores the underlying experience. Branching is adaptive, not pre-programmed.

Over-scripting (treating AI like a survey), asking leading questions in opening prompts, front-loading too many topics (leaving no time for depth), neglecting warm-up questions (participants need trust-building), and designing for breadth instead of depth (5 deep topics beats 15 shallow ones).

Use one clear question at a time in every modality. Voice prompts must be understandable on first hearing; chat prompts should be concise and allow time to type. When using visual stimuli, confirm what the participant can see. Pilot each modality rather than assuming equivalent depth.

Assess suitability for the audience and topic before choosing AI moderation. Include clear consent, comfort checks, and a way to decline or stop. Some studies need a trained human moderator or additional safeguards. A guide alone does not establish that the method is appropriate.

Start with a small pilot that covers the main audience differences. Review full transcripts and audio, then revise confusing prompts or missed evidence needs. Record the guide version and assess whether changes limit comparisons between waves; a revision does not automatically improve quality.

Yes. The linked Markdown worksheet includes a decision brief, topic plan, neutral probe rules, stopping conditions, and a pilot review log. Edit it for your audience and method before fieldwork. It is a planning document, not a guarantee of research quality.

Check whether it elicited a concrete example or clarified the participant's reasoning without introducing an assumption. Compare the probe with the preceding response, listen to the audio when meaning is unclear, and record any missing evidence before approving the guide.
Get Started

Put This Framework Into Practice

Sign up free and run your first 3 AI-moderated customer interviews — no sales call. Panel recruiting is billed separately.

Self-serve

Launch your first study in minutes. Results in 24 hours.

See it First

Explore a real study output — no sales call needed.

No contract · No retainers · First insights in 24 hours