Back to docs
Interview Experience

Custom AI Interviewer Persona: Brand Voice & Tone for AI-Moderated Research

How to shape your AI interviewer's voice, tone, and persona so it sounds like your brand — not a generic chatbot. Covers personality dimensions, when to adjust formality, and how to configure persona in Koji.

The Bottom Line

A custom AI interviewer persona is the configurable voice, tone, formality, and personality of the AI that moderates your customer interviews. When you're running research on behalf of a brand — Stripe, Notion, your own startup — the AI shouldn't sound like a generic chatbot. It should sound like a thoughtful interviewer from your team. That means matching the formality of your brand voice, using vocabulary your customers already hear from you, and projecting a personality that puts the right kind of participant at ease.

In Koji, you shape the AI interviewer's persona through three levers: the brief-level instructions (high-level tone, formality, must-mentions and must-avoids), the wording of your questions, topics and guardrails (where your product's vocabulary and boundaries reach the interviewer), and the branding settings on the interview landing page (logo, colours, intake messaging that primes the participant before the AI says a word). Together, these turn the default friendly-curious-researcher persona into a voice that feels native to your brand.

This guide explains the personality dimensions worth thinking about, which combinations work for which audiences, and the exact configuration knobs available in Koji.

Why Persona Matters for AI Interviews

It's tempting to dismiss persona as cosmetic. It isn't. Three concrete effects:

  1. Completion rate. When the AI's tone matches the brand the participant signed up with, they stay engaged longer. A formal AI interviewer on a casual consumer app feels off; a chatty AI on an enterprise compliance survey feels unserious. Either way, drop-off rises.
  2. Answer candour. Participants are 2x more candid with a moderator who feels like one of the team than with a generic third-party voice. Persona signals trust before the first answer.
  3. Brand health. Every customer interview is also a brand interaction. A clumsy AI moderator damages the relationship; a thoughtful one strengthens it.

For B2B research where the participants are your customers (not random panel respondents), persona is especially load-bearing. They're comparing the AI moderator to the human CSM or AE they've already met. The persona either lives up to that bar or undermines it.

The Four Persona Dimensions Worth Configuring

A good persona is more than "friendly vs formal". Here are the four dimensions that actually shape how an AI interviewer feels:

1. Formality

On a spectrum from very casual to very formal. A SaaS startup interviewing free-trial users wants conversational ("Got it — what happened after you tried the import?"). A regulated industry like healthcare or finance wants neutral-to-formal ("Understood. Could you describe what occurred after the import attempt?"). Pick the level your brand uses in customer-facing emails and match it.

2. Pace

How quickly does the AI move through questions? Brisk personas confirm the answer and move on — good for power users with limited time. Patient personas linger on each answer, asking 2–3 follow-ups before progressing — good for empathy interviews or hard-to-reach customer segments. In Koji, pace is controlled by the probing depth setting (1 to 3 follow-ups per question) and the interview mode (structured = brisk, exploratory = patient, hybrid = balanced).

3. Warmth

How much affect does the AI project? Cool personas are professional and neutral; warm personas acknowledge feelings ("That sounds frustrating") and use lightly conversational connectives ("Totally — and after that…"). Warmth is helpful for stay interviews, exit interviews, and any emotionally loaded topic. It's less appropriate for B2B procurement research where buyers expect efficiency.

4. Domain Voice

Does the AI use industry vocabulary correctly? If you're researching developers, "shipped" and "PR" should land naturally. If you're researching CFOs, "burn rate" and "MRR" should be used precisely. Domain voice is mostly shaped by the words in the study itself: the question text, the brief's topics and your tone instructions. Context documents you upload (a product one-pager, a glossary) help the research assistant use the right terms when it drafts those, but the interviewer never reads the files.

Three Persona Archetypes (and When to Use Each)

Most teams converge on one of three archetypes:

Comparison table of three AI interviewer persona archetypes, the Curious Colleague, Professional Researcher and Subject-Matter Peer, across formality, pace, warmth, domain voice and best-fit audience.
Three persona archetypes and the audiences they fit best.

The Curious Colleague. Casual formality, brisk pace, warm tone, light domain voice. Works for: consumer apps, prosumer SaaS, early-stage startup customer discovery, exit interviews where you want the participant to feel heard. Default starting point.

The Professional Researcher. Neutral formality, patient pace, cool tone, precise domain voice. Works for: B2B enterprise research, healthcare or finance regulated industries, market sizing studies. Signals that the research is serious without being cold.

The Subject-Matter Peer. Casual-to-neutral formality, brisk pace, cool-to-warm tone, heavy domain voice. Works for: developer research, designer research, technical buyer interviews — any audience where being seen as a peer matters more than being seen as a researcher. The AI uses the right jargon without explaining it.

Most Koji users start with the Curious Colleague archetype, then adjust one or two dimensions as they see real transcripts.

How to Configure Persona in Koji

There are three places where persona is shaped:

1. Brief-Level Tone Instructions

When you're generating the brief with the AI consultant (or editing it manually), you can add tone-and-style instructions directly:

"Tone: casual but precise — match Stripe's developer-facing voice. Use 'shipped', 'rolled out', 'flag' naturally. Avoid corporate-speak ('synergy', 'leverage'). Acknowledge frustration when participants describe friction."

These instructions are loaded into the AI interviewer's system prompt and apply across every conversation in the study. The more specific, the better. Generic instructions ("be friendly") produce generic personas. Specific instructions ("warm but brisk, use 'ship', avoid 'utilise'") produce distinctive personas.

2. Question Wording, Topics and Guardrails

The interviewer works only from the study you publish, so the words in it carry your domain voice:

  • Question text. Write questions in your product's terminology (feature names, key metrics) and your audience's register. The interviewer asks them as written and follows up in the same language.
  • Topics in the brief. List the areas to probe, so follow-ups go where you need depth.
  • Guardrails. List what the interviewer must avoid, such as quoting prices, naming other customers or pitching the product. Research, not sales.

Context documents you upload (a product one-pager, a brand voice guide, past research) help the research assistant draft all of this in your terms. They stay with the research assistant: the AI interviewer never reads them during an interview, so anything it must know goes into the questions, topics or guardrails.

3. Branding & Intake Settings

The interview landing page is the participant's first impression. Configure:

  • Logo and brand colours — so the participant knows immediately whose research this is.
  • Custom intake messaging — a short welcome explaining the goal and what to expect. This primes the participant for the AI's tone.
  • Consent and intro language — if your brand has specific data-handling language, include it here.
  • Voice mode default — pick whether voice is the default or text is, depending on which feels more on-brand.

With brand consistency from landing page → intake → AI moderator, participants experience one coherent voice rather than a generic AI dropped into your domain.

Persona Across the Six Structured Question Types

Koji interviews mix open conversation with six question types: open ended, scale, single choice, multiple choice, ranking and yes/no. Persona carries across all of them, but it shows up differently:

  • Open ended questions are where persona does most of its work. Warmth and pace decide whether a participant keeps talking after the first answer.
  • Scale, choice, ranking and yes/no questions collect a structured answer. In text interviews the participant picks from buttons, a list or a drag-to-order widget. In voice interviews the AI asks the same question conversationally. The tone of the lead-in and the follow-up is the persona; the answer options stay exactly as you wrote them.
  • Follow-ups per question. Each question can have no follow-ups or up to three, plus its own probing instructions ("ask what changed since they started"). A brisk persona with one follow-up and a patient one with three can share the same question list.
  • Scales anchor on the score. By default, a scale question's follow-up refers to the participant's own rating, which reads naturally in any persona.

See the structured questions guide for how each type is set up and reported.

Common Persona Mistakes

Trying to make the AI sound human. Participants know they are talking to an AI. Pretending otherwise erodes trust. Aim for a thoughtful AI interviewer, not a fake person.

Over-engineering the persona. Three lines of tone instructions usually beat thirty. Brief, specific, and concrete > a 500-word brand voice manifesto. The AI is good at applying a few constraints; less good at distilling a long abstract document into voice.

Forgetting branding on the landing page. The AI's persona doesn't exist in a vacuum. If the participant arrives at an unbranded white page, the AI's personality has no context. Always brand the landing page.

Not reading the first transcripts. Persona problems show up in the first few interviews. Run test interviews, read them end to end and adjust the tone instructions before you send the link to everyone.

A Worked Example: Configuring Persona for a Developer Research Study

You're interviewing developers about their CI/CD setup. Here's the setup, start to finish.

Step 1: Pick an archetype. Subject-Matter Peer — developers want to talk to someone who speaks their language, not a market researcher.

Step 2: Add tone instructions to the brief:

"Tone: casual peer voice. Use 'shipped', 'rolled out', 'flag', 'main' naturally. Don't explain technical concepts unless the participant asks. Acknowledge engineering frustrations ('yeah, flaky tests are the worst') but don't pile on. Keep questions short — engineers prefer crisp."

Step 3: Put the vocabulary in the study. Write the CI/CD terms you want used into the questions and topics, and add guardrails for what to stay away from, such as pricing or roadmap dates. If you upload a glossary or your engineering blog's last three posts as context documents, the research assistant uses them while drafting. Check that the terms made it into the questions: the interviewer only sees the study.

Step 4: Configure interview mode. Set to hybrid — cover required questions about current toolchain, then free-roam on what they wish existed. Probing depth: 2 follow-ups (engineers volunteer detail without prompting).

Step 5: Brand the landing page. Use your engineering team's logo variant and a 1-sentence intro like: "Quick chat with our AI interviewer about your CI/CD setup. ~8 min, no sales pitch."

Step 6: Run 3 test interviews and read the transcripts. Adjust as needed. If the AI is using too much jargon, dial it back. If it's being too formal, add an explicit "lean casual" instruction.

This 30-minute setup loop produces a persona that feels like your engineering team interviewing customers — not a generic AI chatbot.

Frequently Asked Questions

Can I configure the AI interviewer's voice (literally — the voice it speaks in) for voice interviews? Yes. Koji's voice mode supports configurable voice profiles — pick the gender, accent, and pace that match your brand. For most B2B research, a neutral, mid-pitch voice with a measured pace works best. For consumer research, you can lean warmer or more energetic.

Does persona affect interview quality scores? Persona shapes engagement (completion rates, answer depth) more than it shapes the 1–5 quality score itself. Quality scoring measures whether questions were covered, whether answers were on-topic, and whether structured answers parsed cleanly — these are persona-agnostic. But because better personas drive longer, more candid answers, they indirectly raise quality scores.

Can I run different personas in different studies under the same account? Yes. Persona is study-level, not account-level. You can run a Curious Colleague persona on your free-trial onboarding study and a Professional Researcher persona on your enterprise CFO interviews simultaneously.

What about multilingual studies — does persona translate across languages? Tone instructions transfer, but specific vocabulary doesn't (industry terms differ across languages). For multilingual studies, note in the brief that the AI should use the local industry vocabulary in each language, and review the translated question text.

Can I clone a persona across studies? Yes — duplicate a study and the brief (including tone instructions) copies over. Easiest way to maintain a consistent voice across multiple research projects.

Is there a default persona if I don't configure anything? Yes — Koji's default is "thoughtful, curious, professional researcher" with neutral formality, balanced pace, mild warmth, and no specific domain voice. It's a sensible starting point but you'll get better engagement by tuning at least the formality and domain voice dimensions.

Related Resources

Related Articles

AI Interviewer Tuning: How to Get Research-Grade Voice Interviews

A complete playbook for tuning Koji's AI interviewer — company context, probing depth, structured questions, and interview mode — to deliver interviews indistinguishable from a human researcher.

Customizing Branding

How to personalize your interview landing page with custom headlines, descriptions, badges, mode settings, and OG images.

How to Customize Your Research Study: Branding, Landing Pages, and Intake Forms

Complete guide to Koji's study customization options — landing page design, branded colors, animated orbs, intake forms, trust badges, interview mode settings, and link previews.

How to Interview Enterprise Customers and C-Suite Decision Makers

A practical playbook for running customer research interviews with enterprise buyers and C-suite decision makers. Covers recruiting strategy, ROI framing, time-respect, multi-stakeholder triangulation, and how to use Koji's AI interviewer to land 30-minute exec conversations without burning your champion.

Structured Questions in AI Interviews

Mix quantitative data collection — scales, ratings, multiple choice, ranking — with AI-powered conversational follow-up in a single interview.

Uploading Context Documents

How to add background files that help Koji's research assistant design a sharper brief and better questions.

Working with the AI Consultant

Tips and strategies for chatting effectively with Koji's AI Consultant to design a strong research study.

Voice vs Text Interview: When to Use Each Mode

Choosing between voice and text mode for your AI interview? This guide breaks down response depth, completion rate, audience fit, and cost — plus a decision matrix that tells you which mode wins for each research scenario.