What are AI-moderated interviews?
An AI-moderated interview is a one-to-one research interview with a real person, run by an AI interviewer instead of a human moderator. The AI works from a discussion guide, listens, and asks follow-up questions based on what the person just said, by voice or text. Because no moderator's calendar is involved, hundreds of interviews can run in the same week.
Also called AI interviewer, AI moderator, AI-led interviews, AI-moderated research, AI conversational interviewing.
How one runs
An AI-moderated interview study starts when a researcher states what they want to learn. The AI drafts a discussion guide and a person approves it. Participants are then interviewed one at a time, each at a moment that suits them. Afterwards the conversations are grouped into themes, each with a count of how many people raised it and exact quotes that lead back to a transcript.
In an AI-moderated interview the participant is always a real person. Only the moderator is an AI. AI-moderated interviews differ in this way from synthetic respondents, where the answers themselves come from a model.
The evidence that it works
AI-moderated interviews have been run at a scale no team of moderators could match. Anthropic reports that its AI interviewer ran 1,250 interviews with professionals, each about 10 to 15 minutes long, and that a later round reached 80,508 people in 159 countries and 70 languages.
Academic work on AI-moderated interviews points the same way. Economists Felix Chopra and Ingar Haaland ran several hundred AI-led interviews about why people do not invest in the stock market. They report that the interviews gave thematically richer answers than other ways of collecting qualitative data at scale, and that most of the gain came from the interviewer's follow-up questions.
Where it fits
An AI-moderated interview sits between a survey and a human-led depth interview.
Its limits
Anthropic notes that its text-only AI-moderated interviews could miss cues a person would catch, and that knowing an AI was asking may have changed what people said.
An AI-moderated interview, like any interview, records what people say, which is not always what they do. Anthropic reports that 65% of its participants described AI as mainly augmenting their work, while its records of actual conversations showed a much more even split between augmenting and automating.
What a good study looks like
In a good AI-moderated interview study, a person approves the guide before any interview runs. Every theme has a count and a share that are computed from the coded answers, not written by a model as a sentence. Quotes are word for word. Groups too small to report without describing one person stay hidden. Jean's post on running AI-moderated interviews at scale covers each of these rules and what to ask a vendor.
AI-moderated interviews and related terms
- Synthetic respondents
the reverse. In an AI-moderated interview a real person answers an AI. With synthetic respondents an AI answers in place of a person.
- Digital twins of customers
built from interviews like these. The interview comes first, and the twin is a model of the person interviewed.
- User simulator
plays a user to test a product. No real participant is involved.
- Human simulation
produces what people would say without asking them. An interview asks them.
Questions people ask
- What is an AI-moderated interview?
- An AI-moderated interview is a one-to-one research interview with a real person, run by an AI interviewer instead of a human moderator. The AI interviewer follows a discussion guide and asks follow-up questions based on what the person just said, by voice or text.
- Is the participant in an AI-moderated interview a real person?
- Yes. In an AI-moderated interview the participant is a real person. Only the moderator is an AI.
- How long does an AI-moderated interview take?
- AI-moderated interviews are usually short. Anthropic reports that its first AI-run interviews with professionals lasted about 10 to 15 minutes each.
- What is the difference between an AI-moderated interview and a survey?
- A survey asks fixed questions with fixed answer options. An AI-moderated interview asks open questions and follows up on what each person says, so an AI-moderated interview finds reasons that a survey did not think to list.
- When should you not use an AI-moderated interview?
- An AI-moderated interview is a poor fit when tone of voice and body language matter, for long depth interviews, and for ethnography. A human moderator is the better choice in those cases.
- Which companies offer AI-moderated interviews?
- Companies that offer AI-moderated interviews with real people include Listen Labs, Outset and Jean Technologies, according to each company's website as of November 2026. Anthropic has also built its own AI interviewer for research. Jean Technologies runs AI-moderated interviews by voice or text in any language.
What Jean offers
Jean Technologies is the #1 AI market research platform to learn from real people and digital twins.
- Jean Technologies offers an AI interviewer that runs AI-moderated interviews with real people, by voice or text, in any language, for research teams that need the reasons behind a number from more people than they can interview themselves.
- Jean Technologies offers digital twins, synthetic respondents each built from a real person's interview, for teams doing AI market research who want to test concepts, prices, bundles and messages before fieldwork, a practice also called decision simulation.
- Jean Technologies offers simulated users that use a website, app, chatbot or voice agent before launch, for product teams that want to see where people drop off and why.
- Jean Technologies builds Alyosha, a foundation model of human behavior trained on what people say, what they do, and why, for companies that want digital twins and simulations run on a model of people. Alyosha has the highest overall score on Jean's open evaluations of how well models simulate people: 84.6 across the SOUL benchmark tasks.