Before launching a website redesign, adjusting an e-commerce conversion funnel, or repositioning an offering, user interviews are at the heart of UX experts' work. They allow us to understand how a product's users actually think: what hinders them, what builds their trust, what makes them act or not. These structured conversations are conducted to gather what data does not show. Today, AI tools promise to do the same thing, faster and at a lower cost.
Can artificial intelligence conduct user interviews? What uses of AI are genuinely useful in UX Research? What are the current limitations of these tools?
In this article, discover what AI can truly bring to user research, the situations where it offers a productivity gain, and those where human intervention remains indispensable.
Pourquoi faire des entretiens utilisateurs ?
Web analytics tools measure what happens: how many people clicked, at what stage they dropped off, what content was viewed. This is quantitative analysis. What these tools don't tell you is why. Why this form is off-putting, why this page generates poorly qualified leads, why a logical user journey on paper doesn't match how your customers actually think.
These are precisely the questions that user interviews exist to answer. These are structured conversations, conducted with people representative of the target audiences, to understand their needs, their barriers, and the logic that guides their decisions. The aim is not to collect opinions, but to observe how they think in the face of a real situation and to gather qualitative analysis.
- Why would a qualified visitor leave without making contact
- What vocabulary do the targets use to describe their problem and does it match that of the website?
- At what point in the journey is trust built or lost?
- What decision criteria are not addressed in the content?
Les entretiens utilisateurs s'inscrivent généralement dans les premières étapes d'un projet, souvent pendant la phase de découverte ou de recherche. Ils sont essentiels pour comprendre les besoins, les motivations, les comportements et les points douloureux des utilisateurs finaux. Ces informations aident à définir le problème, à identifier les opportunités et à guider la conception et le développement du produit ou du service.
User interviews typically take place before a significant decision: before a redesign, before the launch of a new service, or before reworking a conversion funnel. They allow you to ask the right questions before committing resources. Their role is to reduce the risk of building something well-designed but poorly oriented.
They can also intervene after a launch, to understand why the results are not as expected despite a technically sound system. In this case, they complement the quantitative analysis: the data shows where the problem lies, and the interviews explain why.
What AI can and cannot do in user interviews
The study Navigating the Jagged Technological Frontier (Dell’Acqua et al., Harvard Business School / Boston Consulting Group, 2023), a study of 758 consultants, highlights that AI significantly improves performance on formalised tasks – summarising, drafting, structured analysis – but impairs the quality of judgement on tasks requiring a nuanced contextual understanding. For the latter, participants using AI produced results that were 19% less reliable than those working without it. The authors refer to this phenomenon as the «Jagged Technological Frontier»: AI excels where the task is clearly defined and fails where it is not precisely defined.
Thus, AI tools can today analyse large volumes of verbatim feedback, group recurring themes in customer returns or generate summaries from transcripts. These uses are relevant and AI excels at them: they speed up the processing of what has already been collected.
However, AI cannot and should not conduct an interview in place of a human because it fails in this fine reading. This is the case with the physical and social experience that unfolds during a user interview: vocal intonation, gestures, hesitations, silences. The same statement, depending on the intonation, can be interpreted as negative or positive by a human, whereas AI will not perceive the nuance.
Jakob Nielsen, a pioneer in web usability, speaks of a gap and the AI's inability to capture users« behavioural nuances. The AI lacks understanding of the physical and social experience that allows a human researcher to grasp what is happening in the room, not just what is being said. A participant who replies »yes, that's very good" while crossing their arms and looking away communicates something that no AI language model will understand.
In the case of digital accessibility, Replacing user interviews with AI would mean missing the point. It's through usage and interaction that we can understand how a person with a disability navigates and the issues they might encounter. For example, two people using the same assistive tool can have radically different navigation strategies. It is precisely this diversity of usage that makes direct observation of the people concerned indispensable. No modelling can replace this real-world confrontation today.
L’IA peut assister les chercheurs UX dans plusieurs cas : * **Analyse de données à grande échelle :** L'IA peut rapidement analyser de grands volumes de données qualitatives et quantitatives (verbatims utilisateurs, notes d'entretiens, données comportementales) pour identifier des tendances, des schémas et des points douloureux qui seraient difficiles à détecter manuellement. * **Génération d'hypothèses :** En analysant les données existantes, l'IA peut suggérer des hypotheses sur les problèmes utilisateurs ou les opportunités et aider à orienter les recherches futures. * **Personnalisation des expériences :** L'IA peut aider à segmenter les utilisateurs en groupes plus fins et à comprendre leurs besoins spécifiques, permettant ainsi de concevoir des expériences plus personnalisées. * **Création de personas :** L'IA peut aider à construire des personas plus précis et basés sur des données, en synthétisant les informations provenant de diverses sources. * **Identification de problèmes d'utilisabilité :** Les outils basés sur l'IA peuvent analyser des sessions utilisateurs enregistrées pour détecter automatiquement des frictions, des erreurs ou des points de blocage dans une interface. * **Sélection et recrutement de participants :** L'IA peut aider à identifier et à contacter des participants potentiels pour des études UX en fonction de critères spécifiques. * **Automatisation des tâches répétitives :** L'IA peut automatiser la transcription d'entretiens, la classification de retours utilisateurs ou la génération de rapports préliminaires, libérant ainsi du temps pour les chercheurs. * **Tests A/B et optimisation :** L'IA peut aider à concevoir et à analyser des tests A/B plus efficaces, en identifiant les variables les plus pertinentes à tester et en interprétant les résultats. * **Prédiction du comportement utilisateur :** Dans certains cas, l'IA peut être utilisée pour prédire comment les utilisateurs vont interagir avec un produit ou un service. * **Conception et génération de contenu :** L'IA peut aider à générer des brouillons de textes, des options de libellés ou même des idées de conception basées sur les données et les meilleures pratiques.
AI and user interviews can absolutely coexist in a research process, provided each is assigned its appropriate role.
Some tools even offer to conduct conversational interviews with users automatically. These systems can be useful for quickly gathering a large volume of feedback on simple topics or for exploring hypotheses. However, they do not replace research interviews when the objective is to understand complex decision-making mechanisms, observe behaviours, or adapt questions based on the participant's reactions.
Before the pitch
AI can help structure preparation: it can formulate an interview guide, generate hypotheses from existing data, and identify unexplored angles in previous research. This is a useful formatting and bootstrapping task but does not replace the researcher's judgment to validate what is worth exploring.
On the field
When it comes to understanding complex reasoning or uses, AI does not replace the interviewer. On the other hand, certain transcription or automated note-taking tools can reduce the researcher's cognitive load during the interview.
After the pitch
It is perhaps after fieldwork that AI brings the most: transcribing, grouping verbatim comments, identifying thematic recurrences in a volume of data that a human alone would process more slowly and less systematically. On this front, the gains are real. The Harvard/BCG study mentioned above confirms this: for structured and well-defined tasks (summarising, categorising, rephrasing), AI significantly improves processing speed and quality.
The challenge is not to pit AI against user research but to identify what can be automated and what requires contextual human interpretation. Using AI to group existing verbatim feedback is one thing. Replacing interviews with AI is another. In the first case, we speed up a process. In the second, we eliminate the source of information itself and make decisions based on assumptions that we believe we have verified but have never been tested against reality.
Overall, AI is a productivity tool for UX researchers and experts: it compresses processing time, reduces repetitive work and allows for larger volumes to be covered. However, it operates downstream of the collection process, not in its place. The UX expert remains the guarantor of what is collected, of the interpretation, and of the resulting recommendations.
User interviews allow us to understand why your targets behave as they do. They inform structuring decisions in digital projects to understand usage and avoid all assumptions.
AI finds its full place in this approach, but downstream and as a productivity tool: for transcribing, grouping, and identifying recurring patterns in what has already been collected. On these well-defined tasks, the gains are real and documented. What it cannot do is replace the encounter itself or capture what plays out beyond the words. The challenge is therefore not to choose between AI and user research, but to distinguish what can be automated and what requires the interpretation of a human situation. This distinction directly influences the quality of the decisions made in a digital project.