User research in the age of generative AI
Actualizado: 2026-05-03
User research has always been one of the most expensive disciplines in product teams. Recruiting participants, conducting interviews, transcribing, analyzing, and synthesizing takes weeks. Since 2023 generative AI has been promising to shorten each of those phases, and by 2025 there is enough track record to see which parts deliver and which do not. The answer is not symmetric: there are steps where AI is a clear improvement and others where it introduces a subtle risk of losing contact with the real user.
Key takeaways
- Automatic interview transcription is the most mature application: saves hours without losing quality.
- AI does well at initial note synthesis and guide preparation, but every quote in a final deliverable must be verified against the original transcript.
- Synthetic personas do not replace real participants: they produce plausible responses, not the useful surprises and contradictions.
- Reducing the number of real interviews because “AI fills in the gaps” is a statistical error: it reduces the chance of discovering what you didn’t know you didn’t know.
- The workflow that performs best: real interviews sufficient to capture variability, AI for transcription and first-pass analysis, humans for interpretation and decisions.
What AI does well in this field
Automatic transcription of interviews is probably the most mature and least controversial application. Tools like OpenAI’s Whisper, Deepgram[1], or services integrated into Zoom produce transcriptions with precision good enough for analysis, including timestamps and speaker separation. What used to cost an hour for every hour of interview now costs a few minutes of review. This saving is net: nothing is lost along the way.
Field note synthesis has also improved considerably. Models like Claude 3.5 or GPT-4o can summarize transcripts, group quotes by theme, and highlight contradictions between participants. The researcher still validates and refines, but the first step of qualitative analysis now takes minutes. That frees time for the genuinely hard part: interpreting what the patterns mean.
Finally, AI is useful in preparation: generating interview guides from research objectives, proposing question variants, detecting bias in phrasing, and translating materials across languages. The tool does not replace the researcher’s judgment, but it accelerates the initial draft.
Where AI fails or misleads
The most dangerous area is synthetic persona generation. Several tools promise to create simulated users to chat with to “understand” a segment without interviewing real people. The temptation is obvious: zero cost, instant response, round-the-clock availability. The problem is that what you get is not a person, it is the statistical average of the training corpus filtered by the prompt. A synthetic persona like “working mother, 35, Madrid” produces plausible answers, but without any of the contradictions, surprises, or intuitions that make a real interview useful.
I have seen teams make product decisions based on conversations with synthetic personas and later discover that real users thought something completely different. The model does not know what is not on the internet: local cultural nuances, family habits, specific frustrations with particular interfaces. Using synthetic personas as a substitute for real research is a shortcut that looks like it saves money and ends up multiplying the cost.
Another problem area is automatic analysis of raw interviews. Models can summarize, but they also invent quotes or attribute statements to the wrong participant when context is long. When analysis feeds important decisions, every quote going into a final document must be verified against the original transcript. AI is a good first pass; it is a bad single source of truth.
The risk of misunderstood efficiency
There is a tendency in teams adopting AI for research: reducing the number of real participants because “AI fills in the gaps.” This reasoning is fallacious for a specific statistical reason. The value of an interview is not in the average data point it provides, but in the possibility of surprise. Each additional interview has some probability of producing an insight that shifts the hypothesis. Halving interviews does not only halve the data, it halves the chance of discovering what you didn’t know you didn’t know.
AI can interpolate between data you already have, but it cannot extrapolate beyond them. If the initial research had sampling bias, the model will amplify it. If the sample was too small to capture a minority but critical segment, AI will not warn about the omission. These are blind spots that can only be detected by direct contact with real users.
A hybrid format that works
The workflow that performs best combines both layers:
- Real interviews, numerous enough to capture variability (typically 10-25 depending on the objective).
- Transcription and first-pass synthesis with AI.
- Semantic search over transcripts to answer team questions.
- Interpretation, prioritization, and decisions in human hands.
- Verified deliverables: every quote against the transcript, every pattern claim with concrete evidence.
AI also helps in later phases: answering “what did participants say about X?” with semantic search is fast and reliable. Generating initial reports with representative quotes works well. Translating findings across languages or adapting them to different internal audiences is also a task where current models perform.
My read
AI has reached user research the same way it has reached everywhere else: turning the tedious into the fast without changing what is fundamentally hard. Transcribing is no longer a problem. Summarizing is no longer a problem. Interpreting what users want and why remains just as hard as before, because the user is still human and the clues are still in their contradictions, not their averages.
For product teams, the practical recommendation is clear:
- Adopt AI for transcription and first-pass synthesis without reservation.
- Adopt it for guide and material preparation with review.
- Reject it as a substitute for real participants.
- Measure its help in time saved, not in interviews skipped.
Teams that tune their processes while preserving real contact with the user gain speed without losing quality. Those who use AI as an excuse to talk to fewer people end up with products that make sense on paper and fail in real hands.
