A synthetic user is an AI-generated profile. They simulate how a target audience (persona) thinks, decides and reacts. Test a product, a message or a policy on synthetic respondents and see what they would do, and why.
How To Create Synthetic Users
While general-purpose AI chatbots can be used to create synthetic users, there are also dedicated AI-based platforms designed for this task.
To generate these AI-generated users, Researchers provide information on their target audience, study goal and interview type, then the platform provide a set of persona-like profiles and interview transcripts.
Within a few seconds, your synthetic users have been created, and interview transcripts are ready to read. These products provide the ability to ask follow-up questions and continue the interview.
Run problem-exploration interviews to surface user behaviors, pain points, and context — then arrive at organic research with sharper questions and stronger hypotheses.
Where Synthetic User Research May Fits Your Workflow
Synthetic users are designed as a discovery co-pilot, not a replacement for real research. Use it to front-load the problem space, fine-tune your questions, and spend your organic research budget where it matters most:
Early exploration & problem discovery. Map the problem space before committing to a full study. Run Problem Exploration interviews to surface user behaviors, pain points, and context — and arrive at organic research with better questions.
Concept & messaging testing. Test ideas, product concepts, and campaign messaging before launch. Use Concept Testing and Custom Script Interviews to get structured feedback on multiple directions in parallel — in minutes, not weeks.
Continuous insight between research phases. Fill the gaps when traditional research is too slow, too expensive, or impossible to schedule. Run iterative validation studies throughout the product lifecycle — not just at milestone moments.
How to Use Synthetic User Findings
Some of what you learn from synthetic users’ findings may be inaccurate or misrepresentative. Without real human research, you won’t catch and correct those inaccuracies. You may make incorrect business decisions that may cause rework, loss of time and money – or worse, loss of customers or lawsuits. Here’s how to use synthetic user findings safely, to maximize its benefits and avoid its risks.
- People’s online thinking and behaviors are different from their real-life persona. As a result, the data generated with synthetic users is skewed and not an accurate reflection of what people really think or do. Nothing replaces contextual inquiry.
- Treat the data you acquire from synthetic users as hypotheses that need testing. Synthetic user data can be useful for developing proto personas or proto journey maps that are revisited and refined after doing research with real people.
- Do not present synthetic-user research findings as real human research findings. This is an unethical and creates the risk of permanently damaging the perception of your research and brand. Always be clear about where your findings came from.
XD professionals and product teams should treat synthetic user findings as hypotheses that need testing. Synthetic users can be used to help with initial research about new audiences and to generate hypotheses and ideas that should be tested through research with real people.
Real human research is essential. Synthetic users cannot replace the depth and empathy gained from studying and speaking with real people.
Supplement – don’t substitute. If you’re using synthetic users in your research process, they should complement, not replace, real research.
Use synthetic research for specific purposes. Synthetic users are useful research and generating hypotheses, but not for final decision-making.
—
Rosala, Maria and Moran, Kate. Synthetic Users: If, When, and How to Use AI-Generated “Research”. NNGroup. June 21, 2024. https://www.nngroup.com/articles/synthetic-users/
Synthetic Users.com. https://www.syntheticusers.com