How does work? uses advanced AI and natural language processing to generate synthetic personas that can mimic real human behavior. The user inputs a persona’s characteristics, problem(s) that persona has, and the proposed solution, and the model runs virtual user interviews to gather feedback from the synthetic personas and then summarizes them in a complete report.

How accurate are the synthetic users generated by

We've been working hard to ensure the synthetic personas behave as though they were organic humans. Our success is measured by our ability to deliver that experience. Most important though is that you focus on the outcomes and less on the nature of the synthetic personas, i.e. ensure your customer base is represented but focus on the insights you are getting rather than the synthetic nature of our participants. As the term illustrates, Synthetic Users are composite creatures put together in the bowels of a neural network.

How does compare to traditional user research methods?

Synthetic Users has been designed to act as a discovery co-pilot. It accelerates an otherwise expensive and operationally taxing process.

How does handle diversity and representation of different user groups?

You decide your audience, the type of synthetic user or persona you want to interview. You may wish to run a discovery process with a very niche audience or a more heterogeneous bunch. You decide.

How does ensure the results are unbiased?

We don't. Biases have served us humans for hundreds of thousands of years as a way to accelerate learning. What is important is that we reveal the biases as parameters and allow our users the ability to change those in order to get the best insights. With real interviews you can gauge biases and write that in your notes. With Synthetic Users you'll be able to do the same.

How does handle privacy and data security?

We have to be honest. We are working on a layer above the Large Language Model and therefore we are at the mercy of its own policies. We suggest you familiarise yourself with their terms, as our terms sit on top of those.

How can we be sure that the feedback provided by synthetic users is valid?

We periodically compare the results run in a discovery process with real interviews with the same study but with synthetic users within Synthetic Users. Through our application layer we are always aiming to close the delta between analogue testing and Synthetic Users.