Evaluate design through the lens of a simulated Japanese customer.



Year: 2026 | Industry: Fintech | Region: Japan |  Role: UX Strategist/Prompt Engineer | Team: UX Research | Deliverable: Lived Experience GPT (Chat GPT)
  • Our offshore teams and remote workers unfortunately cannot engage with their Japanese customers on a regular basis, and they need a way to close that gap. Simulated personas come in many shapes and sizes, but they often represent Japanese customers in a superficial, and sometimes even caricatured, way. The challenge was to develop a GPT that comes as close as possible to the lived experience of a real Japanese person.

  • The UX Research team decided to develop two distinct GPTs: one that identifies a persona, and one that determines how a real person would evaluate a design proposal.

The persona GPT combines every day Japanese behavior, financial habits, social norms and economic context.
The design review GPT uses besides socio-economic and cultural context, the core Japanese user and its associated user behavior as main inputs.
  • Both GPTs are optimized for simplicity. A designer uploads a document or idea, and the GPT generates a structured persona or evaluation in plain English with minimal business jargon, ready to share in a slide deck or in Slack.

  • The persona result includes:
1. Target group
2. Socio-economic and cultural context
3. Personel perspective
4. What designers should understand
5. Assumptions
6. Next steps

  • The design review result includes:
1. Core Japanese user
2. First reaction 
3. Biggest friction
4. Likely action
5. Assumptions
6. Next steps

  • Both GPTs have become either starting points or pivotal review moments in design projects. Even though the latest company data sets have been used and hallucinations have been kept to a minimum, the UX research team has emphasized that the results are indicative and do not represent real Japanese users.

Special thanks to the UX research team: Beau Tana, Pallavi Varma, Jane Susiriwatananont.