Method, evidence and limits
How Sunzu research works
Sunzu is an AI user research platform for product, design and marketing teams. It builds synthetic humans from customer data to run depth interviews, concept tests, UX tests and ad tests in minutes.
What is a synthetic human?
A synthetic human is an AI model of an audience member, used to explore how that person might respond to a research question, concept, design or advert. It is a simulation, not a recruited human participant.
Sunzu grounds those models in a company’s customer evidence and enriches them with a behavioural corpus. The aim is to produce findings that teams can trace and review, then use to sharpen the questions they take to real people.
What data grounds the research?
Customer evidence can include interview transcripts, surveys, support themes, CRM data, product analytics and previous research. That evidence anchors the audience; Sunzu’s behavioural corpus fills dimensions where the customer data is silent.
The corpus described on the Sunzu website contains 57M+ signals, 4k+ evidence sources, 1M+ profiles and 34M+ mapped attributes. These describe the evidence base, not the number of participants in any benchmark.
How are the models validated?
Sunzu’s methodology has two stages: data enrichment and behavioural modelling. Two validation gates check the model before it answers. Findings carry source references and confidence ratings; an explicit abstention is used where the evidence does not support an answer.
Internal back-testing
How does Sunzu compare with human findings?
Each percentage is relative to a human reference set to 100% for that study. The results measure themes covered, insights found or defects detected. They are separate comparisons, not an overall accuracy score.
| Study and measure | Sunzu in minutes | Human expert with AI in days | Human reference in months |
|---|---|---|---|
| Depth interviewsThemes covered | 76% | 54% | 100%Human insights, retested |
| Concept testingInsights found | 85% | 58% | 100%Research, 500+ humans |
| UX testingDefects detected | 75% | 34% | 100%Research, 500+ humans |
| Ad testingInsights found | 69% | 55% | 100%Research, 500+ humans |
What does “Human insights, retested” mean?
For depth interviews, the reference is the insights retrievable from the same humans when retested within a two-week interval. Sunzu covers 76% of the reference themes; a human expert with AI covers 54%.
Concept, UX and ad testing use research with 500+ humans as their reference. The time labels describe the compared research workflows; the two-week interval describes the depth-interview retest.
How should I interpret the sample-size comparisons?
- Depth interviews: equivalent to sample size of 6+ human users.
- Concept testing: equivalent to sample size of 30+ human users.
- UX testing: equivalent to hiring 5+ human UX experts.
- Ad testing: equivalent to sample size of 20+ human users.
These are Sunzu’s reported, study-specific equivalences. They do not mean synthetic participants are recruited humans, or that the same result is guaranteed for another audience or study.
Source: Sunzu product benchmarks. The methodology paper explains the approach and its limits. These figures come from Sunzu’s internal back-testing, not an independent certification.
Does Sunzu replace research with real people?
No. Synthetic research supports a faster first pass: explore directions, identify likely friction and focus the next human study. Lived emotion, cultural nuance and unexpected behaviour still require real people. Teams should review the evidence and use human research to validate consequential decisions.
The methodology paper describes these boundaries alongside the engineering and published literature.
Can I use Sunzu through MCP?
Sunzu supports depth interviews and concept tests through the Model Context Protocol, using Claude, ChatGPT or another compatible MCP client. UX testing and ad testing run in the web app.
Who provides Sunzu?
Sunzu is a service and brand of Sunzu, Inc., a Delaware corporation. Alpha Base OS Ltd. represents Sunzu in Europe, the United Kingdom and Switzerland. Company registration and contact details are available on the legal entity page.