> ## Documentation Index
> Fetch the complete documentation index at: https://docs.semilattice.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# User models

> What user models are, how they're built, and what makes them useful.

<AccordionGroup>
  <Accordion title="What is a user model?">
    A user model is an AI representation of a specific group of people. It's built from real human data and predicts how that group would answer questions they've never been asked. Think of it as a research panel that responds in seconds.
  </Accordion>

  <Accordion title="What ready-made user models are available?">
    50+ user models and growing. UK and US adults, 16 UK Consumer Finance segments (from Growing Families to Just About Managing), tech industry segments (developers, designers, data scientists), and B2B software buyers. Ready-made user models are free to use.
  </Accordion>

  <Accordion title="How are custom user models different?">
    Custom user models are built from your data: survey responses specific to your market, your customers, your users. They're private to your account and tested for accuracy using cross-validation.
  </Accordion>

  <Accordion title="What data do I need to build a custom user model?">
    Survey data with questions, answer options, and response distributions is the foundation. Minimum 4 questions, ideally 20+. The more relevant and varied the seed data, the better the model generalises to new questions. We're also beginning to work with other types of data like qualitative interviews, product analytics and user feedback. [Get in touch →](https://app.semilattice.ai/user-models/request) if you'd like to find out more.
  </Accordion>

  <Accordion title="How do segments work?">
    Segments are separate user models representing subgroups within a broader category. For example, our UK Consumer Finance collection has 16 segments, each with different demographics, financial behaviours, and attitudes. You can ask the same question to multiple segments and compare how they respond.
  </Accordion>

  <Accordion title="Can a user model get better over time?">
    Yes. Adding more seed data improves coverage and accuracy. More questions give the model more context to draw on when predicting new ones. Accuracy is re-evaluated automatically after each update.
  </Accordion>

  <Accordion title="What happens if the model doesn't know?">
    Every prediction comes with an accuracy score. If the model has low confidence for a particular type of question, the score reflects that. You can see accuracy scores for every user model in the dashboard.
  </Accordion>
</AccordionGroup>