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

# How Replicas Are Built

> The Engram Model, individual human encoding plus environmental adapters, and the pipeline that turns a real person into a replica

## The Engram Model

Rehearsals replicas are powered by Engram, a model built to replicate individual human decisions,
feelings, and actions. Unlike synthetic-persona approaches that prompt a general AI to roleplay a
demographic profile, Engram combines two components.

<CardGroup cols={2}>
  <Card title="Individual Human Encoding" icon="fingerprint" iconType="duotone">
    Each replica is built from rich, multi-modal data about a specific real person: structured
    voice and video interviews, social-media content, and factual demographic data. This captures
    what someone would choose and how they reason through a decision.
  </Card>

  <Card title="Environmental Adapters" icon="globe" iconType="duotone">
    People do not decide in a vacuum, and replicas should not either. Engram adapts each individual
    to real-world context: local news and social sentiment, macroeconomic conditions, nearby
    events, and product research a real person might do. Replicas react to the world the way real
    people do.
  </Card>
</CardGroup>

## What Goes Into a Replica

Every replica is grounded in real data about one real individual:

<CardGroup cols={2}>
  <Card title="Structured Interviews" icon="microphone">
    A rich onboarding interview to start, then a growing set of further vertical-specific
    interviews that continually enrich the replica. Designed by UX researchers and behavioral
    economists, they explore decision processes, values, constraints, and preferences.
  </Card>

  <Card title="Social Media" icon="share-nodes">
    Public content across major platforms (posts, images, video) that reveals interests,
    lifestyle, and voice.
  </Card>

  <Card title="Demographics & Personality" icon="chart-pie">
    Age, gender, location, education, household income, and career, along with personality traits
    like communication style, how they make decisions, their values, and interests.
  </Card>

  <Card title="Screening Facts" icon="filter">
    Verified answers a person gave when qualifying for a study, which become fixed facts a replica
    cannot contradict.
  </Card>
</CardGroup>

## The Four-Stage Construction Pipeline

<Steps>
  <Step title="Participant Recruitment" icon="users">
    We recruit participants so that our cohorts mirror the real population across age, household
    income, geography, education, and employment, matched to U.S. Census numbers.
  </Step>

  <Step title="Structured Interview" icon="comments">
    Each participant completes an in-depth onboarding interview covering product category usage,
    purchase decision processes and constraints, price sensitivity and value perception, media
    consumption, and their broader life context, priorities, and trade-offs. That onboarding is the
    starting point, not the whole picture: replicas are continually enriched with further
    interviews over time.
  </Step>

  <Step title="Replica Calibration" icon="sliders">
    Interview responses are processed into an individual replica that maintains the person's
    decision-making patterns, preserves their stated constraints and priorities, reflects their
    actual behavioral tendencies rather than idealized answers, and captures their voice and
    reasoning style.
  </Step>

  <Step title="Individual Validation" icon="circle-check">
    We evaluate accuracy per replica by holding out sections of a person's interview as a hidden
    test set, then checking whether their replica reproduces those answers without having seen
    them. For example, if someone said they would pay \$40 to \$60 for a pair of jeans, we confirm
    their replica lands in a similar range without being shown that number first.
  </Step>
</Steps>

## Cohorts: Grouping Replicas

Replicas are searchable and can be grouped into cohorts, which are filtered populations that
define who a given simulation should interview (for example, women 22 to 35 earning \$100K+).
Cohorts can be filtered on demographics, geography, income, and other attributes, and can be
balanced to match census-style distributions so the simulated population reflects the real one.

<Tip>
  A cohort can also carry up to three screening questions, evaluated per replica before a
  simulation runs, so you only interview people the study is actually about, the same way a human
  study screens participants. See [Building & Targeting a Cohort](/docs/platform/building-cohorts) for
  how this works in the product.
</Tip>

<Card title="Next: What Is a Simulation?" icon="flask" href="/docs/methodology/what-is-a-simulation" horizontal>
  Once replicas are built and grouped into a cohort, you can put a scenario in front of them.
</Card>