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

# Simulation

> Rehearse a decision against a simulated population before it meets the real one.

<Warning>
  **Research direction.** This is the least built of the four. We are describing where the backbone leads, not shipping it. [Reach out](mailto:jonathan@jeantechnologies.com) if this is the problem you have.
</Warning>

Once you have a model that predicts what a person does next, you can run it forward. Point it at a population, change one thing about the world, and watch what the population does differently.

That turns a lot of expensive, slow, one-shot decisions into something you can rehearse:

<CardGroup cols={2}>
  <Card title="Product" icon="box">
    Test demand, feature tradeoffs, pricing, and switching behavior before committing engineering to any of them.
  </Card>

  <Card title="Messaging" icon="megaphone">
    Positioning, creative, and offers, evaluated against a population rather than a focus group of twelve.
  </Card>

  <Card title="Segmentation" icon="users">
    Find the groups that actually behave differently, instead of the demographic buckets you inherited.
  </Card>

  <Card title="Scenario planning" icon="git-branch">
    Stress-test a strategy against competitive moves and economic shifts that have not happened yet.
  </Card>

  <Card title="Communications" icon="radio">
    Preview how an announcement reads to the people who will actually receive it.
  </Card>

  <Card title="Policy" icon="scale">
    Model the second-order response to a rule change before the rule ships.
  </Card>
</CardGroup>

## Why we think this belongs on a behavioral backbone

The companies doing this well right now are worth studying. [Simile](https://www.simile.com/) built generative agents grounded in interviews and survey responses. [Aaru](https://www.aaru.com/) frames the pitch precisely: ask people and they answer, simulate them and they act. [Demosyne](http://demosyne.com/) runs long-lived worlds where the consequences compound over months rather than resolving in a single prompt.

The shared insight is that stated preference is a poor substitute for revealed preference. People misremember, rationalize, and tell you what they think you want.

Our angle is on the substrate. Most simulation today puts a language model in a persona and asks it to behave like a person, which inherits everything the language model knows about how people *describe* themselves. A [foundation model of behavior](/products/foundation-models) is trained on sequences of what people actually did. If that model is good, it should be the better engine to simulate from, because it never had to route through self-report.

That is a claim, not a result. It is the one we most want to test.

## How it would work

<Steps>
  <Step title="Ground a population" icon="users">
    Construct a population from real behavioral sequences, not from written personas. Sampled to match the distribution you care about.
  </Step>

  <Step title="Change a condition" icon="sliders-horizontal">
    Introduce the new price, the new feature, the new message, the new competitor.
  </Step>

  <Step title="Run it forward" icon="play">
    Each simulated actor produces a sequence of actions, not an opinion. Aggregate over the population.
  </Step>

  <Step title="Validate against holdout" icon="check">
    The only thing that makes this useful is correlation with a real outcome you withheld. No engagement runs without that check.
  </Step>
</Steps>

<Note>
  **On validation.** A simulation that cannot be scored against reality is a very expensive way to produce a confident number. If we work on this with you, agreeing the holdout comes before agreeing the scope.
</Note>

## The rest of the downstream surface

Simulation is one thing a behavioral backbone unlocks. The others are closer in and mostly follow the same pattern of adapting one pretrained model rather than building a new system:

| Task                | What the backbone provides                                                           |
| ------------------- | ------------------------------------------------------------------------------------ |
| **Recommendation**  | Shipping first. See [Foundation models](/products/foundation-models).                |
| **Matching**        | Compatibility between two people, scored on outcomes rather than stated preferences. |
| **Personalization** | Assistants that adapt to how you work without being told each session.               |
| **Memory**          | Deciding what context about a person is worth keeping and surfacing.                 |

<Card title="Talk to the team" icon="mail" href="mailto:jonathan@jeantechnologies.com" horizontal>
  [jonathan@jeantechnologies.com](mailto:jonathan@jeantechnologies.com)
</Card>