Documentation

A complete reference for how Behavioural Engines works — its models, workflow, features, and design boundaries.

Overview

Behavioural Engines is a structured simulation platform grounded in formal behavioural science. It translates academic models — Prospect Theory, Hyperbolic Discounting, Rational Inattention, and others — into an interactive environment where you can configure parameters, run deterministic simulations, compare results, and export outputs.

The platform is designed for thinking, not prediction. It clarifies how behavioural mechanisms operate under controlled conditions. Every model is grounded in peer-reviewed literature with full citations, mathematical specifications, and equation notation.

Why it exists

The foundational models in behavioural science live in papers and textbooks, and if you want to actually run one you are usually setting up a research environment, writing code from scratch, or working around whatever a statistics package happens to support. There is no well-designed, accessible, browser-native repository where the canonical models sit together in one place and you can just use them.

This is where Behavioural Engines comes in. Each model is implemented directly from its source literature with the correct mathematics, given sensible parameter controls, and made interactive so you can see what happens as you change the inputs. The point is understanding how these models actually behave and seeing what outputs they produce visually.

Workflow

Select a model

Choose from six formal behavioural models in the workspace. Use ⌘K or the top-bar tabs to switch between them instantly.

Configure parameters

Adjust core and advanced structural coefficients. Load a saved preset or pick from the curated scenario library to get started quickly.

Run the simulation

Hit Run Simulation (or ⌘↵). The backend computes a deterministic output and returns bounded probability outputs, metric results, and chart data.

Compare & explore

Pin the result as a baseline, tweak parameters, and run again. Both outputs appear side-by-side in the Analysis panel and on all charts as overlay lines.

Review & export

Every run is saved to your History with a searchable name. Pro users can re-run from history, copy shareable links, and export as PDF, CSV, or JSON.

Models

Structural Adoption

Applied Microeconomics

Logistic structural model estimating bounded adoption probability from behavioural levers with diminishing incentive returns.

Prospect Theory

Behavioural Economics

Non-linear value model with probability weighting and loss aversion.

Hyperbolic Discounting

Behavioural Economics

Comparative intertemporal choice model contrasting hyperbolic and exponential time discounting.

Expected Utility Theory

Classical Economics

Normative decision model computing expected utility under constant relative risk aversion (CRRA).

Inequity Aversion (Fehr–Schmidt)

Behavioural Economics

Structural social-preference model where utility depends not only on one's own payoff but also on payoff differences relative to others.

Rational Inattention

Behavioural Economics

Decision model where agents optimally limit attention due to costly information processing.

Platform Features

Workspace

Parameter control

Every structural coefficient is adjustable — both core inputs and advanced options collapsed behind a toggleable panel.

Parameter presets

Save named configurations per model. Presets sync across devices for signed-in users via server-side storage.

Scenario library

Pre-built scenarios for each model illustrate canonical real-world conditions — a fast starting point for exploration.

Command palette

Press ⌘K (or Ctrl+K) to open a searchable command palette. Navigate to any model or page without touching the mouse.

Simulation & Analysis

Comparison mode

Pin any result as a baseline, then adjust parameters and re-run. Metric panels show both side-by-side; charts overlay dashed baseline lines against solid current lines.

Visual charts

Recharts-powered curve visualisations for every model — value functions, discount curves, probability weighting, and more.

Live analysis

Results appear in a structured analysis panel with clearly labelled metrics, colour-coded by sign, immediately after each run.

History

Simulation logs

Every run is stored with its full parameters, results, model version, and timestamp. Paginated and searchable.

Named runs

Give any simulation run a custom name directly from the History page or the detail view. Names sync across devices.

Re-run

Load any past simulation's parameters back into the workspace with one click and re-run with modifications.

Exports & Sharing

Export as PDF

Generate a formatted PDF of your simulation — parameters, results, and metadata — for reports and documentation.

Export as CSV

Download structured tabular output for further analysis in Excel, Python, R, or any data tool.

Export as JSON

Retrieve the full simulation object as JSON — useful for integration with custom pipelines or downstream processing.

Shareable links

Copy a direct link to any saved simulation run and share it with colleagues. The link preserves parameters and results.

Boundaries & Assumptions

Understanding what this platform is not:

Not a forecasting engine for real populations or empirical datasets.
Not a substitute for field trials, experiments, or empirical calibration.
Not a claim that human behaviour is fully captured by any single model.
Outputs are structural and deterministic — they reflect the model, not observed data.
Parameters are illustrative unless calibrated against real measurements.

Behaviour is probabilistic, not deterministic. Incentives interact with perception, not just objective value. Friction reduces action even when incentives are positive. Social adoption can amplify small initial differences. Every output reflects the model structure — not an empirical claim about any population.