Learn · Examples

Monte Carlo simulation, explained by playing one

Monte Carlo simulation repeatedly solves a model with values drawn from its uncertain assumptions. The results show a range of possible outcomes under those assumptions, rather than one forecast.

How often does the household stay within its energy budget?

This is a playable answer made in flatland desk. Move its measured settings to explore the result. The assumptions are fictional.

Goal · 2027-01 through 2028-12

Energy and project cost no more than $7,000 over two years

Starting result

$6,594

Starting odds60 in 100
Selected levers79 in 100
Choices: Air sealing project cost (USD), Heating and cooling use reduced by settingsUncertainties: Heating and cooling demand multiplier, Electricity rate (USD per kWh)

On a narrow screen, scroll the answer sideways to see its full width. Use Tab to reach its settings and the arrow keys to change them.

Open the answer in its own tab · Download the model for desk

These results were measured when the answer was made. The page does not run new simulations. To change formulas or ranges, open the model in desk.

Read the model, assumptions and limits

Read possible outcomes

A range says how far an uncertain assumption could move. The engine draws values from the model’s ranges and solves the corresponding outcomes. A goal gives those outcomes a question to answer: how many meet the target?

The playable answer labels the odds and the range of costs. Its contours show measured settings with similar odds. Read the units and the goal first, then compare where the current setting lies.

Explore a choice

Move a lever in the playable answer. Compare its odds with the starting setting. Then move the goal: a more demanding target may remain hard to reach even with a better choice.

The HTML contains results measured by the real engine when the handoff was made. It explores those saved settings; it does not draw new samples or solve new formulas in your browser. Open the source model in desk to change its assumptions or relationships.

Scenarios and uncertainty answer different questions

Scenario planning names a set of assumptions to examine, such as a higher-price scenario. A Monte Carlo simulation explores the ranges allowed within a model. A scenario is not automatically assigned an odds figure simply because it has a name.

Neither method establishes that the assumptions are right. A narrow range can hide risk. An omitted relationship cannot appear in the results. Agent-proposed ranges remain guesses until the person confirms them or names a source.

Build your own model

flatland desk by Flatland Labs makes a quantitative model’s structure, behavior over time and possible futures visible.

Downloading and local use need no account. A plan includes the built-in agent and the handoff.

Why flatland exists, and where it’s going: Escape.