> For the complete documentation index, see [llms.txt](https://docs.rootcause.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.rootcause.ai/more-details/digital-twin/simulation-types.md).

# Simulation Types

A simulation uses a [Digital Twin](/more-details/digital-twin.md), which is RootCause's runnable causal model of your business, to answer a specific kind of question. Each simulation type runs on the same underlying twin but is configured for a different purpose: predicting outcomes, testing interventions, finding optimal inputs, diagnosing anomalies, and more.

This section has one page per simulation type, covering when to use it, how to set it up, and how to read the result. For the workflow that produces a Digital Twin in the first place, see [Step 5: Build Digital Twin](/user-guide/creating-digital-twin.md).

## The seven types

Static Digital Twins support seven simulation types.

| # | Type                                                                                      | Question it answers                                          |
| - | ----------------------------------------------------------------------------------------- | ------------------------------------------------------------ |
| 1 | [Prediction](/more-details/digital-twin/simulation-types/prediction.md)                   | What outcome is most likely for a specific input?            |
| 2 | [Intervention](/more-details/digital-twin/simulation-types/intervention.md)               | What happens if we change variable X?                        |
| 3 | [Optimization](/more-details/digital-twin/simulation-types/optimization.md)               | What combination of inputs best achieves our goal?           |
| 4 | [Best Action](/more-details/digital-twin/simulation-types/best-action.md)                 | What is the minimum change needed to reach a target outcome? |
| 5 | [Explanation](/more-details/digital-twin/simulation-types/explanation.md)                 | What drives an outcome, and what does a cause influence?     |
| 6 | [Root Cause Analysis](/more-details/digital-twin/simulation-types/root-cause-analysis.md) | What caused this specific observed outcome?                  |
| 7 | [Anomaly Scan & Diagnosis](/more-details/digital-twin/simulation-types/anomaly-scan.md)   | Which records are anomalous, and why?                        |

Temporal Digital Twins, those built on time-series data, support the same seven questions in time-aware form, plus the temporal-only **Causal Health Monitor**. **Forecast** takes Prediction's place: a series has no single row to predict from. See [Temporal Simulations](/more-details/digital-twin/temporal-simulations.md).

Panel (multi-environment) twins get per-environment **Panel** variants. A multi-environment *static* twin supports all seven, Prediction included; a multi-environment *temporal* one follows the temporal family and forecasts instead.

## Outside the UI

Every type on this page runs from the Python SDK and from the REST API, with the same configuration the wizard collects: one verb per family in [Working with Digital Twins](/api-and-integrations/sdk-getting-started/sdk-working-with-twins.md), and one request body per family in [Running Simulations over REST](/api-and-integrations/rest-running-simulations.md). The REST page also carries the table of which scenario `type` to send for which twin kind, since the same question is spelled differently across kinds.