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

# Tests vs. simulations

> Tests specify user messages and checks on agent turns. Simulations describe a user scenario and an outcome, then let AI generate that part of the conversation.

## Overview

Tests specify user messages and checks on agent turns. Simulations describe a user scenario and an outcome, then let AI generate that part of the conversation. Both exercise your agent in the selected environment.

<a id="choose-the-conversation-style"></a>

## Choose the conversation style

Use scripted turns when a known input or sequence must produce a particular response, route, or tool call.

**Tip:** 

Use **scripted turns** when a known input or sequence must produce a particular response, route, or tool call. Use a **simulation** when the user can take different paths toward the same outcome. A test conversation can contain both.

<a id="compare-behavior"></a>

## Compare behavior

Compare messages, checks, conversation length and starting context for Tests and Simulations.

| Dimension | Scripted tests | Simulations |
| --- | --- | --- |
| User messages | You write exact messages. | AI generates messages from a scenario. |
| Expected behavior | Response, routing, and tool-call checks on agent turns. | Success criteria for the simulated conversation. |
| Conversation length | The sequence of turns you author. | A configured maximum conversation turn count. |
| Best fit | Repeating a known regression or checking a precise interaction. | Exploring different paths through a realistic user scenario. |
| Starting context | Launch event and starting variables/persona. | The same saved conversation context. |
| Execution | Run from the shared editor or Tests list. | Run the conversation containing the simulation through those same controls. |

<a id="the-same-support-scenario"></a>

## The same support scenario

For an order-status agent, a scripted test can send “Where is order 123?” and check that the order lookup tool was called.

For an order-status agent, a scripted test can send “Where is order 123?” and check that the order lookup tool was called. A simulation can describe a customer who has lost their order number and passes only when the agent provides an appropriate next step. The second example tests the outcome across generated messages rather than fixing every user reply.

<a id="shared-editor-and-saved-conversations"></a>

## Shared editor and saved conversations

Open Tests and New test to author either approach in the shared editor.

**Note:** 

Open **Tests** and **New test** to author either approach in the shared editor. A saved conversation can combine scripted and simulated segments. Its selected launch event and starting persona or variable values apply to both styles.

<a id="explore-each-approach"></a>

## Explore each approach

Compare the Test editor with the Simulation editor.

- [Test editor](/docs/documentation/measure/tests)
- [Simulation editor](/docs/platform/rehearsal/simulations/editor)
- [Run tests and simulations](/docs/platform/rehearsal/runs/running)
