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

# Scenario Adherence

> Test that your agent follows a required flow.

Use this type when your agent must follow a fixed flow, for example a compliance script or an identity check.

## Build a scenario

Draw the flow as a scenario on the **Scenario Builder** page, and select the agents that it applies to. If you have a [JSON scenario definition](/api-reference/endpoint/create-scenario.md), import it instead.

* Each path from the start to an end becomes one Digital Human, so each branch you add adds a test.
* Each Digital Human follows its path turn by turn, so you can see where your agent leaves the flow.

![Scenario Builder canvas with the toolbox, a start node, agent and user turns, and a three-way branch that rejoins at a final user turn](https://mintcdn.com/bluejay/eKcFBkjZX47pI8Ss/images/workflows.png?fit=max\&auto=format\&n=eKcFBkjZX47pI8Ss\&q=85\&s=54dc1ed91d73441a05ce3061a31b17a7)

## Run it

**1. Select the card**

[Create a simulation](/test/simulations/create.md#create-a-simulation) and select the **Scenario Adherence** card.

![Scenario Adherence card in the Create Simulation type picker](https://mintcdn.com/bluejay/EeUk0hD_moG9tWmI/images/create-simulation-card-scenario-adherence.png?fit=max\&auto=format\&n=EeUk0hD_moG9tWmI\&q=85\&s=263c7a638310187e934203e044677fb6)

**2. Pick the scenarios**

A scenario with no path from the start cannot be selected, so fix its graph first.

With the API, pass `workflow_adherence_v2`, a map of scenario ID to the number of Digital Humans, to [Generate Digital Humans](/api-reference/endpoint/generate-digital-humans.md).

## Limits

* Voice agents only.
* Bluejay makes a maximum of 200 Digital Humans for each generate request. Paths beyond that are left out.

## Related

* [IVR Flow](/test/simulation-types/ivr-flow.md)
* [Scenario API](/api-reference/endpoint/create-scenario.md)
* [Scenario MCP tools](/mcp/testing-tools.md#scenarios)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.