> For the complete documentation index, see [llms.txt](https://docs.drizz.dev/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.drizz.dev/fathom/running-a-test-with-fathom.md).

# Running a Test with Fathom

Prerequisites

Before starting a Fathom test run, ensure the following:

1. A local Android emulator is running
2. The emulator is connected to the Drizz Desktop App

#### Starting a Run

1. Open Fathom by clicking the chat icon in the top left of the page
2. Type the test intent in the chat window describing the scenario to execute
3. Fathom will begin executing the test on the connected emulator

#### During Execution

Fathom executes each step automatically. In some cases, the agent may encounter situations where it cannot determine the next action — for example, an unexpected application state, a navigation loop, or an ambiguous UI path.

When this occurs, Fathom will pause and prompt the user for guidance. Providing a clarification allows the agent to resume and continue the execution.

This human-in-the-loop mechanism ensures test runs can recover from complex or unexpected application behaviors.

#### Completing a Run

Once execution is complete, Fathom automatically generates a test script based on the actions performed. The script is available for review in the editor immediately after the run concludes.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.drizz.dev/fathom/running-a-test-with-fathom.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.