# What Works & What Doesn’t

This section outlines the authoring and execution patterns that produce reliable results in Drizz, along with common anti-patterns that can lead to inconsistent or unexpected behavior. It is intended to help teams write clear, deterministic test steps, avoid ambiguity, and ensure stable execution across devices and environments. By following these guidelines, teams can improve test reliability, reduce execution failures, and scale automation with confidence.

#### What **Works**

1. Clear, single-line commands
2. Explicit context
3. Strict syntax for system commands
4. Scrolls with direction
5. MAP\_ACTION with intent
6. Stable device connection
7. Correct app identifiers
8. Proper Xcode/Android Studio setup
9. Clean conditional blocks
10. Unique memory variable names

#### **Doesn’t Work**

1. Multi-action lines
2. Ambiguous command instructions
3. Loose system command phrasing
4. Missing direction or container context
5. Running without device setup
6. Imprecise conditional logic
7. Overwriting memory 


---

# Agent Instructions: 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/getting-started/overview/drizz-usage-expectations-and-operational-guidelines/what-works-and-what-doesnt.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.