# Action Commands Action Commands represent the core interaction layer in Drizz. They are used to perform user-driven actions such as tapping, typing, scrolling, dragging, and validating content on the screen.\ Drizz interprets these commands using Vision AI and context-aware reasoning to reliably identify UI components without relying on fragile selectors or DOM dependencies. These commands are authored in natural language and mapped to deterministic actions during execution. Each Action Command corresponds to a single user intent, ensuring predictable behavior across Android, iOS, and mobile web applications.\ By combining visual understanding, contextual cues, and execution heuristics, Drizz delivers highly stable UI interactions even in dynamic, image-heavy or frequently updated interfaces. --- # 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/commands-reference/action-commands.md?ask= ``` 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.