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

# Act towards goal

> Use the act() command to accomplish tasks with natural language

The [`act()`](/04-reference/01-agent-frameworks/02-python/02-vision-agent-api/agent#act) command lets you describe what you want to achieve in natural language, and the AI agent figures out how to do it.

## Basic Usage

```python theme={null}
from askui import VisionAgent

with VisionAgent() as agent:
    agent.tools.webbrowser.open_new("https://docs.askui.com")
    agent.wait(3)  # Wait for page to load

    agent.act("open the search field and search for agentic instructions")
```

## When to Use act()

Use [`act()`](/04-reference/01-agent-frameworks/02-python/02-vision-agent-api/agent#act) when you want to:

* Quickly prototype an automation
* Handle complex multi-step workflows
* Work with UIs that change frequently
* Let the AI figure out the best approach

For more control over individual steps, see the guides on [selecting elements](./01-select-elements) and [extracting data](./02-extract-data).

## Learn More

For advanced prompting techniques and best practices, see [Agentic Mode Best Practices](/03-explanation/02-best-practices/04-agentic-mode) which covers:

* Using "simulate" for enhanced stability
* Adding verification conditions
* Working with multiple approaches for actions
* Handling complex conditional logic