The 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

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() 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 and extracting data.

​
Learn More

For advanced prompting techniques and best practices, see Agentic Mode Best Practices which covers:
  • Using “simulate” for enhanced stability
  • Adding verification conditions
  • Working with multiple approaches for actions
  • Handling complex conditional logic