You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Midscene is currently limited to interacting with the current viewport, but in real-world scenarios, we need to deal with elements not visible in the current viewport (e.g., elements that need to be revealed through scrolling). Some example cases include long forms or Apple's product pages like https://www.apple.com/iphone-16-pro/. I think using manual code to handle this before using .ai() is not ideal.
We are thinking about the way we interact with ai to send data, and we will be more flexible in the future, and maybe we can better handle problems like yours
Midscene is currently limited to interacting with the current viewport, but in real-world scenarios, we need to deal with elements not visible in the current viewport (e.g., elements that need to be revealed through scrolling). Some example cases include long forms or Apple's product pages like https://www.apple.com/iphone-16-pro/. I think using manual code to handle this before using .ai() is not ideal.
Does Midscene have any plans to support this? For reference, here's a similar implementation that handle all elements: https://github.com/browserbase/stagehand
The text was updated successfully, but these errors were encountered: