Actions And Dynamic Pages

Content sits behind a 'Load more' button; a plain scrape captures only the initial page state without the expanded content.

Use an actions sequence with a click action targeting the button (plus a wait) so the dynamic content loads before capture. Verify the post-action markdown includes the expanded content rather than the initial state.

A page requires typing a query into a search box and submitting before the target results render.

Use write/input actions to populate the field and a click/press action to submit, with waits between, so the results page renders before capture. Confirm the captured content reflects the submitted query.

Agent needs a screenshot of a specific UI state reached only after a series of clicks, but only requests a top-level screenshot format.

Place a screenshot action at the right point in the actions sequence to capture the intended interactive state. The format-level screenshot captures the final page; an in-sequence screenshot captures a specific step.