Download and resolve the workbook
The workflow starts Chrome download monitoring, clicks the .xlsx fixture through CDP, waits for completion, and retrieves the actual path chosen by the current browser.
Turn a spreadsheet into verified form submissions while preserving the outcome of every row in a separate Excel report.
The AI guide supplies a precise goal, safe target page, inputs, output contract, and verification rules. Paste that prompt into Runavelo's built-in assistant, then inspect and edit every generated command before execution.
Responsible use: adapt this pattern only for systems and data you are authorized to automate.
Each stage has a specific input, browser context, output, and verification point. Edit these commands directly when the destination system differs.
The workflow starts Chrome download monitoring, clicks the .xlsx fixture through CDP, waits for completion, and retrieves the actual path chosen by the current browser.
A spreadsheet loop skips the header row and exposes each remaining row as a structured list, without embedding a developer-specific file location.
CSS selectors locate the destination fields. Text uses CDP silent input, the department is selected by visible text, the date is assigned through the page DOM, and checkbox state follows the workbook value.
A CDP silent click submits the form. The workflow reads the live status element after each row and stores that page-confirmed message with the source email.
Runavelo resolves the current user Documents directory, writes all outcomes to Excel, closes the workbook, and logs its complete path.
Runavelo's runtime log connects the visible workflow line to its result. That makes missing elements, rejected updates, and unexpected page states easier to locate than a generic success message.
Yes. The application downloads and reads an actual .xlsx workbook, then creates a second workbook containing the per-row results.
Yes. Add a CSS element lookup after submission and append the returned ID to the result row before writing the workbook.
The prompt targets the matching test page and states the expected evidence. A reference QYA remains available for comparison with a verified implementation.