Help Centre › Building Processes
This article describes the RPA Browser functionality to interact with the browser using AI.
For a full list of available functions, please read BROWSER functions.
Description
The BROWSER Interact with AI function allows you to use artificial intelligence to perform a natural language browser action, such as clicking a button, typing into a field, or selecting a dropdown option.
Setting it up
To use the BROWSER Interact with AI function, follow these instructions:
{{popups:rpas/add:action=browser-interact}}
Once on a process map:
- Navigate to the process where you would like to add the BROWSER Interact with AI function
- Click on the green button’s drop-down (right side of the green button labelled “Process”)
- On the menu that appears, click on the “+ Activity” item
- From here you can select the BROWSER Interact with AI option
- Click "Add" once you are done
Input parameters
| Parameter | Required | Type | Default | Description |
|---|---|---|---|---|
| Instruction | Yes | Textarea | – | Natural language instruction describing the action to perform (e.g. “click the login button”, “type hello in the search box”). |
| Variable | No | Text | interact | Variable name to store the result. |
Output variables
| Variable | Type | Description |
|---|---|---|
| Variable | Dictionary | A dictionary with keys: action (string), selector (string), success (boolean). |
Errors
| Error | Description |
|---|---|
| Browser not open | No browser session is active. |
| Action failed | The AI could not perform the requested action. |
Tips
- Supported actions include: click, write, select, check, uncheck, double_click, set_input_value, and press.
- This function is AI-powered and maps your natural language instruction to the appropriate browser action.