PrompteryxBeta
    ⌘K
    PlatformSupport
    Menu
    IntroductionInstall Desktop & extensionQuick StartPlatform Overview
    OverviewWhat you can makeAI Browser Agent in the chatModels and AutoConnectorsSchedulesProjectsExplore and publishingShare linksMemory and SkillsPersonal agent (beta)Welcome, settings and skinsPlans, credits and top-upsPrompteryx DesktopGroups (pilot)Phone app (early access)
    OverviewCreating WorkflowsTesting & DebuggingScheduling
    OverviewGetting StartedCommandsRecordingSettingsStructured OutputParallel AgentsTips & Best Practices
    OverviewInstallationSidebar AgentUsing Attached FilesExecute on Current TabExporting to Visual Studio
    Overview
    OverviewOpen PageClickClick CoordinatesFillExtract TextScreenshotWaitPress KeyFocus ElementBlur ElementSelect TextHighlight ElementSet ViewportGet Bounding BoxScrollHoverSelect OptionAssertionsCookiesEvaluate JavaScriptExample Workflows
    OverviewPrompteryx Browser AgentOpenAI
    OverviewSchedule TriggerWebhook Trigger
    OverviewGoogle SheetsGoogle CalendarConnect Hub (3,000+ apps)Example Workflows
    AI Vision SettingsChrome Automation ProfilesCloud BrowserBrowser Profiles & Persistent ContextVideo RecordingExecution LogsSharing & CollaborationEdit History
    Selectors GuideVariables
    Start hereGet an API keyRun the AI browser agentDrive a cloud browserRun workflows from anywhereUse connected apps (Connect Hub)SDK (TypeScript)CLIMCP for AI assistants
    REST APIWebhooksMCP toolsCloud Browser APICloud Browser quickstartMigrate from Browserbasen8nZapierMake.com

    Need help? Contact Support

    1. Documentation
    2. Nodes
    3. Browser Actions

    Browser Nodes

    Complete reference for all browser automation nodes

    Overview

    Browser nodes enable you to automate web browser interactions using Playwright. These nodes can control Chrome to perform actions like clicking, typing, extracting data, and more. Browser actions run on your machine through Prompteryx Desktop when you pick a Chrome profile, or on our Cloud Browser when you pick a Cloud Browser profile.

    Every browser automation workflow must start with an Open Page node to launch the browser and navigate to a URL. After that, you can chain together any combination of browser nodes.

    Navigation

    Open Page

    Navigate to a URL and load a web page

    Go Back

    Navigate back in browser history

    Go Forward

    Navigate forward in browser history

    Reload Page

    Refresh the current page

    Scroll to Element

    Scroll an element into view

    Mouse Wheel Scroll

    Scroll with the mouse wheel by a pixel amount

    Switch Tab

    Switch between browser tabs

    Close Tab

    Close a browser tab

    Interactions

    Click Element

    Click on page elements

    Double Click

    Double-click on elements

    Right Click

    Right-click for context menu

    Click Coordinates

    Click at specific X/Y position

    Hover

    Move mouse over elements

    Drag & Drop

    Drag elements to targets

    Tap Element

    Touch screen tap simulation

    Focus Element

    Focus on input elements

    Blur Element

    Remove focus from elements

    Forms & Input

    Fill Input

    Type text into form fields

    Fill Form

    Fill several fields in one step

    Clear Input

    Clear input field contents

    Press Key

    Press keyboard keys and shortcuts

    Select Option

    Select from dropdowns

    Check Checkbox

    Check checkboxes and radios

    Uncheck Checkbox

    Uncheck checkboxes

    Upload Files

    Upload files to forms

    Data Extraction

    Extract Text

    Get text content from elements

    Extract Data

    Turn a list on a page into records

    Get Inner Text

    Get visible text only

    Get Inner HTML

    Get HTML content of elements

    Extract Attribute

    Get element attributes

    Get Bounding Box

    Get element position and size

    Get Page Title

    Get the page title

    Get Page URL

    Get the current URL

    Screenshot

    Capture page or element images

    Get Cookies

    Read browser cookies

    State Checks (Is/Has)

    Is Visible?

    Check if element is visible

    Is Hidden?

    Check if element is hidden

    Is Enabled?

    Check if element is enabled

    Is Disabled?

    Check if element is disabled

    Is Checked?

    Check if checkbox is checked

    Is Editable?

    Check if element is editable

    Has Text?

    Check if element contains text

    Has Value?

    Check if input has value

    Assertions

    Assert Element State

    Verify element state (visible, enabled, etc.)

    Assert Element Content

    Verify element text, value, or count

    Assert Element Attribute

    Verify element attributes and CSS

    Assert Checked

    Fail if not checked

    Assert Unchecked

    Fail if checked

    Waits

    Wait for Element

    Wait for element to appear/disappear

    Wait (Timeout)

    Wait for a fixed duration

    Wait for URL

    Wait for URL to match pattern

    Wait for Function

    Wait for JS function to return true

    Browser Settings

    Set Viewport Size

    Change browser window size

    Emulate Media

    Set dark/light mode, print mode

    Set Geolocation

    Override browser location

    Add Cookies

    Add cookies to browser

    Clear Cookies

    Remove all cookies

    Set HTTP Headers

    Add custom request headers

    Advanced

    Evaluate JavaScript

    Run custom JS in browser

    Highlight Element

    Visually highlight elements

    Select Text

    Select text in elements

    Dispatch Event

    Simulate clicks, hovers, and other events

    CAPTCHA

    Check CAPTCHA

    Wait for Auto-CAPTCHA to finish (no solve spent)

    Solve CAPTCHA

    Solve the page's CAPTCHA now (spends one solve)

    Getting Started

    The Visual Studio Node Library with the Browser tab selected, showing browser action cards ready to drag onto the canvas
    The Node Library's Browser tab — every action on this page is a card you click or drag onto the canvas.
    1. Always Start with Open Page

    Every browser automation must begin with the Open Page node. This launches the browser instance and navigates to your starting URL.

    2. Use the Selector Picker

    Click the target icon in any node with a selector field to open the Selector Picker. It lets you click on elements in the browser to generate reliable selectors automatically.

    3. Test Step by Step

    Use the Visual Builder's test mode to run your automation step-by-step. This helps you verify that each node is working correctly before running the full workflow.

    Example Workflows

    These pre-built tutorial workflows demonstrate how to use most browser nodes. Each workflow includes step-by-step labels explaining what each node does. You can clone any template from the Explore page and run it to see the nodes in action.

    Google Search & Navigation

    Navigate pages, fill search forms, press keys, and extract page data

    open-pagefillpress-keywait-navigationget-page-title+4 more

    Fill Out a Web Form

    Text inputs, dropdowns, checkboxes, file uploads, and form submission

    fillselect-optioncheckuncheckclear-input+2 more

    Extract Data from Web Pages

    Extract text, HTML, attributes, and count elements

    extract-textextract-attributeget-inner-htmlget-inner-textcount-elements

    Capture Screenshots & PDFs

    Full page screenshots, element screenshots, and PDF generation

    screenshotscreenshot-elementpdf

    Validate Element States

    Check visibility, enabled/disabled, editability, and text/value matching

    is-visibleis-enabledis-editableis-checkedhas-text+1 more

    Assert Element Properties

    Assert state, content, and attributes with pass/fail validation

    assert-visibleassert-hiddenassert-textassert-valueassert-element-state

    Multi-Tab Browser Management

    Open, switch between, and manage multiple browser tabs

    switch-tabclose-tabclose-pagebring-to-front

    Advanced Mouse Interactions

    Double-click, right-click, hover, drag & drop, and touch events

    double-clickright-clickhoverdrag-dropfocus+1 more

    Wait for Dynamic Content

    Wait for elements, navigation, network requests, and custom conditions

    wait-timeoutwait-selectorwait-navigationwait-requestwait-response

    Browser Settings & Responsive Testing

    Viewport sizes, media emulation, geolocation, cookies, and headers

    set-viewportemulate-mediaset-geolocationadd-cookiesclear-cookies

    JavaScript Evaluation & Advanced

    Custom JavaScript execution, element highlighting, and advanced features

    evaluate-javascripthighlight-element

    Related Documentation

    Visual Builder Overview

    Learn how to create workflows

    Selectors Guide

    Master element selection

    AI Browser Agent

    AI-powered browser automation

    Testing Workflows

    Debug your automations