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. Prompteryx in Chrome
    3. Installation

    Installing Prompteryx in Chrome

    Add and set up Prompteryx in Chrome, our Chrome extension

    Prerequisites

    Prompteryx in Chrome works alongside Prompteryx Desktop, a desktop app for Windows. Make sure you have the Prompteryx Desktop installed and signed in before proceeding. You only need both for local runs: the AI Browser Agent also runs on Cloud Browser without them.

    Installation Steps

    1
    Add it from the Chrome Web Store

    Prompteryx in Chrome is on the Chrome Web Store. Adding it takes a few seconds, works on Chrome, Edge and Brave, and it updates itself.

    Add to Chrome
    1. On the Chrome Web Store page, click Add to Chrome
    2. Pin the Prompteryx icon from the puzzle-piece menu
    3. Reload prompteryx.ai — the status badge turns green

    Can't use the Chrome Web Store? Load the same extension from the ZIP on the Download page.

    2
    Pin the Extension (Recommended)

    For easy access, pin the extension to your Chrome toolbar:

    1. Click the puzzle piece icon (Extensions) in Chrome's toolbar
    2. Find "Prompteryx AI Browser Agent" in the list
    3. Click the pin icon next to it

    The Prompteryx icon will now always be visible in your toolbar.

    3
    Sign In to Your Account

    The side panel runs with the Prompteryx account the desktop app is signed in to, and uses that account's AI Credits. With the desktop app running:

    1. Click the Prompteryx icon in your toolbar
    2. The sidebar panel will open
    3. If the panel says "Not signed in", click "Sign in"
    4. Sign in to your Prompteryx account in the new tab
    5. Return to the sidebar—it picks up the sign-in by itself and shows "Signed in as …"

    The line under the panel header shows which Prompteryx site and account the panel is using. Click "Switch" there to change the site.

    "Ready" in the panel header and your Balance in the action bar confirm a successful sign-in
    4
    Verify the Desktop App Connection

    Make sure Prompteryx Desktop is running on your computer. The extension communicates with the desktop app to execute browser automations. It only talks to the desktop app on your own computer (127.0.0.1), pairs with it using a secret created for your install, and only accepts messages from prompteryx.ai.

    How to verify:

    • Look for the Prompteryx icon in your system tray
    • In the sidebar header, the status should show "Ready" ("Desktop app not running" means the panel can't reach the desktop app)
    • Try sending a simple command like "Go to google.com"

    Multiple Chrome Profiles

    Profile Isolation

    Prompteryx in Chrome keeps some state per Chrome profile and shares some across them. This means:

    • Separate settings: Each profile can have its own preferences
    • Separate chat history: Chat history follows the Prompteryx account each Chrome profile is signed in to on prompteryx.ai
    • One desktop app account: Runs from every Chrome profile go through the same Prompteryx Desktop and are billed to the account the desktop app is signed in to. If a profile's Prompteryx account differs, the "Switch" dialog says which account is billed.

    Keep this in mind if several people share one computer with different Chrome profiles.

    Troubleshooting

    "Not signed in" keeps appearing

    If the panel still says "Not signed in" after signing in:

    • Make sure you signed in on the site shown under the panel header (use "Switch" to change it)
    • Sign the desktop app in directly: right-click the Prompteryx tray icon → Sign in… and approve it in your browser
    • Try closing and reopening the sidebar panel
    "Desktop app not running"

    If the extension can't connect to Prompteryx Desktop:

    • Verify Prompteryx Desktop is running (check system tray)
    • Restart the desktop app if needed
    • Update both if either is old: the extension must be 3.0.0 or later and the desktop app 1.1.0 or later, or they can't pair
    • Check your firewall isn't blocking localhost connections
    • Try restarting Chrome
    Extension not showing in toolbar
    • Click the puzzle piece icon (Extensions) in Chrome
    • Make sure Prompteryx is enabled
    • Click the pin icon to add it to your toolbar
    • Try reinstalling the extension if it's not visible at all

    Next Steps

    Using the Sidebar Agent →

    Learn how to use the AI chat interface

    Execute on Current Tab →

    Run automations on your active page

    Using Attached Files →

    Share images with the AI for context

    Exporting to Visual Studio →

    Save recorded actions as workflows