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. Attached Files

    Using Attached Files

    Share images with the AI to provide visual context for your requests

    Why Attach Files?

    Sometimes words alone aren't enough. By attaching images, you can show the AI exactly what you're looking for, making your requests more precise and helping the AI understand complex visual elements.

    Example Use Case

    Attach a screenshot of a design mockup and say "Make this page look like the attached image" or "Find the button that looks like this" while attaching a cropped image of the button you want to click.

    Visual Reference

    Attach screenshots, design mockups, or diagrams to show the AI what you're looking for. Perfect for "make it look like this" requests.

    Element Identification

    Crop and highlight specific elements you want the AI to interact with, especially when they're hard to describe in words.

    How to Attach Files

    1
    Click the Attach Button

    In the sidebar input area, click the paperclip icon (📎) to the left of the text input field.

    2
    Select Your File

    Choose one or more image files from your computer (up to 5 per message). Only images can be attached. Supported formats include PNG, JPG, JPEG, GIF, and WebP. You can also paste an image from the clipboard with Ctrl+V.

    3
    Preview and Send

    You'll see a thumbnail of the attached file above the input area (click × on a thumbnail to remove it). Type your message explaining what you want the AI to do with the image, then press Enter or click Send.

    Supported File Types

    FormatExtensionsBest For
    PNG.pngScreenshots with text, UI elements
    JPEG.jpg, .jpegPhotos, complex images
    GIF.gifSimple graphics, icons
    WebP.webpModern web images

    Example Use Cases

    "Click the button I circled"

    Take a screenshot of a webpage, draw a circle around a button using any image editor, and attach it with the message "Click the button I circled in the image". The AI will identify the circled element and click it.

    "Fill out the form like this"

    Attach an image showing a filled-out form as an example, and say "Fill out the form on this page with similar information, using john@example.com as the email". The AI will understand the form structure from your example.

    "Make this layout"

    Attach a design mockup or wireframe and say "Configure the page settings to match this layout". The AI will try to match the visual arrangement shown in your reference image.

    "Find elements that look like this"

    Attach a cropped image of a specific UI element (like a particular icon or button style) and ask "Find all elements on this page that look like the attached image".

    Tips for Best Results

    Crop to Focus

    Crop images to show only the relevant portion. A focused image is easier for the AI to interpret than a full-screen screenshot.

    Use Annotations

    Draw circles, arrows, or highlights on your screenshots to clearly indicate what you're referring to.

    Clear Quality

    Use clear, uncompressed images when possible. Blurry or heavily compressed images may be harder for the AI to interpret.

    Describe Your Intent

    Always include text explaining what you want. Don't just attach an image— tell the AI what to do with it.

    Related Documentation

    Using the Sidebar Agent →

    Learn the basics of giving commands

    Execute on Current Tab →

    Run actions on your active page