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. Getting Started
    3. Overview

    Platform Overview

    What Prompteryx is, the ways you can automate with it, and where to go deeper.

    Prompteryx is an AI platform for getting work done on the web. You can tell an AI agent what you want done in plain language, or build a precise, repeatable workflow visually. Both can run in your own Chrome on your machine or in an always-on Cloud Browser, on demand or on a schedule, and both connect to your other tools through Connect Hub.

    It all starts in the app

    When you sign in you land on the Prompteryx app: one chat where you ask for anything, with any model. It builds websites and games, makes images, video, music, voiceovers and sound effects, writes documents, slides and spreadsheets, does cited research, starts the AI Browser Agent when a task needs a website, builds workflows and uses your connected apps. Projects, Explore and Schedules live in its sidebar, next to links to the full-page tools described below; Memory, Skills and Connections are in its account menu. See What you can make and AI Browser Agent in the chat.

    The Prompteryx app

    Two ways to automate

    AI Browser Agent
    Describe the task; an AI drives the browser for you.

    Type what you want — “find the three cheapest listings and give me a table” — and the agent navigates, clicks, types and reads pages until it has your answer. Pick the AI model per run, get results as text or structured JSON, fan a batch out across parallel agents, and export the recorded actions as a reusable workflow once the AI has figured the task out.

    The AI Browser Agent page with the Model dropdown open, listing the Prompteryx stacks and the Claude and GPT options
    The AI Browser Agent composer — pick a model, type the task, and delegate.
    AI Browser Agent docs
    Visual Studio
    Build exact, repeatable workflows from drag-and-drop nodes.

    Compose browser actions (open page, click, fill, extract), control flow, AI steps and integrations into a workflow you can test, schedule and share. Deterministic and free of per-step AI cost — ideal once a process is nailed down. Start with Creating Workflows or browse the node reference.

    Visual Studio docs

    Where automations run

    Your own Chrome

    With the Prompteryx in Chrome and Prompteryx Desktop, automations run in your real browser with your real logins — including a sidebar agent that works on whatever tab you have open.

    Cloud Browser

    A managed browser that runs without your machine: live view, persistent profiles that stay signed in, residential proxies, video recording, and downloads captured for you. The AI Browser Agent runs here whenever your desktop app isn't connected, so there is nothing to install to get started. Best for schedules that must run while your computer is off. Cloud Browser docs.

    Connecting your tools

    Connect Hub
    Google Sheets, Gmail, Slack, Notion and 3,000+ other apps as workflow nodes — read rows, send messages, file results. Connect Hub docs.
    Batch Prompter
    Run a spreadsheet of prompts on ChatGPT, Google Gemini, Midjourney or Runway — one row at a time, in your own Chrome through Prompteryx Desktop. Batch Prompter docs.

    Run it unattended

    Schedules
    Both surfaces run on a clock: workflows via the Schedule Trigger, and agents via Schedule an Agent — describe a task once and a cloud agent runs it every day, hour, or custom cron.
    Developers
    Trigger workflows over REST, receive webhooks, drive the Cloud Browser API from Playwright, connect Claude or ChatGPT over MCP, or call Prompteryx from n8n, Zapier and Make with their HTTP and webhook apps. Developer docs.

    Next steps

    Install

    Extension + desktop app for local automation (skip if going cloud-only).

    First task in the app

    Send your first request from the app's home.

    First workflow

    Build a simple automation in Visual Studio in 5 minutes.