Skip to main content

Welcome to XY Browser Agent

Capture browser work with full context, refine it into workflows, and automate it at scale.

The XY Browser Agent is XY's multimodal browser automation experience for teams that work inside payer portals, EHR web interfaces, and other browser-based systems. It combines browser recording with optional screen and audio context so teams can capture how work is done, refine it into reusable workflows, and run it with more speed and consistency over time.

Launch What it does​

With the Browser Agent, teams can:

  • Record browser workflows by performing the task once
  • Capture multimodal context with browser actions plus optional screen and audio guidance
  • Refine recorded work into cleaner, more reusable workflows
  • Connect one or many browser tasks into broader automation flows
  • Run workflows in a co-pilot or more automated mode depending on the process
  • Manage execution while workflows are running

Features Key Features​

Target Visual Workflow Recording​

Record the task once by clicking, typing, navigating, and interacting with the page normally. XY captures the browser steps and page structure so the work can be reused instead of rebuilt from scratch.

Multimodal Multimodal Optional Screen and Audio Capture​

When useful, the Browser Agent can capture more than browser steps alone. Optional screen and audio capture gives teams richer context for review, training, collaboration, and workflow refinement.

Audio Passive Process Mining​

Subject-matter experts can explain edge cases and reasoning while they work, helping teams bootstrap prototype workflows faster with fewer meetings and less back-and-forth.

Enterprise Web App Visibility​

Recorded workflows are not trapped inside the extension. Teams can also review and manage them from the XY Web App.

Refine Refine and Edit Workflows​

Recorded workflows can be cleaned up, corrected, and expanded after capture. Teams can remove mistakes, improve individual steps, and convert recorded work into something more reliable and reusable.

Workflow Design No-Code Workflow Design​

Teams can use natural-language guidance and visual editing to shape browser tasks into more complete workflows without needing to write custom code.

Execution Optimized 24/7 Execution​

The Browser Agent is designed to run workflows like a human user in browser-based systems while helping teams move repetitive work out of manual queues and into repeatable execution.

Self Healing AI Only When You Need It​

For more variable browser work, XY can help handle authentication steps, page changes, pop-ups, and broken flows so teams are not left maintaining brittle automations by hand.

Co-Pilot Co-Pilot or Automate​

Some workflows are best run with a person in the loop, while others can become more autonomous over time. The Browser Agent supports both approaches so teams can choose the right level of oversight.

HIPAA Built for Healthcare Operations​

The Browser Agent is designed for secure healthcare automation and is a strong fit for operational work that still depends on websites, portals, and other browser-only systems.

Target Perfect For​

  • Portal work such as status checks and submissions
  • Data entry across repetitive web forms
  • File handoffs in systems that require manual uploads or downloads
  • Operational workflows that people currently perform by clicking through websites
  • Healthcare administration tasks that live in payer, EHR, or vendor portals
  • Teams that want no-code automation instead of brittle scripts or one-off macros

Record Refine Automate Record, Refine, Automate​

The Browser Agent experience is built around three stages:

  1. Record: Capture browser actions, and optionally screen and audio context, while an expert performs the task.
  2. Refine: Edit, clean up, and improve the captured work so it is ready to reuse.
  3. Automate: Run the workflow in a supervised or more automated way depending on the process and your team's comfort level.

Quick Start Quick Start​

Ready to get started? Here's what you need to do:

  1. Install the Extension - Get XY Browser Agent from the Chrome Web Store
  2. Quick Start Guide - Create your first workflow in 5 minutes
  3. Account Setup - Create or sign in to your XY account

Documentation Documentation Overview​

This documentation is organized to help you master XY Browser Agent step by step:

  • Getting Started - Installation, setup, and your first workflow
  • Recording Workflows - Learn how to create, save, and review browser workflows

Benefits Why Choose XY Browser Agent?​

Unlike tools that only work well with APIs, the Browser Agent helps teams automate real web work directly in the browser:

  • Start from real work instead of rebuilding everything from scratch
  • Capture more context with optional video and audio alongside browser actions
  • Learn faster from experts through passive process mining and recorded explanation
  • Keep workflows visible in both the extension and the web app
  • Refine over time as your team learns what should be automated
  • Use no-code workflow editing to shape recordings into more complete automations
  • Move toward 24/7 execution for repetitive browser-based work
  • Use it alongside integrations and files instead of treating browser work as separate from the rest of XY

Ready to transform your productivity? Let's get started! Next Install XY Browser Agent