Recording

Zeus Desktop provides comprehensive browser action recording, automatically capturing user operations in the browser as editable, replayable workflows.

Overview

Workflow recording is built on the Chrome DevTools Protocol (CDP), capturing DOM-level browser events with higher accuracy and stability compared to traditional coordinate-based recording approaches.

Core Capabilities

Capability	Description
Precise Recording	CDP-based DOM event capture with dual locator strategy: CSS selectors + semantic features
Visual Editing	Drag-and-drop reordering, step-by-step editing, insert/delete action steps
Parameterization	Mark fixed values as variables for dynamic injection
Parameterized Replay	Enter parameter values during test replay to verify workflow correctness
Video Sync	Action events are time-aligned with recorded video; click a step to jump to the video timestamp

Quick Start

1. Select a Browser Profile

Before recording, select a browser profile. Each profile has its own independent cookies, cache, and login state.

2. Start Recording

Click the Start Recording button on the recording page
Select a browser profile
Optionally enable video recording (captures screen visuals simultaneously)
The browser launches automatically and enters recording mode

3. Perform Actions

Operate the browser normally. The system automatically captures the following events:

Page navigation (URL changes)
Mouse clicks
Text input and modification
Keyboard keystrokes
Page scrolling
Form submission
Drag and drop

4. Stop Recording

Click the Stop Recording button. The recorded action sequence is displayed in the editor for further editing and saving.

Supported Action Types

Browser Events

Type	Description	Parameterizable
`navigate`	Navigate to a specified URL	✅ URL can be parameterized
`click`	Click a page element	❌
`input`	Type text into an input field	✅ Input value can be parameterized
`change`	Change a form control value (dropdowns, etc.)	✅ Value can be parameterized
`scroll`	Scroll the page or an element	❌
`keypress`	Press a keyboard key (Enter, Tab, etc.)	❌
`wait`	Wait for a specified duration	❌
`submit`	Submit a form	❌
`drag`	Drag an element to a target position	❌

System-level Events (Extensions)

Type	Description
`system_click`	System-level mouse click
`system_keypress`	System-level keyboard input
`app_switch`	Application switch
`applescript`	AppleScript execution
`shell_command`	Shell command execution

Element Locator Strategy

During recording, each action’s target element uses a multi-strategy locator approach to ensure high accuracy during replay:

Locator Priority

Priority	Method	Confidence	Description
1	`testId`	1.00	Exact match on `data-testid` attribute
2	`exact`	0.95	Full semantic match (role + name)
3	`selector`	0.85	CSS selector match
4	`fuzzy`	0.70	Fuzzy match (text content, ARIA attributes)
5	`position`	0.60	Visual position match
6	`nth`	0.50	Index-based fallback

Semantic Features (ElementFeatures)

Rich semantic features are recorded for each action’s target element:

interface ElementFeatures {
  role?: string          // ARIA role
  name?: string          // Accessible name
  testId?: string        // data-testid
  ariaLabel?: string     // aria-label
  text?: string          // Text content
  placeholder?: string   // placeholder attribute
  tagName?: string       // HTML tag name
  type?: string          // input type
}

These features enable the replay engine to locate the correct target element through semantic information even when the page DOM structure has changed.

Editing Workflows

Workflow Editor

After saving a recording, you can modify the action sequence in the workflow editor:

Drag-and-drop reordering: Adjust the execution order of action steps
Edit actions: Modify selectors, values, URLs, and other properties
Insert steps: Add new action steps at any position
Delete steps: Remove unnecessary actions
Video sync: Click a step to automatically jump to the corresponding timestamp in the recorded video

Editing Action Details

Click any action step to open the editing dialog:

Basic info: Action type, description
Selectors: CSS selector, XPath, element features
Value: Input value, navigation URL
Parameterization settings: Mark as variable, set variable name and default value

Parameterization

Parameterization converts fixed values in a recording into dynamically injectable variables — a key capability for enabling AI Agent-driven execution.

What is Parameterization

Using a login flow as an example:

Step	During Recording	After Parameterization
Enter username	`admin`	`{username}`
Enter password	`123456`	`{password}`
Navigate to system	`https://sys.example.com`	`{systemUrl}`

After parameterization, these values are no longer fixed — they are supplied externally at replay/invocation time.

Single Action Parameterization

Click an action step in the workflow editor to open the editing dialog
Toggle on the Parameterize switch
Set the Variable Name (e.g., username)
Optionally enter a Parameter Description (e.g., “Login username”)
Optionally set a Default Value (e.g., admin)
Save

Once parameterization is enabled, the action’s value field displays as a variable reference (e.g., {username}), and the actual value is injected at runtime.

Batch Parameterization

For workflows with multiple input actions, you can use the Batch Parameterize feature:

If there are non-parameterized input/change/navigate actions, a Batch Parameterize prompt appears at the top of the workflow editor
Click it, and the system automatically generates variable names based on element attributes (name, id, placeholder, etc.)
Current values are automatically set as default values
You can further adjust settings in the editing dialog

Variable Resolution

The replay engine uses {variableName} syntax for variable substitution:

Input value: "Hello, {username}! Your code is {verifyCode}"
Variables passed: { username: "John", verifyCode: "123456" }
Actual execution: "Hello, John! Your code is 123456"

Variable resolution supports:

Full replacement: {username} → John
Inline replacement: https://{host}/api → https://example.com/api
Unmatched variables are kept as-is: {unknown} → {unknown}

Replay Testing

Basic Replay

For workflows without parameterized actions, simply select a browser profile and start replay.

Parameterized Replay

When a workflow contains parameterized actions, clicking replay opens a Parameter Input Dialog:

All parameterized fields are automatically displayed
Parameter name, description, and default value are shown
Required parameters (no default value) are marked in red
Enter test values and click Start Replay

Replay Engine

Replay is CDP-based and has the following characteristics:

Feature	Description
Element Wait	Automatically waits for the target element to appear (up to 10 seconds)
Retry Mechanism	Automatically retries failed actions (up to 3 times, 1-second interval)
Timeout Protection	Skips a single action after 30-second timeout
Progress Feedback	Shows real-time execution progress and step status
Visual Status	Highlights the current execution step in the editor (blue = in progress / green = success / red = failed)

Video Recording

Recording Options

Option	Description
Screen/Window Source	Choose to record the entire screen or a specific window
Resolution	720p / 1080p / 4K
Frame Rate	30fps / 60fps
Microphone Audio	Record voice narration
System Audio	Record system sound (macOS requires BlackHole)

Video-Action Synchronization

Video and action events are aligned by timestamps:

Each action records a videoTimestamp (seconds relative to recording start)
Clicking an action step in the editor automatically jumps the video to the corresponding time
During replay, the video preview syncs with action execution

Storage Estimates

Resolution	Frame Rate	Duration	File Size
720p	30fps	10 minutes	~80-120 MB
1080p	30fps	10 minutes	~150-250 MB
1080p	30fps	1 minute	~15-25 MB

Local Storage

Workflow data is stored in the local file system:

{userData}/workflows/
├── {workflow-id}.json          # Workflow definition (action sequence + metadata)
├── {workflow-id}/
│   ├── recordings/             # Recorded video files
│   │   └── recording.webm
│   ├── screenshots/            # Keyframe screenshots
│   │   ├── action-001.png
│   │   └── action-002.png
│   └── metadata.json           # Sync metadata

Workflow JSON Structure

{
  "id": "wf-abc123",
  "name": "Log in to system and query data",
  "actions": [
    {
      "id": "act-001",
      "type": "navigate",
      "url": "https://system.example.com",
      "timestamp": 1700000000000
    },
    {
      "id": "act-002",
      "type": "input",
      "selector": "#username",
      "value": "{username}",
      "isParameterized": true,
      "variableName": "username",
      "paramDescription": "Login username",
      "defaultValue": "admin",
      "elementFeatures": {
        "role": "textbox",
        "name": "Username",
        "placeholder": "Enter username"
      }
    }
  ],
  "profileId": "profile-001",
  "toolName": "login_and_query",
  "toolDescription": "Log in to the system and query specified data",
  "isPublished": true
}

Next Steps

After recording and parameterizing a workflow, you can publish it as an RPA tool so that AI Agents can invoke it remotely.

Web

Desktop

Chrome Extension

iOS

Android

CLI

Overview

Core Capabilities

Quick Start

1. Select a Browser Profile

2. Start Recording

3. Perform Actions

4. Stop Recording

Supported Action Types

Browser Events

System-level Events (Extensions)

Element Locator Strategy

Locator Priority

Semantic Features (ElementFeatures)

Editing Workflows

Workflow Editor

Editing Action Details

Parameterization

What is Parameterization

Single Action Parameterization

Batch Parameterization

Variable Resolution

Replay Testing

Basic Replay

Parameterized Replay

Replay Engine

Video Recording

Recording Options

Video-Action Synchronization

Storage Estimates

Local Storage

Workflow JSON Structure

Next Steps

​Overview

​Core Capabilities

​Quick Start

​1. Select a Browser Profile

​2. Start Recording

​3. Perform Actions

​4. Stop Recording

​Supported Action Types

​Browser Events

​System-level Events (Extensions)

​Element Locator Strategy

​Locator Priority

​Semantic Features (ElementFeatures)

​Editing Workflows

​Workflow Editor

​Editing Action Details

​Parameterization

​What is Parameterization

​Single Action Parameterization

​Batch Parameterization

​Variable Resolution

​Replay Testing

​Basic Replay

​Parameterized Replay

​Replay Engine

​Video Recording

​Recording Options

​Video-Action Synchronization

​Storage Estimates

​Local Storage

​Workflow JSON Structure

​Next Steps

Overview

Core Capabilities

Quick Start

1. Select a Browser Profile

2. Start Recording

3. Perform Actions

4. Stop Recording

Supported Action Types

Browser Events

System-level Events (Extensions)

Element Locator Strategy

Locator Priority

Semantic Features (ElementFeatures)

Editing Workflows

Workflow Editor

Editing Action Details

Parameterization

What is Parameterization

Single Action Parameterization

Batch Parameterization

Variable Resolution

Replay Testing

Basic Replay

Parameterized Replay

Replay Engine

Video Recording

Recording Options

Video-Action Synchronization

Storage Estimates

Local Storage

Workflow JSON Structure

Next Steps