AI Assistant

AI Assistant

AI Assistant is one of Owlfy’s core features. Triggered by holding the voice key and describing a complex task, it uses a powerful AI scheduling engine to complete tasks through planned execution.

Operation Method

Hold the voice key, describe your task, then release.

Default Voice Keys:

• Windows: Right Alt key or Mouse wheel
• macOS: Fn key or Mouse wheel

You can customize the voice key in Settings.

Core Capabilities

Full Skill Support

AI Assistant intelligently invokes a vast array of built-in Skills to handle diverse tasks:

• Images, Audio & Video: Format conversion, compression, cropping, smart editing, material extraction, dubbing, and more
• Documents: Writing, summarizing, translating, rewriting, merging, splitting, format conversion, and more
• System Operations: Opening programs, file management, system settings, cleanup, shutdown/lock screen, and more
• Web Automation: Searching, extracting web content, downloading resources, automating web operations, and more

Plan & Execute

For complex tasks, AI Assistant breaks them into executable plans, then tackles them one by one through:

• Writing and running code
• Executing CLI commands
• Calling APIs
• Using MCP (Model Context Protocol) tools
• Invoking built-in Skills

Example:

• Task: “Summarize the key points from all PDFs in my Downloads folder and create a Word document”
• Plan:
  1. Scan Downloads folder for PDF files
  2. Extract text from each PDF
  3. Summarize key points from each document
  4. Generate a formatted Word document with all summaries

Local-First

For tasks that can be completed locally — such as document processing, image processing (non-AIGC), and audio/video processing (non-AIGC) — AI Assistant prioritizes local execution. Files are not uploaded to the cloud, ensuring maximum data security.

Skill Categories

Life Services

Skill	Description	Command Example
Map Navigation	Route queries, navigation guidance	”Navigate to Zhongguancun”
Ride-hailing	Call ride-share services	”Call me a car”
Train Ticket Query	Query train ticket info	”Tomorrow’s high-speed train from Beijing to Shanghai”
Flight Query	Query flight info	”Next Monday’s flight from Beijing to Sanya”
Stock Analysis	Stock market analysis	”Analyze Kweichow Moutai”
Package Tracking	Track express delivery	”Track my SF Express”
Weather Forecast	Query weather info	”How’s the weather in Beijing tomorrow”
Product Search & Comparison	Compare product prices	”How much is iPhone 15”
Gas Price Query	Query latest gas prices	”What’s today’s gas price”
Traffic Restriction Query	Query vehicle restrictions	”What’s today’s restriction number”
Currency Conversion	Currency exchange rates	”100 USD to CNY”

Network Services

Skill	Description	Command Example
Check IP Address	Get current network IP	”What’s my IP”
Cloud Storage Search	Search cloud storage resources	”Search for xxx cloud resources”
Generate Short Link	Convert long URL to short	”Shorten this link”
Bilibili Video Download	Download Bilibili videos	”Download this Bilibili video”
TikTok Video Download	Download TikTok videos	”Download this TikTok video”
Search Video Materials	Search video materials	”Find some food video materials”
Query Company Info	Query business registration	”Look up Tencent”
Query Company Risks	Query company risk info	”Does this company have risks”

System Operations

Skill	Description	Command Example
Open Program	Launch specified application	”Open WeChat”
Open Webpage	Open specified URL	”Open Baidu”
Open Directory	Open specified folder	”Open work folder”
Search	Use search engine	”Baidu search xxx”
Search Files	Search for files on computer	”Find the contract file”
Change Wallpaper	Change desktop wallpaper	”Change to a nice wallpaper”
Manage Startup Items	Manage auto-start programs	”Disable xxx startup”
Batch Rename	Batch modify filenames	”Rename these files to 001, 002…”
Organize Directory	Organize specified folder	”Organize the downloads folder”
Adjust Brightness	Adjust screen brightness	”Brighten screen”
Adjust Volume	Adjust system volume	”Set volume to 50%“
Split Screen	Set window split screen	”Split screen left and right”
Clean System Junk	Clean junk files	”Clean up junk”
View Resource Usage	View CPU, memory usage	”Is my computer slow”
Manage Ports	Manage network ports	”Release port 8080”

AI Generation

Skill	Description	Command Example
AI Drawing	Generate images from text	”Draw a cute cat”
AI Image Editing	AI edit and modify images	”Remove this”
Add Artistic Text	Add artistic text to images	”Add ‘Happy Birthday’ to the image”
Multi-image Fusion	Generate new image from multiple	”Merge these two images”
AI Dubbing	Text-to-speech	”Read this text”
AI Text-to-Video	Generate video from text	”Generate an intro video”
AI Image-to-Video	Generate video from image	”Make this image move”
AI Music Composition	Generate original music	”Compose a cheerful piece”

File Processing Skills

AI Assistant also supports powerful file processing:

Image Processing

• Compress, convert formats, remove backgrounds
• Adjust resolution, rotate, crop
• OCR text recognition
• Multiple images to GIF/PDF

Audio/Video Processing

• Compress, add watermarks
• Smart silence removal, concatenate
• Format conversion, frame extraction
• Voice recognition

Document Processing

• Merge/Split PDF
• PDF watermark
• Markdown to PDF/Word
• AI generate PPT
• Edit Excel/Word/PPT

Third-party Skills (MCP)

Owlfy supports installing third-party MCP (Model Context Protocol) skills to extend AI Assistant’s capabilities.

Installing MCP Skills

1. Browse available MCP skills in the Skill Plaza
2. Click “Install” button
3. Follow prompts to complete configuration
4. Use via voice after installation

Usage Tips

Combined Commands

You can combine multiple tasks in one request:

"Check tomorrow's train from Beijing to Shanghai, then find a hotel nearby"

Contextual Conversation

AI Assistant supports contextual understanding:

User: "How's the weather in Beijing tomorrow?"
AI: "Beijing will be sunny tomorrow, 15-25 degrees..."
User: "What about Shanghai?"
AI: "Shanghai will be cloudy tomorrow, 18-28 degrees..."

Batch File Processing

Select multiple files for processing:

Select 10 images → "Compress these images to under 1MB"

AI Assistant Settings

Sandbox Mode

Determines the scope of operations AI can perform:

• Restricted: Limited to specified workspace folders
• Standard: Can access common user directories
• Unrestricted: Full system access (use with caution)

Approval Policy

Control when AI asks for confirmation:

• Before high-risk operations
• Before file deletions
• Before system changes
• Based on stamina consumption threshold

Related Documentation

• Sonic Execution — Learn about Sonic Execution
• Voice Input — Learn about Voice Input
• Scheduled Tasks — Automate recurring tasks