Documentation

JamSheed AI Documentation

Everything you need to know to get started and master JamSheed AI

Quick Start

1

Install

Download JamSheed AI for your platform (macOS, Windows, or Linux) and run the installer.

Download now →
2

Activate License

Launch the app and enter your license key. Free tier includes 50K tokens/month.

View pricing →
3

Start Talking

Use voice or text to give commands. Try: "Turn up volume" or "Open Spotify"

Core Features

Voice Commands

Control your computer naturally with your voice. JamSheed AI uses advanced speech recognition to understand your commands.

Example Commands:

  • "Turn up the volume" - Adjust system volume
  • "Open Spotify and play my workout playlist" - Launch apps and control media
  • "Take a note: Meeting with John at 3pm" - Quick note-taking
  • "Show me files modified today" - File operations

Task Automation

Automate repetitive tasks and workflows. Create custom automation scripts or use natural language.

Example Automations:

  • "Organize downloads folder by file type"
  • "Backup my documents to external drive"
  • "Send weekly report to team@company.com"
  • "Resize all images in this folder to 1920x1080"

Terminal Integration

Execute terminal commands using natural language. No need to remember complex syntax.

Natural Language to Commands:

  • You say: "Find all JavaScript files in this project"
  • Runs: find . -name "*.js"
  • You say: "Show disk usage"
  • Runs: df -h

Integrations

Connect JamSheed AI with your favorite tools and services for seamless workflows.

Email & Calendar

  • • Gmail integration
  • • Outlook integration
  • • Google Calendar

Productivity

  • • Slack
  • • Notion
  • • Trello

Storage

  • • Google Drive
  • • Dropbox
  • • OneDrive

Development

  • • GitHub
  • • GitLab
  • • Jira

Configuration & Settings

Customization Options

Voice Settings

  • • Choose wake word ("Hey JamSheed")
  • • Select input language
  • • Adjust microphone sensitivity
  • • Enable/disable voice feedback

AI Model Selection

  • • Claude Sonnet 4.5 (most capable)
  • • GPT-4o (balanced)
  • • Gemini 2.5 Flash (fastest)
  • • Auto-select based on task

Privacy & Security

  • • Local conversation storage
  • • Encrypted API keys
  • • Device binding
  • • Clear history options

Interface

  • • Dark/Light mode
  • • Keyboard shortcuts
  • • Notification preferences
  • • Compact/Comfortable view

Best Practices

Performance Tips

  • • Use Gemini Flash for quick tasks (faster response)
  • • Enable prompt caching for repetitive workflows
  • • Clear conversation history periodically
  • • Keep the app updated for latest optimizations

Security Best Practices

  • • Never share your license key publicly
  • • Review automation scripts before running
  • • Use device binding for shared computers
  • • Enable two-factor authentication (coming soon)

Frequently Asked Questions

How does voice recognition work?

JamSheed AI uses advanced speech-to-text models that run locally on your device for privacy. The recognized text is then processed by the AI to understand your intent.

Can I use JamSheed AI offline?

Voice recognition works offline, but AI features require an internet connection to access LLM APIs. We're working on local model support for offline AI capabilities.

Which AI models are available?

Free tier includes Gemini 2.5 Flash. Pro and Team plans include Claude Sonnet 4.5, Claude Haiku, GPT-4o, GPT-4o Mini, and Gemini 2.5 Pro/Flash.

How do I set up integrations?

Go to Settings → Integrations, select the service you want to connect, and follow the OAuth flow. Your credentials are encrypted and stored securely.

Can I customize automation workflows?

Yes! Use the Workflow Builder in the app to create custom automation sequences. You can also write scripts in JavaScript or Python that JamSheed AI can execute.

Need More Help?

Our support team is here to assist you with any questions or issues.