Alex Sidebar’s agents are specialized AI assistants, each trained for specific development tasks. Alex automatically selects the right agent for your workflow for autonomously handling your development tasks!

Agent mode is now always on! Claude 3.5 Sonnet remains the default model for its superior code generation capabilities, but you can now use other supported models including:

  • DeepSeek R1
  • DeepSeek V3
  • Claude 3.7 Sonnet
  • o3-mini
  • GPT-4o
  • o1
  • Gemini 2.0 Flash

Choose your preferred model from the model selector while maintaining all agent capabilities.

​
Quick Actions

Smart Automation

Let agents handle repetitive tasks while you focus on core development work.

Multi-Model Support

Switch between different AI models while maintaining agent capabilities and context.

​
Understanding Agents

Agents work best by:

  • Learning your project structure and patterns
  • Maintaining contextual understanding across sessions
  • Automating common development tasks
  • Suggesting improvements based on best practices
  • Using regex code search for precise file analysis

You can make agents more effective over time by providing more notes about your project and coding preferences. Learn more about project notes here.

​
Getting Started

1

Initialize Agent

Press Command + Shift + A or use the Agent Settings dropdown to toggle Use agent for your project.

2

Project Introduction

Use voice or text to describe your project:

"This is an iOS app using SwiftUI and MVVM architecture. 
The main features include user authentication and data persistence."
3

Let Agent Learn

The agent will:

  • Analyze project structure
  • Study coding patterns
  • Build contextual understanding
  • Use regex search to find relevant code patterns

​
Best Practices

Clear Communication

Provide specific requirements and context for best results

Iterative Development

Break complex tasks into smaller, manageable steps

Review Changes

Always review and test agent-suggested modifications

Maintain Context

Keep project notes updated for better agent performance

Was this page helpful?