PureCode AI
  • PureCode AI Extension
  • Getting Started
    • Getting Started
  • Features
    • Chat
      • @Features
        • @Docs
        • @Files
        • @Folder
        • @Code
        • @Git
        • @Terminal
        • @UI
    • Dual Operation Modes
      • Normal Mode [ Chat ]
      • Agent Mode
      • Switching Between Modes
    • Context Awareness
      • Normal Indexing
      • Advance Indexing
    • Human-like Code Understanding with @codebase
    • Interactive Planning Mode
    • Adaptive Learning Preferences
    • Global and Project Custom Instructions
      • Global Instructions
      • Project Chat Instructions:
    • Docs Indexes and UI Docs Indexes
      • Docs Indexes
      • UI Docs Indexes
    • "Reject" and "Accept"
    • Image-to-Code
    • Video Tutorial's
    • Prompting Techniques
    • Chat Vs Codebase Chat
    • Solving Errors
  • Frequently Asked Questions
  • Changelog
Powered by GitBook
On this page
  1. Features
  2. Dual Operation Modes

Agent Mode

PreviousNormal Mode [ Chat ]NextSwitching Between Modes

Last updated 4 days ago

Agent Mode is ideal for more in-depth tasks, such as planning, researching, and executing complex workflows. It enables the AI to take a step back, analyze the entire project, and suggest architectural changes or new implementations. The AI operates more like an assistant, helping you plan the next steps, make architectural decisions, and ultimately deliver these changes.

Key Features:

  • Tool-Enhanced Flow: In Agent Mode, PureCodeAI has access to more advanced tools that can analyze, test, and modify your code. This mode enables you to do in-depth research, code reviews, or implementation planning before making changes.

  • Research & Ideation: The AI helps you explore different approaches and consider alternatives, making it easier to decide on the best implementation strategy.

  • High-Level Planning: Agent Mode helps you lay out the steps for a feature or project and offers insights into the architecture, dependencies, and necessary components.

  • Execution Control: While in this mode, the AI helps guide you through execution after thorough research and planning, reducing the risk of errors in complex features.

When to Use:

  • When planning new features or large-scale refactors and want the AI to guide you step-by-step.

  • When exploring complex architectural decisions or assessing different approaches before implementing code changes.