Quick Start Guide

This guide will help you get started with TalkCody quickly. You'll learn how to install the application, configure your first AI provider, and start your first conversation.

Installation

Your First Conversation

Once you've configured your API key, you're ready to start coding with AI assistance!

Starting a Chat

1. Create a New Project (optional)

   • Click on the Projects tab
   • Select "New Project" or "Import Project"
   • Choose a local directory

2. Open Chat Interface

   • Navigate to the Chat tab
   • You'll see the conversation interface

3. Ask a Question

   • Type your question or request in the input field
   • Press Enter or click Send
   • Watch as the AI responds with streaming text

Example Conversations

Here are some things you can try:

User: Help me create a React component for a todo list with TypeScript

User: Review this code and suggest improvements
[Attach or paste your code]

User: Explain how async/await works in JavaScript with examples

User: Write unit tests for the calculateTotal function

Understanding the Interface

Main Views

TalkCody has several main views accessible from the sidebar:

• Chat: Main conversation interface with AI
• Explorer: Browse and manage project files
• Projects: Manage multiple projects and workspaces
• Agents: Configure custom AI agents with specialized prompts
• MCP Servers: Manage Model Context Protocol integrations
• Settings: Configure API keys, models, and preferences

Chat Features

The chat interface includes:

• Message History: Scrollable conversation history
• Streaming Responses: Real-time AI responses
• Code Highlighting: Syntax-highlighted code blocks
• Tool Execution: AI can execute tools (file operations, searches, etc.)
• Attachments: Upload images or files for AI analysis
• Voice Input: Use voice-to-text for hands-free input

Working with Projects

TalkCody works best when connected to a project directory:

Customizing AI Behavior

Selecting a Model

Different tasks benefit from different models:

1. Open Settings → Model Settings
2. Choose a default model or switch models per conversation
3. Adjust parameters:
   • Temperature: Controls creativity (0.0 = focused, 1.0 = creative)
   • Max Tokens: Maximum response length

Creating Custom Agents

For specialized tasks, create custom agents:

1. Navigate to the Agents view
2. Click "New Agent"
3. Configure:
   • Agent name and description
   • System prompt (defines behavior)
   • Assigned tools (file operations, search, web crawling)
   • Default model

Examples of useful agents:

• Code Reviewer: Focused on code quality and best practices
• Documentation Writer: Specialized in writing clear docs
• Test Generator: Creates comprehensive unit tests
• Bug Finder: Analyzes code for potential issues

Next Steps

Now that you're up and running, explore more advanced features:

• AI Chat - Deep dive into chat features
• AI Agents - Create specialized AI assistants
• MCP Servers - Extend capabilities with external tools
• Configuration - Fine-tune your setup

Troubleshooting

Common Issues

API Key Not Working

• Verify the key is correct and has sufficient credits
• Check that the provider API is accessible
• Try using a different provider to isolate the issue

Slow Responses

• Check your internet connection
• Try a faster model (e.g., GPT-4.1 Turbo, Claude Haiku)
• Reduce max tokens setting

Application Won't Launch

• Check macOS version compatibility (requires macOS 10.15+)
• Verify security settings allow TalkCody to run
• Try reinstalling the application

For more help, visit the FAQ or check the GitHub issues page.