LLM Learning Project

This repository contains learning materials and documentation about Large Language Models (LLMs), focusing on prompt engineering, context engineering, and practical implementation examples.

📚 Project Structure

LLM-learning/
├── README.md                           # This file - project overview and navigation
├── package.json                        # Node.js dependencies and project configuration
├── prompt_vs_context.md               # Detailed comparison of prompt vs context engineering
├── sample_document.md                 # Example Markdown document with images
├── plan_mode.md                       # Planning and mode documentation
├── mcp.md                            # MCP (Model Context Protocol) documentation
├── systemPrompt_vs_reminder.md       # System prompt vs reminder analysis
├── reminder.js                       # Node.js script demonstrating LLM API usage
├── systemremider.js                  # System reminder implementation
└── images/                           # Image assets for documentation
    ├── vs.jpg                        # Visual comparison diagram
    └── vs1.jpg                       # Additional comparison diagram

📖 Documentation

Core Learning Materials

• Prompt vs Context Engineering - Comprehensive analysis of the differences between prompt engineering and context engineering, including:

  • Key concepts and definitions
  • Why context engineering is crucial for creating effective Agents
  • Performance considerations and token management
  • Practical examples and visual comparisons

• Sample Document - Example Markdown document demonstrating proper formatting and structure

• Plan Mode - Documentation about planning modes and methodologies

• MCP Documentation - Model Context Protocol implementation details

• System Prompt vs Reminder - Analysis of system prompt versus reminder techniques

🚀 Getting Started

Prerequisites

• Node.js (for running the example scripts)
• API key for LLM services (configure in .env file)

Installation

npm install

Running Examples

npm start
# or
node reminder.js

🎯 Key Topics Covered

Context Engineering

• Understanding LLM context limitations and token management
• Attention budget and performance optimization
• Curating and maintaining relevant information
• Diminishing marginal returns in context usage

Prompt Engineering

• Crafting effective LLM instructions
• Organizing prompts for better outputs
• Best practices for prompt design

Practical Implementation

• Real-world examples and use cases
• Performance optimization strategies
• Agent creation methodologies
• API integration examples

🔗 External References

The documentation references various concepts and tools including:

• Claude Code implementation strategies
• Database vs JSON storage considerations
• Cross-platform development approaches
• Privacy and security considerations

---

This repository serves as a comprehensive learning resource for understanding and implementing LLM-based solutions effectively.