Skip to content
AI Systems 2026

Lab 01: Development Environment Setup

Beginner Due: 2026-03-10

Objectives

Section titled “Objectives”
  • Install AI coding CLI tools and configure API keys
  • Successfully connect to the DGX H100 server via SSH
  • Understand the GitHub repository fork and PR workflow

Prerequisites

Section titled “Prerequisites”
  • GitHub account
  • Terminal (macOS/Linux) or WSL (Windows) available

Lab Steps

Section titled “Lab Steps”

  1. Verify Node.js Installation

    Terminal window
    node --version  # v20.x.x or higher
    pnpm --version  # 10.x.x or higher

    If Node.js is not installed, get it from nodejs.org.

  2. Install AI Coding CLI Tools

    Terminal window
    pnpm add -g @anthropic-ai/claude-code
    claude --version

  3. Configure API Keys

    Obtain an API key from console.anthropic.com, then:

    Terminal window
    # Add to ~/.bashrc or ~/.zshrc
    export ANTHROPIC_API_KEY="sk-ant-..."
    source ~/.bashrc

  4. First Run Test

    Terminal window
    mkdir ~/hello-agent && cd ~/hello-agent
    claude "Create a Python file that prints 'Hello, AI Engineering 2026!'"
    python hello.py

  5. Observation Task: Record AI’s Autonomous Decisions

    Open the code the AI generated and observe the following:

    • What did the AI decide on its own? (filename, function structure, variable names, comment language, etc.)
    • Distinguish between what you explicitly instructed and what the AI decided autonomously, and record both.
    • How does this observation connect to the Week 1 concept of “AI Model vs. AI System”?
    # Observation Log (write in observations.md)
    ## What I instructed
    - "A file that prints 'Hello, AI Engineering 2026!'"
    

    ## What the AI decided autonomously
    - Filename: ???
    - Variable/function names: ???
    - Code structure: ???
    - Comment language: ???
    - Other: ???

  6. Connect to the DGX Server

    Terminal window
    ssh [student-id]@dgx.chu.ac.kr
    # Initial password: student ID
    passwd  # Change immediately!

  7. Fork and Clone the Repository

    Terminal window
    # After forking on GitHub
    git clone https://github.com/[YOUR_USERNAME]/ai-systems-2026.git
    cd ai-systems-2026
    pnpm install
    pnpm run dev  # Check the local site

Deliverables

Section titled “Deliverables”

Submit a PR with the following files in assignments/lab-01/[student-id]/:

  • README.md — Installation process and troubleshooting notes + AI system analysis report (300 characters minimum)
  • hello.py — Python file generated by an AI coding CLI
  • observations.md — Record of AI’s autonomous decisions
  • screenshots/ — Screenshots of completed installation and DGX connection (2 or more)

Bonus Points:

  1. Compare the top 5 systems on the SWE-bench Verified leaderboard and analyze the correlation between model size and performance.
  2. Propose how EU AI Act Article 14’s human oversight requirements can be applied to our course environment.