Co-Developing with Generative AI

Before We Start

• Using lab computers? Sign in now
• Brought your own computer? Make sure you can access your terminal/PowerShell
• Everyone: We'll help you install required tools as we go
• Need help? Just ask!

How Do LLMs Work for Coding?

• LLMs are trained on billions of lines of code from open-source projects, documentation, and Stack Overflow
• They predict what code should come next based on patterns
  • Can complete functions, suggest implementations, explain code, and debug errors
• Command-line agents (like Gemini CLI) can execute commands, read/write files, and iterate on code
  • Different from chat interfaces
  • Actively interact with your development environment

Limitations for Coding

• Generates plausible but broken code
  • Syntax may look right but logic can be flawed
• Outdated libraries/syntax
  • May suggest deprecated methods or old versions
• Security vulnerabilities
  • Can create code with security flaws that could be exploited
• Can't understand your full codebase
  • Limited context window means it doesn't see everything

Prompt Engineering Basics

How you ask matters as much as what you ask

• Be specific: "Create a Python function that sorts a list of dictionaries by the 'date' key" vs. "Help me sort some data"
• Provide context: Share relevant code, error messages, project structure
• Iterate: Refine your prompts based on results

What is the Terminal?

A terminal (or command line) is a text-based interface for controlling your computer

Instead of clicking buttons and icons, you type commands

Opening Your Terminal

Installation

npm install -g @google/gemini-cli

echo 'eval "$(/opt/homebrew/bin/brew shellenv)"' \
  >> ~/.zprofile
eval "$(/opt/homebrew/bin/brew shellenv)"

brew install gemini-cli

Login Setup

• After installation, run gemini to authenticate with Google
• Choose "Login with Google" and follow the browser prompt
• Free tier: 60 requests/min, 1,000 requests/day
• Having technical issues? Just ask!

Ethical Challenges

• Academic Integrity - How do we cite AI-assisted work? What's collaboration vs. skills offloading?
• Bias & Fairness - AI models reflect biases in their training data
• Environmental Impact - Training and running AI systems consume significant energy

Power & Labor Considerations

• Who builds these systems? Often underpaid workers label data and moderate content
• Who controls AI? Major tech companies control development and access
• Privacy concerns - What data are you sharing? How is it used for training?

Why Use AI Coding Tools, then?

• Prototyping and exploring ideas quickly
• Helps learn new languages/frameworks by example
• Debugging assistance and explaining error messages
• Documentation and code explanation
• Reduces context switching (stay in your terminal)
• Democratizes access to coding for people without CS backgrounds

When NOT to Use AI

Use AI as a tool, not a replacement for understanding

• When learning fundamentals for the first time
• For sensitive or confidential data/code
• When you need guaranteed accuracy (medical, legal, safety-critical)
• When the goal is to develop your own problem-solving skills
• When it would violate academic or professional policies

Choose Your Project Track

• Website (e.g. Portfolio, link tree, small HTML/CSS/JS pages)
  • Example: Create an scaffolded study guide for command line basics with inline CSS and JavaScript
• Visualization (e.g. Simple map, chart, or interactive element)
  • Example: Build an interactive timeline visualizing events in the history of computing based on the Wikipedia page for the topic

Start with a README

• Ask the agent to create a README.md file first
  • This helps you understand and approve the workflow before building
• The README should:
  • Describe your project idea
  • Outline the project structure
  • List key features or goals

Hands-On Activity

After approving the README.md, work with the agent to implement the project components

Duration: 15-20 minutes

We'll walk around the room to help

Choose your track and start building!

Discussion: Your Experience

• What worked well? When did the AI agent help most?
• What didn't work? When did you get stuck or frustrated?
• Surprises? Did the AI do anything unexpected (good or bad)?
• Trust & verification: How did you know if the generated code was correct?

Critical Assessment

Think about these questions:

• When is AI-assisted coding appropriate for your work?
• When might it be inappropriate or problematic?
• How would you document/cite that you used AI in a project?
• What skills do you still need to develop yourself?

Resources

Claude Code - AI assistant for your entire development workflow

Google AI for Students - 1-year free trial (requires SheerID verification)

GitHub Copilot - AI code suggestions in your editor

GitHub Desktop - Visual Git interface, no command line needed