Part Two — Build It Yourself

Chapter 4

Your Tools:
Zero to Ready in One Afternoon

Six tools. No assumed knowledge. By the end of this chapter, Professor Dr. Tan's computer will be equipped with everything needed to build a market intelligence pipeline from scratch.

⏱ Estimated time: 90–120 minutes · One afternoon

Before You Start

This chapter assumes you are using a Windows computer. Every step is written for Windows. If you are on a Mac, the concepts are identical but a few of the installation steps are slightly different — the chapter notes will flag these where they occur.

You will need:

You do not need:

Why These Six Tools Specifically

These are exactly the six tools that Team 1 used to build their market intelligence pipeline in TR2 2026. They are free, widely used in professional software development, and — critically — they are the same tools that your students will use. Going through this chapter means you will have personal experience with every tool you ask your students to work with.


Tool 1 — GitHub Account

🐙
GitHub
github.com

GitHub is where your code lives. It is the platform where Team 1 made their 86 commits, managed their 26 branches, reviewed their 61 Pull Requests, and ran their three automated CI/CD workflows. Think of it as a combination of Google Drive (for storing files), a version history system (showing every change ever made), and an automation platform (running workflows automatically). Every team member contributes through GitHub. Every output is visible, timestamped, and attributed to a specific person.

What to Do — Step by Step

  1. Open your web browser and go to github.com
  2. Click the green "Sign up" button in the top right corner
  3. Enter your email address. Use a professional email — this account will be associated with your work as an educator
  4. Create a password. Make it strong — at least 12 characters with a mix of letters, numbers, and symbols
  5. Choose a username. This will be visible on everything you create. Professor Dr. Tan's username is ProfDrTan — follow a similar professional format
  6. Complete the verification puzzle GitHub shows you
  7. Click "Create account"
  8. GitHub will send a verification code to your email. Open your email, copy the 6-digit code, and enter it on the GitHub page
  9. GitHub will ask a few setup questions — answer them or click "Skip personalisation" at the bottom
✅ You Know It Worked When
You are looking at a page that says "Welcome to GitHub" or shows your dashboard with your username in the top right corner.

Enable Two-Factor Authentication (Strongly Recommended)

  1. Click your profile picture (top right) → Settings
  2. In the left sidebar, click "Password and authentication"
  3. Scroll to "Two-factor authentication" and click "Enable"
  4. Follow the prompts to set up 2FA using an authenticator app (Google Authenticator or Microsoft Authenticator — both are free)
Why This Matters for Teaching

When you ask students to create GitHub accounts, their accounts are connected to their professional identity for life. LinkedIn integrates with GitHub. Employers look at GitHub profiles. The habits they form now — professional usernames, two-factor authentication, clear commit messages — follow them into their careers. Teach them right from the start.

Team 1 Connection

sinder38's GitHub account is the architectural foundation of everything Team 1 built. His very first commit — on 30 May 2026 — was Add basic gitignore. A simple one-file commit. By 21 June, the same account was managing 26 branches, 3 CI workflows, and an automated bot. Every sophisticated capability grew from that first commit. Your first commit will do the same.


Tool 2 — Git on Your Computer

📦
Git
git-scm.com

GitHub is the website where your code is stored online. Git is the software on your computer that sends code to and from GitHub. Think of GitHub as a filing cabinet in the cloud and Git as the hands that put files in and take them out. Without Git on your computer, you cannot connect to GitHub from your machine. You will install it once and then barely think about it again — it works in the background.

What to Do — Windows

  1. Go to git-scm.com in your browser
  2. Click the large "Download for Windows" button. The download starts automatically
  3. Once downloaded, open the file (it will be named something like Git-2.45.0-64-bit.exe)
  4. The installer opens. Click "Next" on every screen — the default settings are correct. Do not change anything
  5. On the screen that says "Choosing the default editor used by Git", change the dropdown from Vim to "Use Visual Studio Code as Git's default editor" — you will install VS Code next, and this connects them
  6. Continue clicking "Next" and then "Install"
  7. When installation completes, click "Finish"

Connect Git to Your GitHub Account

After installation, you need to tell Git who you are. Press the Windows key, type cmd, and press Enter to open a Command Prompt (a black window with white text — do not be alarmed, this is normal). Then type each of these commands, pressing Enter after each one. Replace the details in quotes with your own name and email:

# Tell Git your name (as it will appear on your commits) git config --global user.name "Prof Dr Tan" # Tell Git your email (must match your GitHub email) git config --global user.email "your.email@example.com" # Verify the settings were saved git config --global --list
✅ You Know It Worked When
The last command shows two lines: user.name=Prof Dr Tan and user.email=your.email@example.com
❌ If You See an Error
If the Command Prompt says "'git' is not recognized as an internal or external command" — Git was not installed correctly. Go back to git-scm.com and repeat the installation. Make sure to close and reopen the Command Prompt after installing.

Tool 3 — VS Code (Your Code Editor)

📝
Visual Studio Code
code.visualstudio.com

VS Code is the application where you write and edit files. It is like Microsoft Word, but designed for code and text files rather than formatted documents. It understands the files you will be creating — Python scripts, YAML workflow files, Markdown documents — and shows them in colour-coded format that makes them easier to read and write. It is free, made by Microsoft, and used by professional developers worldwide. Team 1 used it as their primary editing environment.

What to Do

  1. Go to code.visualstudio.com
  2. Click the blue "Download for Windows" button
  3. Open the downloaded file and click through the installer. Accept the licence agreement and click "Next" on all screens
  4. On the "Select Additional Tasks" screen, tick "Add to PATH" and "Add 'Open with Code' action to Windows Explorer context menu" — both are useful
  5. Click "Install", then "Finish"
  6. VS Code will open automatically. You will see a welcome screen with a dark background

Install Two Essential Extensions

Extensions make VS Code smarter. You need two for this curriculum:

  1. In VS Code, click the square icon on the left sidebar (it looks like four squares, one separated) — this opens the Extensions panel
  2. In the search box, type Python. The first result should be "Python" by Microsoft. Click Install
  3. Search for GitHub Actions. The first result should be "GitHub Actions" by GitHub. Click Install
✅ You Know It Worked When
VS Code is open, the left sidebar shows several icons, and when you click the Extensions icon you can see "Python" and "GitHub Actions" listed under "Installed".

Team 1 Connection

Every file in Team 1's repository — from the simplest README.md to the complex run_pipeline.py — was written in a code editor like VS Code. When JasonEran built the delta engine on 20 June, making five commits in one day, each commit was a set of file changes saved from his editor and pushed to GitHub. The editor is where the thinking becomes code.


Tool 4 — Python

🐍
Python
python.org

Python is the programming language that powers the market intelligence pipeline. It is the language Team 1 used for every automated script — the agents that collect and analyse data, the pipeline that sequences all the agents, the delta engine that scores predictions. Python is the most widely used language in data science, AI, and automation. It reads almost like plain English, which makes it approachable for educators who are not developers. You do not need to write Python from scratch in this curriculum — you need to understand what a Python script does and how to run one.

What to Do

  1. Go to python.org/downloads
  2. Click the large yellow "Download Python 3.12.x" button (the exact version number after 3.12 does not matter — just make sure it starts with 3.12 or higher)
  3. Open the downloaded file
  4. CRITICAL: On the first screen of the installer, there is a checkbox at the bottom that says "Add Python to PATH". Tick this box before clicking anything else. If you miss this step, Python will not work from the command line
  5. Click "Install Now" (the top option)
  6. Wait for installation to complete, then click "Close"

Verify Python Is Working

Open a new Command Prompt (press Windows key, type cmd, press Enter) and type:

python --version
✅ You Know It Worked When
The Command Prompt shows something like Python 3.12.3 — a version number starting with 3.
❌ If You See "Python is not recognized"
You missed the "Add Python to PATH" checkbox during installation. Uninstall Python from Windows Settings → Apps → Python, then reinstall from python.org, this time ticking the PATH checkbox first.

Install the Three Packages You Will Need

Python packages are add-ons that give Python additional capabilities. Install the three packages this curriculum uses:

# yfinance: fetches stock market data automatically pip install yfinance # requests: sends data to and receives data from APIs (like OpenRouter) pip install requests # python-dotenv: reads secret API keys from a .env file (keeps them private) pip install python-dotenv

Type each line into the Command Prompt and press Enter. You will see text scrolling as each package installs. When it finishes and the cursor is back, move to the next command.

✅ You Know It Worked When
After each pip install command you see a line ending in Successfully installed yfinance-... (or whichever package you just installed).
What yfinance Does — and Why It Matters

yfinance is the package that Team 3 used when ZhangJiayu0201 built their first GitHub Actions workflow in seven minutes on 20 June 2026. The script fetch_friday_closes.py used yfinance to automatically download Friday's closing prices for SPX, NDX, and IWM from Yahoo Finance. Three lines of Python code replaced what had previously been a manual process of visiting a website, reading the numbers, and typing them into a file. This is the exact progression — from manual to automated — that this curriculum is designed to produce.


Tool 5 — OpenRouter API Account

🤖
OpenRouter
openrouter.ai

OpenRouter is the service that allows a single Python script to call ChatGPT, Gemini, and DeepSeek simultaneously, without needing three separate API accounts. It acts as a bridge — you send one request to OpenRouter with the name of the AI model you want, and OpenRouter forwards it and returns the response. Team 1's LLM Operator (sun9226066/Charles) used OpenRouter to build the multi-model synthesis pipeline that became one of the most impressive components of their system. Setting up an OpenRouter account takes five minutes and costs nothing until you start making API calls — and for learning purposes, the costs are minimal (a few cents per test).

What to Do

  1. Go to openrouter.ai
  2. Click "Sign In" in the top right, then "Sign up"
  3. Create an account with your email address
  4. Once logged in, click your profile icon (top right) → "API Keys"
  5. Click "Create Key"
  6. Give it a name: ai-trading-lab
  7. Click "Create"
  8. The key appears — it starts with sk-or-. Copy it immediately and save it somewhere safe (a password manager or a private note). You will not be able to see it again after closing this window

Add Credit to Your Account

  1. Click your profile icon → "Credits"
  2. Add USD $5 of credit — this is enough for many months of learning-level API usage

Store Your API Key Safely

Never put your API key directly in a code file. Instead, you will store it in a .env file — a special private file that Python reads but that GitHub keeps private. You will set this up in Chapter 5. For now, just keep your key copied somewhere safe.

⚠️ Important Security Note
An API key is like a password. Anyone who has your key can make API calls that charge to your account. Never share it in a chat message, never paste it into code that goes to GitHub, and never email it. This is exactly why Professor Dr. Tan's token was revoked when it appeared in a chat conversation — the security scanner found it and cancelled it within seconds.

Team 1 Connection

Team 1 stored their OpenRouter API key as a GitHub Actions secret — a value that is encrypted and only accessible to their workflow scripts. The key was referenced in code as os.environ["OPENROUTER_API_KEY"] — never written directly. When the Weekly Pipeline ran automatically, it retrieved the key from the secret vault, called OpenRouter, got responses from three LLMs, and saved the comparison to data/llm/llm_comparison_W24.md — all without any human intervention. You will do the same in Chapter 10.


Tool 6 — The Terminal (Your Command Centre)

⌨️
Windows Terminal
Built into Windows 11 · Download from Microsoft Store on Windows 10

The terminal — also called the command line, command prompt, or shell — is a text-based interface for controlling your computer. Instead of clicking icons, you type commands. It is less intuitive than clicking, but far more powerful for the kinds of tasks this curriculum involves: running Python scripts, sending code to GitHub, creating folders, and triggering automation. Every developer uses the terminal daily. By the end of this curriculum, you will be comfortable with the eight or ten commands that matter for this work, and that comfort will transfer directly to your ability to help students when they get stuck.

Open the Terminal

On Windows 11: Press Windows key + X, then click "Terminal".
On Windows 10: Press Windows key, type cmd, press Enter.

The Ten Commands You Need to Know

You do not need to memorise these now. Read through them once, then practise the ones marked with ★ before moving on.

# ★ Show what folder you are currently in cd # ★ Move into a folder (replace "FolderName" with the actual folder name) cd FolderName # Go up one level (back to the parent folder) cd .. # ★ List all files and folders in the current location dir # ★ Create a new folder mkdir FolderName # ★ Run a Python script python script_name.py # ★ Send code to GitHub (you will use this constantly) git add . git commit -m "Your message here" git push # Check the status of your Git repository git status # Check your Python version python --version # Clear the terminal screen cls

★ Practise These Three Commands Right Now

  1. Open the terminal
  2. Type cd and press Enter — note which folder you are in (probably C:\Users\YourName)
  3. Type mkdir ai-trading-lab and press Enter — you just created a folder
  4. Type cd ai-trading-lab and press Enter — you are now inside that folder
  5. Type dir and press Enter — the folder is empty, which is expected
  6. Type cd .. and press Enter — you are back in the parent folder
✅ You Know It Worked When
You can navigate into and out of the ai-trading-lab folder using the terminal without error messages. The folder exists and you can see it in Windows Explorer.
The Terminal Demystified

Many educators feel intimidated by the terminal because it looks like hacking. It is not. It is just a different way of talking to your computer. Every GUI (graphical user interface) action — creating a folder, running a program, moving a file — has a terminal equivalent. The terminal is simply faster and more precise once you know the vocabulary. In this curriculum, you will use approximately eight commands repeatedly. After a week, they will feel as natural as clicking a button.


Final Verification — All Six Tools

Before moving to Chapter 5, run through this complete verification checklist. Open a terminal and type each command. Every one should produce a result, not an error.

# 1. Verify Git git --version # Expected: git version 2.45.x (or similar) # 2. Verify Python python --version # Expected: Python 3.12.x # 3. Verify pip (Python package manager) pip --version # Expected: pip 24.x.x from ...python3.12... # 4. Verify yfinance package python -c "import yfinance; print('yfinance OK')" # Expected: yfinance OK # 5. Verify requests package python -c "import requests; print('requests OK')" # Expected: requests OK # 6. Verify Git is connected to your identity git config --global user.name # Expected: your name
✅ All Six Checks Pass
Every command returned an expected result. Your computer is fully equipped. You are ready for Chapter 5 — where you will create your first GitHub repository, make your first commit, and push your first file to the cloud.
⚠️ One or More Checks Failed
Go back to the section for the tool that failed and repeat the installation. The most common issues are: (1) Python PATH not ticked during installation, (2) terminal was not closed and reopened after installing a tool. Close the terminal, reopen it, and try again.
What You Have Accomplished

In one afternoon, you have installed and verified six professional-grade tools — the same tools used by software engineers at companies around the world. You have a GitHub account, Git connected to it, a code editor, Python with the essential packages, an LLM API account, and working command-line skills. Team 1 started with these same tools. Chapter 5 is where you start building with them.