APPENDIX G: LAB SETUP GUIDE

WHAT YOU NEED BEFORE YOU START A computer that can run a terminal, which is a window where you type commands. A programming language and runtime: this guide assumes Python, a widely used beginner-friendly language, because the lab files in the layout below end in the letters py. Install a current, supported version from the official Python website. A code editor, which is a program for writing and reading code. Any plain code editor you like is fine. Basic comfort with command-line tools: you should be able to open a terminal, move between folders, and run a command. An Application Programming Interface (API) key for at least one model provider, or a locally run open-weight model, as explained below. A tool for version control, such as git, so you can save the lab at each stage and return to earlier stages. A sandbox for running code that the agent writes or runs: this can be a container or a virtual machine on your own computer, or a disposable folder with strict limits. A little patience, since the first setup is the hardest part. Step by Step Setup Step 1: Create a project folder named resume_review_agent in a place you will remember. Step 2: Open a terminal inside that folder. Step 3: Create a virtual environment, which is a private space that keeps this project's Python packages separate from the rest of your computer. Step 4: Turn the virtual environment on, then install only the packages the lab needs, and write their names in a requirements file so you can repeat the setup later. Stages 1 through 5 of this lab use only what Python already includes, so the requirements file may stay empty. Step 5: Start version control in the folder and make a first save, which is called a commit. Step 6: Create the sample_data folder and fill it with the fictional files described below. Step 7: Set up access to a model as described in the next section. Step 8: Run the smallest possible test, such as asking the model to say hello, to confirm that everything is connected.