Graded Assignment V: Coding with Generative AI

Author
Affiliation

Jelmer Poelstra

CFAES Bioinformatics Core, Ohio State University

Published

October 30, 2025

Overview

This graded assignment is worth 10 points and is due on Monday Nov 3rd at 11:59 pm. You will practice with using generative AI to help you with coding tasks.

Because this is such a free-form assignment, Monday’s recitation session will not cover this assignment. Instead, Monday’s session will be an opportunity for you to ask questions about, or a recap of, other course material.

Directions and grading

Submission expectations

  • Deadline: Monday Nov 3rd at 11:59 pm (you are being given extra time because this assignment was provided to you so late)
  • Submission: You will submit your assignment by tagging the instructor in an Issue in your GitHub as per the last step below

Academic integrity

Use of generative AI Tools (e.g. ChatGPT, Microsoft Copilot, Google Gemini) is permitted
Getting help on the assignment is not permitted
Collaborating, or completing the assignment with others, is not permitted
Copying or reusing previous work is not permitted
Open-book research for the assignment is permitted
APA Citations and/or formatting for this assignment are not required

Rubric

You can earn a total of 10 points:

  • 8 points for the generative AI exploration part
  • 2 points for the Git/GitHub part

Detailed steps

Setting up & Git

  1. Open your own VS Code installation and connect it to OSC. Create a new dir for this assignment, /fs/ess/PAS2880/users/$USER/GA5, and switch to that dir in VS Code using the “Open Folder” option. This should be your working dir for the entire assignment.

  2. Initialize a Git repository. Commit to the repo throughout the assignment as you see fit, but as per usual, more granular commits are better than fewer large ones. Use and commit a .gitignore file as appropriate.

  3. Create a README.md and open it. This should be your main document for the assignment, where you document your trials with generative AI tools.

Main assignment: explore using genAI tools

  1. Explore the use of genAI tools to help you with coding tasks and and document your trials. Make sure to read all the text below before you start.

  • You can use whichever genAI tool(s) you like, though we recommend that you use VS Code integrated AI (GitHub Copilot and/or Google Gemini via the extension) for at least part of the assignment. You can also compare different options (e.g. Microsoft Copilot in the browser vs. GitHub Copilot in VS Code) with the same prompt.

  • You can ask whatever questions you like, within the following guidelines:

    • Keep them somewhat simple and in line with what we have so far been doing in the course without AI assistance (e.g., don’t go and ask for an entire complex analysis pipeline or some kind of app)
    • Ask it for Unix shell (Bash) code and/or scripts
    • Try at least one question that you (more or less) know how to do yourself
    • Try some questions that you don’t know how to do yourself
    • You are free to start exploring things that you think will be useful for your final project, but this is not required

  • Run the code the AI provides you with, and check to the best of your abilities whether the code seems to be correct and does what you want it to do (if you don’t know how the code works, ask the AI to explain it to you, and also check whether the answer seems to make sense). In at least a few cases, follow up on your questions, e.g. if the answer doesn’t seem correct or if you would like to see an answer that uses different commands or options.

  • You should have at least 4 distinct trials documented in your README.md file. Each trial should involve a different task, and at least some of these trials should include follow-up questions.

  • Document your trials in the README.md file. For each trial, include:

    • The exact prompt you used
    • The AI tool you used
    • The code it provided you with
    • Whether the code worked as intended
    • Any follow-up questions you asked, and their answers
    • Your own evaluation of the experience (e.g., usefulness, correctness of answers, ease of use, etc.)
    • Any other relevant notes

  • Additionally, include at least 2 screenshots of what you did, showing questions and answers. These screenshots should be uploaded to OSC and included in your Git repo.

Publish your repo on Github

As before, you’ll publish your Git repo on GitHub and “hand in” your assignment by creating a GitHub Issue.

  1. Create a repository on GitHub, connect it to your local repo, and push your local repo to GitHub.

  2. Create a new issue and tag GitHub users menukabh and jelmerp, asking us to take a look at your assignment.

Back to top