CMU 15-113 + 15-114: Effective Coding with AI

Fall 2026

Looking for last semester? Visit the Spring 2026 course website to see that semester's schedule and materials.
15-113 (mini 1) Prerequisites: 15-110 Principles of Computing or above
15-114 (mini 2) Prerequisites: 15-113 and 15-112 Fundamentals of Programming and CS or above
Time Commitment: 6 hours/week (3 hours in class + 3 hours outside work)
Semester: Fall 2026
Instructor: Mike Taylor (mdtaylor at andrew.cmu.edu)
Note: This is still a pretty new course, especially with the 113/114 split!
The general description and themes shouldn't change much, but we will adapt the schedule, policies, and assignments as necessary.

Description

This application-focused course will teach students how to effectively combine intermediate programming skills with contemporary AI tools to enhance their software development workflow. Students will explore the capabilities and limitations of current AI coding assistants, experiment with prompt engineering, and collectively develop standards for maintaining code quality, transparency, and ethical integrity in AI-augmented workflows. The course will also feature seminars from AI experts in industry and academia. Through weekly coding projects, students will rapidly build complete applications while balancing creative problem-solving with rigorous quality assurance. A collaborative approach emphasizes peer learning, with students sharing discoveries and contributing to evolving best practices for prompting and evaluating AI-generated code, ensuring proper attribution, and establishing transparent development protocols. These projects are also designed to jump-start students' portfolios for future employment. By completion, students gain practical development experience with AI tools and will contribute to evolving best practices for future courses, learning from both instructors and peers' experiences with these rapidly advancing technologies.


15-113 and 15-114: Please read! 15-113 was originally a full-semester course in Spring '26 that required 15-112 as a prerequisite. To meet the demand for an accessible version for students with 15-110, we have now split the original 15-113 into two minis: 15-113 (Part 1, mini 1) and 15-114 (Part 2, mini 2). Students who meet the 15-110 prereq can take 15-113 (mini 1). Students who meet the 15-112 prereq can take 15-113 and then 15-114 to get the full semester experience. This is a slightly unconventional solution with some peculiarities, so if you have any questions, please do let me know. The goal is to provide a great experience for as many of you as possible.


Course Goals: By completion, students gain practical development experience with AI tools and will contribute to evolving best practices for future courses, learning from both instructors and peers' experiences with these rapidly advancing technologies.

The Portfolio Approach

For your first major assignment, you'll build a personal portfolio website using AI (even if you have no prior experience with HTML or web development).

Add your work from other courses and projects and you'll be able to show off your best work for future internships, jobs, and graduate school applications.

This video shows some of the excellent projects students created during Spring 2026. You can find more of their work here! This course jumps into AI-assisted programming from Day 1. We'll alternate between class discussions and regularly building cool stuff, with the goal of finishing the semester with refined strategies for using AI effectively and responsibly.

Guest Lectures

Throughout the semester, we'll host guest lectures from experts in computer science, software engineering, and machine learning/AI research. These engineers and researchers will share:

Tentative Schedule: The schedule of topics presented below is tentative, and may shift to accommodate our guest lectures. Specific dates and speakers will be announced as confirmed. Ideally these will mostly occur during class time, though occasionally we may have optional presentations outside of our normally-scheduled sessions.

Learning Objectives

AI as Force Multiplier: Modern AI tools can be very powerful, but to use them effectively requires us to combine the speed and generative capabilities of AI with our critical thinking and problem-solving skills. This course teaches you how to strategically leverage AI tools to enhance your productivity and versatility while maintaining code quality and strong ethical standards.


At the end of the course, students should be able to:

Ethics Discussions

Ethics discussions will include the following topics:

Please email Mike if you have ideas for additional topics that would be of interest!

The 15-113 Team

Faculty

Mike Taylor

Head TA

Taha Shakeel

Teaching Assistant

Nazanin Ghazi

Teaching Assistant

Alex Chen

Teaching Assistant

Michelle Jiang

Teaching Assistant

Jack Yu

Schedule

Week Mon 12:30pm-1:50pm Wed 12:30pm-1:50pm Assignments Cool Stuff
Week 1
8/24-28
Intro to GenAI		 Lecture 1 Slides
Welcome
• Course intro
• Course ethos
• Useful Tools		 Lecture 2 Slides
Building your Portfolio
• Project 1 description
• HTML crash course
• "My First Webpage"		 HW1:
Intro Survey
(due Sat 8/29 8pm)
Start Project 1		 Guide: Project 1 setup
Guide: Github branches
Week 2
8/31-9/4
AI Intro Cont'd		 Lecture 3 Slides
  • Early Data
  • AI-augmented IDEs
  • VS Code and Copilot
 Lecture 4 Slides
  • Prompting strategies
 Project 1
(due Sat 9/5 8pm)		 Project 1 Example: Taha
Week 3
9/7-11
Core prompting strategies		 No Class: Labor Day Lecture 5 Slides
  • First project reflection
  • Kiro
  • Sprinty Road
 HW2
(due Sun 9/13 8pm)
15-113 is complete after Week 7
FALL BREAK (10/12 - 10/16)
15-114 begins in week 8 after Fall Break

Grading

Component Weight Notes
Homework 20% Mostly smaller, weekly projects. Grading based on evidence of effort, due Fridays
Participation 20% Includes attendance, contribution to discussions and critiques/code reviews, and good collaboration
Big Projects 30% Open-ended. 2 in 15-113, 1 in 15-114
TA meetings 10% Assignments will typically include brief check-in discussions with TAs to help you plan and/or review your work.
Oral project evaluations + quizzes 20% After each project, you will complete an interview with a TA in the style of a mock job interview. You will be evaluated primarily on your process, transparency, and overall ownership if your work. If we choose to have any quizzes, they will count toward this category.

Letter Grades

A: [90-100], B: [80-90), C: [70-80), D: [60-70), R: [0-60)

Grading Philosophy: This course emphasizes effort, growth, and understanding over perfection. Grades reflect engagement with the material, demonstration of learning, and thoughtful use of AI tools. Code doesn't need to be production-perfect, but you must understand it and be able to explain your choices.

Projects

(Note that Projects 2 and 3 are especially tentative and subject to change)

Project 1: Personal Portfolio Website (Weeks 1-2)

Goal: Build a professional portfolio website to showcase your work—using AI to learn web development from scratch

Time: ~6 hours outside class, over two weeks

Context: Most students have never built a website before. This project teaches you to use AI as a learning tool to master new domains (HTML, CSS, JavaScript) while creating something immediately useful.

Requirements:

Deliverables: Live URL, GitHub repo, informal reflection (don't use AI to write this part or do the thinking for you)

Important: Throughout the semester, you'll add each new project to your portfolio. By Week 14, you'll have a complete showcase of your work!

Project 2: Capstone 1 (Weeks 6-7)

Goal: Build a complete, deployed web application

Time: ~9 hours outside class, over two weeks

Requirements: Should include at least one and ideally two of the following: Frontend-backend communication, API usage with authorization, databases, data analysis/visualization, rich interactivity, computer vision or ML. See project writeup for more details.

Examples:

Deliverables: Deployed application with live URL, GitHub repo, demo video, README and prompt log, posted your portfolio website. Will include midpoint checkin and final presentation.

Note: This will be the final project for 15-113 Mini 1. If you are continuing on to Mini 2, you might want to save your very best and most ambitious idea for Capstone 2.

Project 3: Capstone 2 (Weeks 13-14, 15-114 only)

Goal: Make something extremely cool that demonstrates your technical skills and design sensibilities, while using AI effectively as part of your process. This project should be portfolio-ready.

Time: ~9 hours outside class, over ~2 weeks

Requirements: Must include at least two of the following: Frontend-backend communication, thoughtful third-party API usage with secure keys, database, Expo/React Native (phone app), substantial data analysis/visualization, rich interactivity (e.g. WebGL), or computer vision/ML. See project writeup for details.

Examples:

Deliverables: Source code on GitHub (with README, prompt log, and reflection), live demo, short demo video, Google form submission. Includes midpoint check-in and final oral exam/presentation.

Course Policies

AI Usage Policy

Philosophy: Transparency and learning over restriction

Required:

Encouraged:

Not Allowed:

Verification: The instructor may ask you to explain any part of your submitted code, your process for creating it, or possible trade-offs and alternatives. Honesty and transparency always yields the best outcomes. (We care more about transparency than exactly how much AI you relied on.)

Collaboration Policy

Highly Encouraged:

Not Allowed:

General guidance: If you can teach them how to do it, great! If you're just giving them the answer, or if they can't recreate the work on their own without referencing notes or the original, you aren't collaborating. Ask if you aren't sure if something counts as good collaboration.

Academic Integrity

Core philosophy: You must understand and be able to explain all submitted code at a reasonably high level (what does it do, what tech does it use, how do you know it works) though we do expect that there will be some code that you might not be able to explain line-by-line (and that's ok). More importantly, you must represent your work and your submissions with thorough transparency and proper attributions. When in doubt, ask if something is acceptable!

Violations include:

Consequences: Penalties up to course failure, reported to university

As long as you're attempting to be transparent and well-intentioned, you don't really have to worry about academic integrity violations in this class. Still, negligence or uncertainty is not an acceptable excuse. When in doubt: Ask! Better to ask than assume.

Late Policy

Homework:

Major projects:

Graded meetings/interviews or other assessments:

Extensions and Excused Absences

If you need an extension or an excused absence due to extenuating circumstances such as medical or family emergencies or university-related conflicts, please fill out this form.

Tools and External Resources

Required Tools (All Free for Students)

Course Materials

Office Hours and Support

Getting Help

Accommodations

Students with documented disabilities should ensure that their memorandum of accommodations has been sent to 15-113/15-114 through the Office of Disability Resources portal. Soon after we receive your memorandum, we'll contact you with additional information on how you can use these accommodations. All tools and activities will be evaluated for accessibility, and alternatives will be provided as needed.

Data Collection

For this class, and in addition to the data we are collecting to form our class-wide best practices, I am planning to conduct research on educational outcomes in collaboration with the Eberly Center. This research will involve your coursework. You will not be asked to do anything above and beyond the normal learning activities and assignments that are part of this course. You are free not to participate in this research, and your participation will have no influence on your grade for this course or your academic career at CMU. If you do not wish to participate or if you are under 18 years of age, please send an email to Chad Hershock (hershock@andrew.cmu.edu), and then your data will not be included. Participants will not receive any compensation. The data collected as part of this research will include student grades. All research-related analyses of data from participants’ coursework will be conducted after the course is over and final grades are submitted. In the future, once we have removed all identifiable information from your data, we may use the data for our future research studies, or we may distribute the data to other researchers for their research studies. The Eberly Center may provide support on this research project regarding data analysis and interpretation. The Eberly Center for Teaching Excellence & Educational Innovation is located on the CMU-Pittsburgh Campus and its mission is to support the professional development of all CMU instructors regarding teaching and learning. To minimize the risk of breach of confidentiality, the Eberly Center will never have access to data from this course containing your personal identifiers. All data will be analyzed in de-identified form and presented in the aggregate, without any personal identifiers. If you have questions pertaining to your rights as a research participant, or to report concerns to this study, please contact Chad Hershock (hershock@andrew.cmu.edu).

Additional notes