| Component | Weight |
|---|---|
| Assignment 1 — experience a coding agent | 10% |
| Assignment 2 — build an agent | 10% |
| Assignment 3 — make the agent smarter, faster, cheaper | 20% |
| Assignment 4 — serve your own agent | 10% |
| Assignment 5 — optimize the full stack | 20% |
| Final Project | 16% |
| Paper Presentation | 10% |
| Class Participation | 4% |
| Bonus (course feedback & problems AI cannot solve) | up to 10% |
You have eight late days for the semester, to spend as you like across the assignments. Late days are counted in whole days: a submission one minute past the deadline consumes one full late day.
For Assignment 3, Assignment 5 and the project, the write-up is a published blog post and the deadline is the moment the pull request is open — not the moment it is merged.
We plan to host guest speakers from industry who build the systems we study. These are among the most valuable sessions of the course and attendance is expected. Please come with questions — the speakers are giving up their time and a silent room is a wasted opportunity.
Recording, photographing, or redistributing guest lectures is not permitted unless the speaker explicitly agrees.
We will arrange meetings with the speakers to ensure that all students have the opportunity to interact with them. There will also be a optional lunch for anyone who wants to meet the speakers in a more relaxed setting.
Up to 10% of bonus credit.
This field moves faster than model training runs, so a great deal of what these systems "know" about GPUs, serving frameworks, and kernel APIs is quietly out of date. Finding those gaps is a genuinely useful skill and it is the point of this exercise. A submission needs all four of:
You are encouraged to use AI tools in this course.
Disclose. Every submitted artifact must include a short note describing which tools you used and for what: a couple of sentences is enough. Undisclosed AI use is an integrity violation; you will not be penalized for using AI tools in your assignments.
Hand in the record. Each assignment submission takes three artifacts: your code, the write-up and an archive of your Claude Code session files. We read these to see how the class is working with an agent and to give you feedback on it, and they may be used in grading as the evidence behind the process claims in your write-up. They add no separate weight to the breakdown above.
Own it. You are responsible for everything you submit. If an AI tool generates code with a subtle bug, a benchmark with a methodological flaw, or a claim about a paper that the paper does not make, that is your error. In discussion, in your presentation, and in questions afterwards, you will be expected to explain your own work without assistance.
Attendance is expected. Participation is 4% of the grade and cannot be earned from an empty seat.
Laptops and tablets are welcome for note-taking and learning. Please keep them closed during student presentations and guest lectures; presenting to a wall of screens is dispiriting, and your classmates deserve the same attention you will want when it is your turn.
If you must miss a class, no permission is needed — but let the instructor and TFs know in advance.
Harvard supports students in observing their religious and spiritual traditions while participating fully in their academic work. If a religious or spiritual observance conflicts with a class meeting, an assignment, or any other course requirement, please contact me as early as possible so that we can try to identify an appropriate academic flexibility consistent with course requirements and University policies.
Because observances and practices vary across traditions and individuals, you do not need to limit requests to dates included on a published religious calendar. Students are encouraged to review the Harvard Multifaith Calendar and the Harvard Chaplains resources at the beginning of the semester, and to communicate anticipated conflicts early whenever possible.
Discussing ideas with classmates is encouraged. Reading papers together, arguing about a design, and debugging alongside each other are all part of how systems work gets done.
What is not acceptable: submitting work you did not do, copying text or code without attribution, fabricating experimental results, or misrepresenting what a measurement shows. Fabricated numbers are the one thing in this course that will be treated as a serious violation without exception — a systems paper whose evaluation cannot be trusted is worthless, and the same holds here.
Half the final project is peer-scored, which puts two more items on that list: agreeing with somebody to trade favourable scores, and marking somebody down over a critical review you believe was theirs. Reviews are anonymous to the presenter and signed to the instructor for exactly that reason.
Cite your sources: papers, blog posts, repositories, and AI tools alike. All work is subject to the Harvard College Honor Code and to GSAS academic integrity policy where applicable.
This course is intended for students of all backgrounds. Students come to AI systems from machine learning, from operating systems, from computational biology, and from industry, and the mix is what makes the discussions interesting. Nobody arrives knowing all of it.
Students needing academic accommodations should contact the Disability Access Office and let the instructor know as early in the semester as possible, ideally within the first two weeks.
Auditors are welcome if there is room. Please email the instructor before the first class. Auditors are expected to do the reading for discussion sessions they attend — the discussion format depends on it — but do not submit assignments and are not graded.
Graduate systems courses have a way of expanding to fill all available time. The five assignments are substantial, and the final project runs on top of the last of them — so scope the project to what the weeks actually hold rather than to what you would like it to be. If the workload is becoming unmanageable, talk to the instructor before it becomes a crisis; project scope in particular can usually be adjusted.
Harvard has resources available at any hour:
Your health matters more than any deadline on this page.
Questions that come up most often. If yours is not here, email the instructor or come to office hours — if it is a good question it will end up on this page.
No, and no assignment requires it and we do not assume prior CUDA experience. One to two classes cover GPU architecture and programming to help you understand the basics enough to reason about serving cost. You can self-learn more if you would like to take the kernel-level optimization path in Assignment 5.
No. Model quality matters here as a constraint and a measured outcome, not as the course's central object of study. We ask what it costs to serve an agent, and how an agent and system change moves cost, latency, throughput, or task success. If you want to study model architectures, or learning theory, this is the wrong course. If you want to know why inference is memory-bound and what anyone can do about it, this is the right one.
You need to know Python and shell. You may touch JavaScript, C/C++, Rust or other programming languages during the course, but your agent should be able to help you navigate it.
Attendance is expected and participation is part of your grade.
No, the lectures will not be recorded.
Yes, if there is room — email the instructor before the first class. We are not able to provide access to computing for auditing students.
No — no midterm and no final.
No. We will cover all costs for the course as long as it is reasonable use for the course.
Plan on the reading a few papers each week, plus the five assignments. Expect to spend a significant amount of time learning and experimenting on your own after class. If you want an A, plan on it.
Email the instructor or come to office hours. If it is a good question it will end up on this page.