Learning outcomes, structure, and expectations
What this course is about#
COMP4020/8020 is a studio-based course on rapidly prototyping web apps with LLM-based coding agents. Each week pairs a lecture on concepts and techniques with a studio crit session where you demo your work-in-progress prototype and get feedback from peers and tutors — the lecture structure and the studio crit model cover how each half of the week runs. The full course description, and the learning outcomes below, are also on the front page of this website.
The semester comes in two halves, and this site calls them that throughout. In the static half, up to the week 7 lecture, everything you build is client-side and deploys to GitHub Pages. In the full-stack half after it, your prototypes get a server and a database, and deploy to Fly.io.
Learning outcomes#
By the end of the course you will be able to:
- design, build and test full-stack web applications using a rapid-prototyping process
- explain how LLM-based coding agents work, including model capabilities, tool use and context management
- design and evaluate different LLM agent workflows for software development
- apply principles from the scholarly literature to work-in-progress and finalised software prototypes
How the course reads its literature#
The fourth outcome draws on two bodies of literature, and the course treats them differently. The first is settled scholarship: the studio and reflective-practice tradition — Schön’s reflective practicum, the feedback and deliberate-practice literature — that shapes the crit and the assessment model. You apply its principles every week: the crit protocol and the standing reflection prompts are that literature, enacted on your own work-in-progress prototypes. The second is the field’s own literature on agentic coding, which moves faster than peer review: the sharpest current thinking about workflows and harnesses appears in practitioner writing — posts, talks, framework documentation — and can change within a semester. Read it with scholarly habits anyway: situate the claim, weigh its evidence, notice what it’s selling.
Labels#
Course items carry a short label used across the site: crits are C1–C10 and assignments are A1–A3. Crits are numbered by their own sequence, not their teaching week: a crit runs the week after its number, so C4 is the week 5 crit. A bare C4 or A2 always means this.
Expectations#
The course requirements are listed in one place: your participation — the week-1 setup, the weekly rhythm, the assignment deadlines and the standing responsibilities, each line linking to the page with the detail.
Workload#
This is a 6-unit course with an expected workload of around 130 hours across the semester — lectures, studio crits, and independent work outside class. The weekly crit cadence spreads that work across the semester, so plan for steady effort each week rather than a late surge.