INF 385T Building Large Language Model Applications

“Build an AI Product in 15 weeks and submit to Y Combinator”

The University of Texas at Austin, Fall 2026
M 9:00 a.m.–12:00 p.m. · UTA 1.208
Jiaxin Pei, jiaxinpei@utexas.edu

Syllabus • Schedule • Project • Canvas

Apply for enrollment

Class Philosophy

This is not a lecture-and-exam course. It is a builder course. You will spend the semester designing, building, and shipping a real AI product—one good enough to put in front of real users.

We cover LLM fundamentals not as an end in themselves, but as tools you need to build something great. The best way to learn what LLMs can and cannot do is to push them to their limits on a problem you care about.

We welcome students with diverse backgrounds—science, engineering, design, business—as long as you are strongly motivated to build something great. We especially welcome PhD students from all areas who want to apply LLMs to their own research domains. The strongest teams combine people who can code, people who can design experiences, and people who have deep understanding of a specific domain.

We hold ourselves and our students to the highest standard. This course is fast-paced and demanding—expect to invest serious time and energy every week. But if you are passionate about building with AI and ready to put in the work, you will leave with a product you are proud of, skills that transfer directly to industry, a portfolio piece that speaks for itself—and, ultimately, an opportunity that changes your life.

The semester culminates in a public demo day with investors from top venture capital firms. Standout teams will have fast-track access to leading accelerator programs to continue building beyond the classroom.

Interested in sponsoring or collaborating?
We welcome partnerships with investors, accelerators, and industry sponsors who want to connect with the next generation of AI builders. Reach out at jiaxinpei@utexas.edu.

Syllabus

Prerequisites

Comfortable writing Python applications, using APIs, and working in a terminal. Prior experience with machine learning or natural language processing is also required.

Course materials

  • Readings and resources will be provided via hyperlinks under Schedule.
  • Exercises, code, etc. will be posted on Canvas.

Course overview and objectives

This course explores the design and development of practical applications powered by large language models (LLMs), with an emphasis on frontier application categories such as coding agents, personal agents, vertical AI, AI-native distribution, and multi-modal systems. Core technical concepts such as prompting, retrieval-augmented generation, embeddings, structured outputs, orchestration, safety, and evaluation are taught in the context of building products rather than as isolated abstractions, with additional technical foundations provided as a Canvas reference page. The course is project-driven: students rapidly prototype individual demos, form teams around the strongest ideas, and then build, test, and pitch an LLM-based application with guidance from founders, investors, and researchers.

By the end of this course, students will be able to:

  1. Design and build a working LLM-powered application from idea to deployed product
  2. Apply core techniques—prompting, RAG, orchestration, agentic tool use, and multi-modal integration—to solve real-world problems
  3. Evaluate LLM systems for quality, safety, and cost
  4. Iterate on a product based on real user feedback
  5. Communicate and present an AI product to technical and non-technical audiences

Schedule

💡
Landscape
Week 1
Survey frontier AI products and opportunities
🧱
Ideate & Build
Weeks 2–4
Coding agents, personal agents, 3 demos
🎤
Lightweight Demo Day
Week 5
Present, vote, form teams
🔨
Team Build
Weeks 6–9
Vertical AI, evals, GEO, safety
🧪
Beta Test
Week 10
Demo & real user testing
🔄
Iterate & Ship
Weeks 11–15
Multi-modal, costs, moats, pitch practice
🚀
Public Demo Day
Week 16
Pitch to investors

Schedule is tentative and subject to change. Guest speakers are distributed throughout the semester rather than concentrated in standalone guest-lecture weeks.

Week 1 (8/24–8/28) – The AI application landscape

Week 2 (8/31–9/4) – Coding agents

Week 3 (9/7–9/11) – Labor Day week

  • Labor Day 9/7; no class.
  • Product to explore: [TBD]
  • Homework: Use a coding agent to build the second demo of the LLM application you want to build

Week 4 (9/14–9/18) – Personal agents & the agentic web

Week 5 (9/21–9/25) – Lightweight demo day

  • Students present their demos, review products others built, vote on the most promising ideas, and form teams for the class project.

Week 6 (9/28–10/2) – AI for vertical domains: law, finance, healthcare

Week 7 (10/5–10/9) – Evaluation, testing & red-teaming

Week 8 (10/12–10/16) – Multi-modal applications & world models

Week 9 (10/19–10/23) – Voice AI and conversational interfaces

Week 10 (10/26–10/30) – Demo day & beta test

  • Teams present their applications and run beta testing with real users.

Week 11 (11/2–11/6) – Generative engine optimization & AI-native distribution

Week 12 (11/9–11/13) – Cost optimization and deployment

Week 13 (11/16–11/20) – AI economics, moats, and go-to-market

Week 14 (11/23–11/27) – Thanksgiving break

  • No classes.

Week 15 (11/30–12/4) – Final guest lecture & pitch practice

  • Final guest lecture from a researcher or founder on what is next, followed by in-class pitch practice and feedback.
  • Guest speaker: [TBD]
  • Homework: Final iteration. Polish demo day presentation

Week 16 (12/7) – Public demo day

  • Last class day.

Technical foundations (Canvas reference page) {: .no_toc }

These materials are not lectured as standalone units, but are available for students to consult as needed while building.

Course requirements and grading policy {: .no_toc }

  • Individual assignments (30%) — Weeks 1–4
    • Week 1: Four one-pagers on AI products
    • Weeks 2–4: Three individual demos built with AI tools
  • Class project (60%) — Weeks 5–16
    • Teams of 3 students with complementary expertise (e.g., engineering, design, domain knowledge).
    • Grading based on:
      • Lightweight demo day presentation (Week 5)
      • Beta test and demo day (Week 10)
      • Iteration progress and user feedback incorporation (Weeks 11–15)
      • Public demo day (Week 16)
  • Peer review and participation (10%)
    • Reviewing and voting on classmates’ demos (Week 5), beta testing other teams’ products (Week 10), and engagement with guest speakers.
  • The course will use plus-minus grading, using the following scale:
GradePercentage
A≥ 93%
A-≥ 90%
B+≥ 87%
B≥ 83%
B-≥ 80%
C+≥ 77%
C≥ 73%
C-≥ 70%
D+≥ 67%
D≥ 63%
D-≥ 60%

Academic integrity and AI tools {: .no_toc }

This course requires you to use AI tools — ChatGPT, Copilot, Cursor, and whatever else helps you build. Building on the shoulders of AI is a core skill this class teaches.

That said, using AI tools does not remove your responsibility to understand what you submit. You must be able to explain every piece of your work — how it works, why you made the choices you did, and what the tradeoffs are. If your only answer is “the AI told me to do it,” that is not your own work.

You are encouraged to discuss ideas with classmates, consult external resources, and use open-source code. However, you must cite any substantial external code or resources you incorporate. For individual assignments, the work you submit must reflect your own understanding. For team projects, all team members are expected to contribute meaningfully and be able to speak to the full scope of the project.

Notice about students with disabilities {: .no_toc }

The University of Texas at Austin provides upon request appropriate academic accommodations for qualified students with disabilities. Please contact the Division of Diversity and Community Engagement, Services for Students with Disabilities, 512-471-6259.

Notice about missed work due to religious holy days {: .no_toc }

A student who cannot meet an assignment deadline due to the observance of a religious holy day may submit the assignment up to 24 hours late without penalty, if proper notice of the planned absence has been given. Notice must be given at least 14 days prior to the due date. For religious holy days that fall within the first 2 weeks of the semester, notice should be given on the first day of the semester. Notice should be emailed to the instructor and course staff.