INF 385T Building Large Language Model Applications

“Build an AI Product in 15 weeks and submit to Y Combinator (or other accelerators)”

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

Confirmed speakers • Syllabus • Schedule • Project • Canvas

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.

If you want to build AI products that people use in the real world, have been thinking about starting a company but are unsure how to make it happen, or have built promising prototypes without a path to turn them into real products, this is the class for you. We created this course to help you think bigger, build faster, and launch serious AI products alongside ambitious peers, top startup founders, and world-class investors.

While this is listed as a graduate-level class, we welcome both undergrad and grad students with diverse backgrounds—science, engineering, design, business—as long as you are strongly motivated to build something great. We 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.

Confirmed speakers

Syllabus

Prerequisites

Students should be comfortable with using coding agents to build things. You don’t need to be super technical but you need to be willing to build.

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 is organized around one central activity: building an AI product that real people can use. In the first part of the semester, students study the current AI application landscape, talk with potential users, and turn an idea into a prototype and pitch. After a lightweight demo day, students form teams around the strongest ideas and spend the rest of the course turning one prototype into a more serious product.

Class time mixes guest lectures from venture capitalists and startup founders, in-class work on the product, and advising. As students develop their projects, we cover coding and personal agents, AI-native distribution, timing, demand, and product, then personalized group advising and preparation for the internal demo day. After the internal demo day, we reflect on what landed, then cover how to pitch and take a product to market, along with defensibility. Students will test their products with real-world users, and at the end of the semester, we will hold a public demo day where teams can pitch directly to investors.

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

  1. Identify promising AI product opportunities by analyzing frontier products, user needs, and startup market signals
  2. Use coding agents and modern LLM APIs to rapidly prototype multiple working demos
  3. Build a team project that integrates agentic workflows, retrieval or memory, structured outputs, evaluation, and multi-modal or voice capabilities where appropriate
  4. Test an AI product with real users, measure quality and failure modes, and iterate based on feedback
  5. Figure out deployment cost, reliability, safety, distribution, defensibility, and go-to-market strategy for an AI application
  6. Present a polished product demo and pitch the product to broad audiences and investors

Schedule

💡
Landscape
Week 1
Survey frontier AI products and opportunities
🧱
Ideate & Build
Weeks 2–4
Coding agents, pitch deck, prototype
🎤
Lightweight Demo Day
Week 5
Present, vote, form teams
🔨
Team Build
Weeks 6–10
Distribution, timing and demand, advising, demo prep
🧪
Internal Demo Day
Week 11
Demo & real user testing
🔄
Iterate & Ship
Weeks 12–15
Demo reflections, pitching, moats, go-to-market
🚀
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

  • Course introduction. Rapid-fire tour of frontier application areas: coding agents, personal agents, vertical AI, generative engine optimization, agentic web, and world models. The goal is to help students see what exists, who is building it, and where ambitious project ideas may come from.
  • Readings
  • Homework
    • Combine HW1 and HW2 into a single PDF and submit one file.
    • HW1 (50 points): Go through the Y Combinator Startup Directory and check startups from 2026. Earlier years are fine, but newer companies are strongly recommended.
      • Check at least 10 startups' websites. You should check more.
      • Select the most interesting one, use their product (talk to their founder if possible), and write a one-pager about it.
      • In your one-pager, include the 10 companies' names and websites. Discuss why that specific company is interesting to you (technology, business, and product), and write about your thoughts after exploring their product and talking to them.
      • Do not ask ChatGPT to find 10 companies from the YC startup directory, and do not ask it to write the one-pager. You may use AI to brainstorm and to help you dig into the company.
    • HW2 (50 points): Write about one AI application or product you would like to build.
      • What is the burning question?
      • Who will be the potential customers?
      • How big can it become if you do everything right?
      • Who is working on relevant things, and why is your idea different?
      • Talk to a potential customer or user and ask for their feedback.
      • How much will they be willing to pay?
      • What do they actually need?
  • Launch Party: We had an amazing launch party on Aug 24. Thanks Antler VC for hosting!

Week 2 (8/31–9/4) – Coding agents

Week 3 (9/7–9/11) – Labor Day week

  • Labor Day 9/7; no class.
  • Homework
    • A working prototype for your product. Due Sep 12, 11:59 p.m.
      • Submit one PDF. Put a link to your demo at the beginning of the PDF.
      • The demo must be hosted at a publicly accessible link. If you need web hosting, AWS provides a free-tier server.
      • Refine your pitch deck based on the latest demo, and create a teaser for your product (5 slides). See Investopedia, Teaser.
      • Finish the two required coffee chats. Include two group photos at the end of your pitch deck.
      • Combine the teaser and the updated pitch deck into a single PDF, with the teaser first and the full pitch after it.

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.
  • Homework
    • If you do not need to pivot, write a short reflection on your progress so far, or on anything else worth mentioning. If you need more customer validation or a pivot, revise your idea and decide what to do next. Feel free to message the instructor on WhatsApp if you want to talk.

Week 6 (9/28–10/2) – AI-native distribution

Week 7 (10/5–10/9) – Timing, demand, and product

  • Why this product, why now, and who it is for. We discuss timing (why the product is possible and needed now), demand (who the customer is and how strong the need is), and the product itself (what you ship and why it is different).
  • Homework
    • Play PartnerSim. Submit a one-pager by Oct 10, 11:59 p.m.
      • What you need to achieve by Week 10
      • Progress on the product
      • Progress on customers
      • Reflections based on feedback from peer groups

Week 8 (10/12–10/16) – Personalized group advising

  • Personalized advising with each project group. Teams meet with the instructor to review progress, pressure-test the idea, and decide what to do next.
  • Homework
    • Build application in teams

Week 9 (10/19–10/23) – Personalized group advising

  • A second round of personalized advising with each project group, focused on what still needs to change before the internal demo day.
  • Homework
    • Play PartnerSim. Submit a one-pager by Oct 24, 11:59 p.m.
      • What you need to achieve by Week 10
      • Progress on the product
      • Progress on customers
      • Reflections based on feedback from peer groups

Week 10 (10/26–10/30) – Preparing for the internal demo day

  • How to get ready for the internal demo day: what to show, how to tell the story, and what still has to be true about the product and the customer.
  • Homework
    • Deck for Demo Day II: Upload your presentation for Demo Day II next Monday.

Week 11 (11/2–11/6) – Internal Demo Day

  • Teams present their applications and run beta testing with real users.
  • Homework
    • Iterate based on real user feedback

Week 12 (11/9–11/13) – Demo day reflections, pitching, and go-to-market

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.
  • Homework
    • Final iteration. Polish demo day presentation

Week 16 (12/7) – Public demo day

  • Last class day.

Technical foundations (Canvas reference page)

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

Course requirements and grading policy

  • Individual assignments (30%) — Weeks 1–4
    • Week 1: Two writeups (50 points each), submitted as one PDF — a one-pager on a YC startup you explored, and an AI application you want to build
    • Week 2: A survey of relevant companies and competitors, customer conversations, and a 12–13 slide pitch deck
    • Week 3: A publicly hosted prototype, a 5-slide teaser, and an updated pitch deck
    • Week 4: A refined pitch deck and demo for the lightweight demo day
  • 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)
      • PartnerSim one-pagers (Weeks 6, 7, and 9) and the Demo Day II deck (Week 10)
      • Internal Demo Day (Week 11)
      • Iteration progress and user feedback incorporation (Weeks 12–15)
      • Public demo day (Week 16)
  • Peer review and participation (10%)
    • Reviewing and voting on classmates’ demos (Week 5), beta testing other teams’ products (Week 11), 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

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

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

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.