CS193T Thinking with AI

Models + Prompting

cbl@stanford.edu — Tue, 29 Sep 2026 00:00:00 -0700

Goals: explore models and modes, practice the "scope of work" and "interview me" patterns, and reflect on finding and retaining your own voice and skills while using AI.

Gradescope — submit the indicated portions by Sunday, October 4 at 11:59 pm Pacific.
Tutorial — discuss with your TA during tutorial in Week 3.

Hello everyone! If you haven’t completed the AI software tools registration and installation process recommended in Assignment 1, you might consider working on that this week. We will begin using features of these models that are not available in the AI Playground next week.

AI Foundations

cbl@stanford.edu — Tue, 22 Sep 2026 00:00:00 -0700

Goal: get ready for the quarter!

Forms — due Friday, September 25 at 11:59 pm Pacific.
Everything else — bring it to your tutorial in Week 2.

Hi everyone! And welcome to CS 193T. We are so excited to have you join us in this exploration of AI and the process of establishing your own personal boundaries around the roles you assign to AI in your work.

Tutorial this week

We won’t have a formal tutorial this week. Instead, you’re welcome to drop in either Thursday from 3:00–4:20 or Friday from 9:00–1:00 (both in CODA B80) for help setting up the AI software tools you’ll need this quarter on your laptops. We’ll have a bunch of TAs floating around and helping you, so please stop by if you’d like help or are having any trouble!
If you are not able to make it to the drop-in session, you will be fine using just the web-based Stanford AI Playground for the first two weeks. But for the sake of your future busy Week 3 self, we do highly recommend you get the tools installation taken care of this week.

Assignment outline

First, complete two forms: a welcome survey, and a survey of tutorial time preferences.

CS193T: Thinking with AI

cbl@stanford.edu — Fri, 18 Sep 2026 00:00:00 -0700

Lecture 1: Welcome!

What’s actually happening when you chat with an AI? This opening lecture demystifies large language models from the ground up — tokens, neural networks, weights and layers, and the two-stage journey from training to inference that turns raw text into a working chatbot. Along the way we introduce the concepts (context windows, transformers, attention) that explain both what makes modern AI so capable and why it still confidently gets things wrong, including hallucination, sycophancy, and the pull to anthropomorphize a fundamentally statistical tool. No coding or technical background required — by the end, you’ll have a working mental model for what AI can and can’t do, which every later lecture builds on.

CS193T: Thinking with AI

cbl@stanford.edu — Fri, 18 Sep 2026 00:00:00 -0700

Lecture 2: Core Prompting

Lecture 1 explained what’s happening inside the model; Lecture 2 is about what you do with it. We cover how to prompt effectively — treating AI like a capable but new hire, using techniques like detailed scope-of-work prompts, the “interview me” pattern, and prompt postmortems you can reuse. We dig into trust and observability (catching confident mistakes, grounding answers in your own data, knowing when to demand evidence over assertions), the mechanics of managing long conversations (context rot, “lost in the middle,” knowing when to start fresh), and resource-mindful habits that are good for your wallet and the planet alike. We close on a thread that will recur all quarter: how to stay the one steering the AI, rather than letting your own skills and independent judgment quietly atrophy.

Guest Panel Speakers

cbl@stanford.edu — Mon, 12 Jan 2026 00:00:00 -0800

Mark Algee-Hewitt, Professor of English

His work combines critical and quantitative approaches to the analysis of literature. He is particularly interested in the literature and aesthetic philosophy of the eighteenth and nineteenth centuries, and he has used computational methods to explore the history of aesthetic concepts across this period. As director of the Stanford Literary Lab, he has led projects on the literature of suspense, the history of racialized language in American literature, and an analysis of the reports of the OECD’s anti-bribery convention.

Assignments

cbl@stanford.edu — Mon, 01 Sep 2025 00:00:00 -0700

We have a great set of assignments planned to give you practice with the material presented in lecture and tutorial.

Common questions about assignments

What programming environment and tools are used?

This list is subject to change, but we currently plan to offer at least some exposure to all of the following:

Anthropic: Claude Chat, Claude Cowork, Claude Code
Google: Gemini Enterprise, Notebook Gemini (AKA NotebookLM), Deep Research, Data Insights, Code Assist
OpenAI: ChatGPT, ChatGPT Work, ChatGPTEdu, Codex
Microsoft: Microsoft 365 Copilot, Github Copilot
Free, open-source models (Deepseek, Mistral, Llama)
Connectors from AI models to your Google Drive files, email, Slack, and more

What is the assignment schedule?

Assignments go out weekly. Your work on them will launch at your weekly tutorial, and you will present the outcomes of your work on the assignment at the following week’s tutorial.

📅 CS193T Course Schedule

cbl@stanford.edu — Mon, 01 Jan 0001 00:00:00 +0000

This is a preview of our planned schedule. We may update this schedule as we go.

About CS193T Thinking with AI

cbl@stanford.edu — Mon, 01 Jan 0001 00:00:00 +0000

This site is for CS193T

Course placement

cbl@stanford.edu — Mon, 01 Jan 0001 00:00:00 +0000

Stanford offers many AI-related courses and it can be difficult to know exactly where to begin. This handout provides a general overview of some of these classes and some advice about selecting the class that’s right for you.

If you have any questions, please feel free to come talk to the course staff! We’d be happy to offer one-on-one advice.

If you may want to major in CS

If you may want to major in CS, you should start in CS106A (no experience), CS106AX (some experience/classes), or CS106B (completed AP CS Java), and from there progress through the CS core courses: CS106A(X), CS106B, CS107, CS103, and CS109. If at any time you decide a CS major is not for you, no problem! You will have gained valuable skills that can serve you will in just about any other discipline. If you decide after CS106A that a CS major isn’t for you, you may want to jump over to CS193V, described below.

Ethical AI Tools

cbl@stanford.edu — Mon, 01 Jan 0001 00:00:00 +0000

We understand that some of you may be taking this class because you’re not a big fan of how AI is used commercially, and you’d like to learn more about various ways to use it more morally, ethically, environmentally, or with a special focus on privacy.

For that reason, we’ve compiled this list of suggestions, resources, and models to use when you’d like your AI practices to align more closely with certain values.

Getting Help

cbl@stanford.edu — Mon, 01 Jan 0001 00:00:00 +0000

We provide a variety of support resources in CS193T to help you as much as possible with assignment, material, or other questions throughout the quarter.

❓I have a conceptual question:

We love conceptual questions about any and all of the course material. Here are some options for you to get help:

Reach out to your tutorial TA by email.
Go to office hours
Post on Ed Discussion forum.

❓I have a bug or question about my AI tool:

We all get stuck when using computers and AI tools. There are times when the best thing to do is to work through the bug yourself – learning by doing is powerful. However, there are also times when an experienced user can help get you on the right track. Course staff will help you learn how to narrow down what may be going wrong in your code and how to approach fixing it.

Honor Code and AI Use Policy

cbl@stanford.edu — Mon, 01 Jan 0001 00:00:00 +0000

You Write the Honor Code and AI Use Policy

One topic we will be covering is how to interpret and honor different courses’ AI policies. We will also have a policy debate about what university courses’ AI policies should be and how that varies across disciplines, levels, and other contexts. For an experiential and community-centered treatment of this topic, we will discuss together during Week 1 what the Honor Code and AI use policies should be for this course.

Lectures

cbl@stanford.edu — Mon, 01 Jan 0001 00:00:00 +0000

We have scheduled our lecture to meet in the largest room available on campus, and expect all on campus students to attend in person and engage with the learning activities. Although there is a policy in place to allow for some flexibility (see syllabus), I want to emphasize how important it is to attend in person if at all possible. By watching videos, you get access to what I’ve said in class, but you are robbed of the experience of hearing what your seatmates have to say during the problem-solving activities, as well as of the opportunity to say things to them. This practice in real-time verbal grappling with programming concepts is essential training for anyone planning a career that involves software engineering or working with software engineers.

Office Hours

cbl@stanford.edu — Mon, 01 Jan 0001 00:00:00 +0000

TA office hours happen inside tutorial

This quarter we’ve combined TA office hours with tutorial. There’s no separate evening helper session to show up to. Instead, every tutorial block has TAs on floater duty whose whole job is helping whoever is in the room.

So if you want TA help, come to a tutorial — any tutorial, not just your own block. No sign-up and no appointment. Bring a bug, a half-built thing, a question about the assignment, or nothing in particular.

Optional Extra Readings

cbl@stanford.edu — Mon, 01 Jan 0001 00:00:00 +0000

None of the readings on this page are required, and none of them will be assessed. They’re here for the times when something in lecture or tutorial catches your interest and you want to go further than the course itself goes.

Readings are grouped by the week they connect to, so you can follow along or dip in whenever a topic grabs you.

Feel free to suggest additions on Ed — if you find something good, we’d like to share it.

Questions from prospective students

cbl@stanford.edu — Mon, 01 Jan 0001 00:00:00 +0000

How will lectures be delivered? Is attendance required? Will they be recorded?

Lectures will be delivered live Tuesdays at 1:30pm in NVIDIA Aud (Huang Building). Attendance is required for on-campus students. Read more about lectures.

How will tutorial work? Is attendance required?

Tutorials will meet weekly in person, and your attendance and participation in tutorial is required. Read more about tutorial.

Will there be exams?

No. On our final exam day, we will have a poster session style showcase of your final projects, to which guests from around campus and industry will be invited.

Syllabus

cbl@stanford.edu — Mon, 01 Jan 0001 00:00:00 +0000

Hi there 👋 and welcome to CS193T!

Teaching Team

Cynthia Bailey

Instructor

Piper Fleming

Head TA

Elise Baumgartner

CGOE Coordinator

Teaching Assistants

Agam Iheanyi-Igwe

Alice Kim

Amari Majuni Porter

Elanna Yan Kei Mak

Elline Harrison

Grace Yan

Jessica Yauney

Leon Liangyu Chen

Palash Kapoor

Tracy Y Wei

Yosief Abraham

Course Overview

Whether you’re excited, curious, skeptical, or just unsure where to start with AI, this course meets you there.

Tutorial

cbl@stanford.edu — Mon, 01 Jan 0001 00:00:00 +0000

Tutorial is where you actually build things. Once a week you’ll spend 80 minutes working on that week’s tool with your TA and the rest of your tutorial group, and you’ll leave with something you made.

Tutorials will start on week 2, and meet either Tuesday, Wednesday, Thursday, or Friday. You’ll be placed in one of those blocks and you’ll stay in it, with the same TA and the same table group, all quarter.

CS193T Thinking with AI

Models + Prompting

AI Foundations

Tutorial this week

Assignment outline

CS193T: Thinking with AI

Lecture 1: Welcome!

CS193T: Thinking with AI

Lecture 2: Core Prompting

Guest Panel Speakers

Guests from around campus share their AI use cases

Mark Algee-Hewitt, Professor of English

Assignments

Common questions about assignments

What programming environment and tools are used?

What is the assignment schedule?

📅 CS193T Course Schedule

About CS193T Thinking with AI

Course placement

If you may want to major in CS

Ethical AI Tools

Getting Help

❓I have a conceptual question:

❓I have a bug or question about my AI tool:

Honor Code and AI Use Policy

You Write the Honor Code and AI Use Policy

Lectures

Office Hours

TA office hours happen inside tutorial

Optional Extra Readings

Questions from prospective students

How will lectures be delivered? Is attendance required? Will they be recorded?

How will tutorial work? Is attendance required?

Will there be exams?

Syllabus

Hi there 👋 and welcome to CS193T!

Teaching Team

Teaching Assistants

Course Overview

Tutorial