Course Resource Guide

Curated online resources organized by unit · Free and low-cost resources prioritized

How to Use This Guide

This guide provides curated resources for each of the three course units. Resources are grouped by topic and marked with a cost indicator. Nearly everything below is free or freely auditable — where a resource has a paid tier, the free portion already covers what's relevant to this course, and that's noted explicitly.

A note on O'Reilly titles: UW–Madison students have free access to the full O'Reilly online learning platform (books, videos, and live courses from O'Reilly, Packt, Manning, and ~200 other publishers) via the library's subscription. Entries below marked Free (UW–Madison, via library) link through ezproxy.library.wisc.edu, which will prompt for your NetID and land you directly on that title. General portal: digital.library.wisc.edu/1711.web/oreilly (opens in new tab).

Students do not need to complete entire courses listed here. The annotations in the "What Students Will Learn" column indicate which parts are most directly relevant to the course. Treat these as a menu, not a mandatory checklist.

Unit 1 — AI-Assisted Software Development   Weeks 1–5

The resources below cover setting up an effective AI-assisted development workflow, frontend basics (TypeScript + p5.js for Project 1), Git/GitLab, GitLab CI/CD pipelines, Docker, backend REST APIs with FastAPI, relational databases, and authentication — everything needed for Lectures 1–9 and Projects 1–2.

Claude Code & AI-Assisted Development

ResourceCostWhat Students Will Learn
Course Shared Skills Repository (GitLab) (opens in new tab)Free (course members)This class’s own library of Claude Code skills and rules, which every student can use and contribute to. Its README explains how to install a skill or rule, how to contribute one through a merge request, and how to use the repository responsibly. Sign in to GitLab with your NetID to view it.
Claude Code 101 (Anthropic Academy) (opens in new tab)FreeOfficial Anthropic beginner course — installation, daily workflow, and customization.
Claude Code in Action (Anthropic Academy) (opens in new tab)FreeIntermediate course on context management, MCP servers, and GitLab repository integration.
Claude Code: A Highly Agentic Coding Assistant (DeepLearning.AI) (opens in new tab)Free (beta)Built with Anthropic — three hands-on projects: RAG chatbot codebase, Jupyter notebook, and Figma-to-web-app.
Claude Code: Software Engineering with Generative AI Agents (Coursera / Vanderbilt) (opens in new tab)Free to auditTaught by Dr. Jules White. Covers delegating to Claude Code like a tech lead, CLAUDE.md files, and large-scale orchestration.
The Claude Code Handbook (freeCodeCamp) (opens in new tab)FreeComprehensive written guide: architecture, context management, practical prompting patterns.
Awesome Claude Code (GitHub) (opens in new tab)FreeCommunity-curated list of skills, hooks, slash commands, and extensions for Claude Code.
Introduction to Agent Skills (Anthropic Academy) (opens in new tab)FreeBuilding, configuring, and sharing reusable markdown instructions (Skills) for Claude Code — a deeper option for students who want to customize their workflow beyond the basics.
Introduction to Subagents (Anthropic Academy) (opens in new tab)FreeUsing and creating sub-agents in Claude Code for task delegation — relevant once projects get large enough that one long agent session stops being the best tool.
AI Fluency: Framework & Foundations (Anthropic Academy) (opens in new tab)FreeAnthropic's own framework for collaborating with AI systems effectively, efficiently, ethically, and safely — a good conceptual complement to the hands-on Claude Code courses above.

Git, GitLab & Version Control

ResourceCostWhat Students Will Learn
Pro Git Book (Official) (opens in new tab)FreeThe definitive, free reference for Git. Chapters 1–3 cover everything students need for the course. Tool-agnostic — applies to GitLab.
Visualizing Git (opens in new tab)FreeInteractive, in-browser tool that draws the commit graph live as you type Git commands — a fast, hands-on way to build real intuition for branching, merging, and rebasing (including the difference between them).
Learn Git Branching (opens in new tab)FreeGamified, level-based interactive tutorial for practicing branching, merging, and rebasing through visual challenges — a popular, more structured complement to Visualizing Git above.
GitLab Docs — Learn GitLab with Tutorials (opens in new tab)FreeOfficial GitLab tutorial library covering CI/CD fundamentals, merge requests, branching strategies, and GitOps deployments.
GitLab CI Fundamentals (GitLab University) (opens in new tab)FreeOfficial GitLab learning path covering .gitlab-ci.yml syntax, stages, jobs, runners, and variables — the core pipeline concepts. Also required pre-class reading for Lecture 14, which is the first lecture where students write a new pipeline stage rather than just consuming one.

Frontend Development

ResourceCostWhat Students Will Learn
MDN Web Docs — HTML, CSS, JavaScript (opens in new tab)FreeThe authoritative reference for web standards. Excellent structured learning path from beginner to advanced.
The Odin Project (opens in new tab)FreeFull open-source frontend curriculum with projects. Covers HTML, CSS, JavaScript, and the DOM in depth.
javascript.info (opens in new tab)FreeComprehensive, well-written JavaScript textbook — covers modern JS including async/await, fetch, and the DOM.
TypeScript Handbook — TypeScript from Scratch (opens in new tab)FreeRequired pre-class reading for Lecture 2. Covers TypeScript basics — types, interfaces, and comparison to Java concepts.
TypeScript Handbook — TypeScript in 5 Minutes: OOP (opens in new tab)FreeRequired pre-class reading for Lecture 2. Covers TypeScript's OOP features — classes, interfaces, and access modifiers.
p5.js — Get Started (opens in new tab)FreeRequired pre-class reading for Lecture 2. Covers the setup()/draw() loop, the canvas coordinate system, and basic drawing/color functions used throughout Project 1's side-scroller game.
p5.js Reference (Official) (opens in new tab)FreeOfficial API reference for every p5.js function — useful for looking up shape, color, image, and input-handling methods while implementing Project 1 features.
The Coding Train — Code! Programming with p5.js (opens in new tab)FreePopular video series teaching programming fundamentals (variables, conditionals, functions, objects) through creative coding with p5.js. Good supplementary practice for students newer to the setup()/draw() paradigm.

Unit Testing (Vitest)

ResourceCostWhat Students Will Learn
Vitest Getting Started Guide (opens in new tab)FreeRequired pre-class reading for Lecture 2. Covers what a unit test is, the arrange/act/assert pattern, and Vitest basics.
Unit Testing with Vitest (Northeastern CS4530) (opens in new tab)FreeA more thorough, ground-up introduction to unit testing itself — what a unit test is, black/white/gray box testing, and the arrange/act/assert pattern in depth — taught through Vitest. Good next step for students who want more than the required quick-start guide before diving into Project 1's tests.

System Design

ResourceCostWhat Students Will Learn
Designing Data-Intensive Applications, 2nd Ed. — Martin Kleppmann (O'Reilly) (opens in new tab)Free (UW–Madison, via library)Optional deep-dive reference — not assigned reading. Chapters 1 and 2 cover reliability, scalability, and data models for students who want the classic treatment.
System Design Primer (GitHub) (opens in new tab)FreeMassive open-source guide covering scalability, load balancing, caching, and database sharding with diagrams. 280k+ stars.
ByteByteGo System Design Newsletter / YouTube (opens in new tab)Free (newsletter) / Paid (book)Visual, accessible system design content from Alex Xu (System Design Interview author). Great for conceptual explanations.

GitLab CI/CD Pipelines

ResourceCostWhat Students Will Learn
GitLab CI/CD Documentation (Official) (opens in new tab)FreeThe authoritative reference for .gitlab-ci.yml syntax, runners, environments, artifacts, caching, and protected variables. Start here.
GitLab Advanced CI/CD Training (GitLab University) (opens in new tab)FreeOfficial GitLab advanced training: reusable pipeline components, parent-child pipelines, dynamic environments, and SAST integration.
How to Create a CI/CD Pipeline with Docker and GitLab (Spacelift Blog) (opens in new tab)FreePractical hands-on tutorial: building Docker images in GitLab pipelines, pushing to GitLab Container Registry, Docker-in-Docker setup, and predefined CI variables.

Docker & Containers

ResourceCostWhat Students Will Learn
Docker Official Documentation & Get Started Guides (opens in new tab)FreeOfficial tutorials from Docker, including 'Learn Docker in a Month of Lunches' references and the CLI cheat sheet.
Docker Full Course (freeCodeCamp) (opens in new tab)FreeFull-length hands-on course covering images, containers, volumes, networking, and Docker Compose for multi-container apps.
Play with Docker (interactive browser labs) (opens in new tab)FreeRun Docker commands in the browser with no installation required. Great for in-class demos and experimentation.

Backend Development & REST APIs

ResourceCostWhat Students Will Learn
FastAPI Official Tutorial (opens in new tab)FreeThe official FastAPI documentation's tutorial — path/query parameters, request bodies with Pydantic, dependency injection, and async endpoints. Matches this course's actual backend stack directly (Projects 2–3 are both FastAPI, not Flask).
REST API Best Practices (Postman Blog) (opens in new tab)FreePractical, authoritative REST design guide from the team behind the industry-standard API tool.

SQL & Databases

ResourceCostWhat Students Will Learn
SQLBolt — Interactive SQL Tutorial (opens in new tab)FreeBest free interactive SQL learning site — 19 lessons covering SELECT through JOINs, aggregations, and subqueries.
Use The Index, Luke — SQL Performance Explained (opens in new tab)FreeDeveloper-focused guide to SQL indexing and query performance. More practical than academic SQL texts.

Authentication & Security Basics

ResourceCostWhat Students Will Learn
jwt.io — JWT Introduction & Debugger (opens in new tab)FreeOfficial JWT explainer plus the interactive debugger students will use to inspect and verify tokens in labs.
OWASP Authentication Cheat Sheet (opens in new tab)FreeRequired pre-class reading for Lecture 8: the Introduction, Store Passwords in a Secure Fashion, Compare Password Hashes Using Safe Functions, and Authentication and Error Messages. The rest is a reference for authentication best practices — password recovery, multi-factor auth, and more.
OWASP Authorization Cheat Sheet (opens in new tab)FreeRequired pre-class reading for Lecture 8: the Introduction (authentication vs. authorization) and the RBAC, ABAC, and ReBAC models, including OWASP's case for preferring ABAC/ReBAC in larger applications.
Auth0 Developer Docs — OAuth 2.0 Explainer (opens in new tab)FreeClear, practical explanation of the OAuth 2.0 flow with sequence diagrams. Better than the RFC for learning purposes.
Unit 2 — Smart Applications   Weeks 6–10

Resources for understanding how LLMs work, prompt engineering, local models with Ollama, RAG pipelines and vector databases, CI/CD deployment to GCP, cloud LLM APIs, agentic tool use, and production monitoring — everything needed for Lectures 10–19 and Projects 3–4.

LLM Theory & Foundations

ResourceCostWhat Students Will Learn
Generative AI with LLMs (DeepLearning.AI + AWS, Coursera) (opens in new tab)Free to auditCovers the full LLM lifecycle: transformer architecture, tokenization, pre-training, fine-tuning, RLHF, and deployment. Three weeks.
Generative AI for Everyone (Andrew Ng, Coursera) (opens in new tab)Free to auditAccessible conceptual intro to generative AI — context windows, hallucinations, embeddings, and RAG at a conceptual level.
AI Capabilities and Limitations (Anthropic Academy) (opens in new tab)FreeAnthropic's own short introductory course on how AI works — a good pairing with Lecture 10's conceptual treatment of LLMs.
AI Engineering — Chip Huyen (O'Reilly) (opens in new tab)Free (UW–Madison, via library)Highly recommended reference for the course. Covers real-world LLM engineering challenges, evaluation, MLOps, and inference.
Hands-On Large Language Models — Jay Alammar & Maarten Grootendorst (O'Reilly) (opens in new tab)Free (UW–Madison, via library)Visual, intuitive treatment of transformer architecture, embeddings, semantic search, and RAG — from the author of the widely-used "Illustrated Transformer" explainer.
Intro to Large Language Models — Andrej Karpathy (YouTube, 2023) (opens in new tab)FreeRequired for Lecture 10: the first 30 minutes — how a model is pretrained on internet text into a base model, then fine-tuned into an assistant, with comparison labels (RLHF) as an optional third stage. Part 3, LLM Security (45:43–58:37), covers jailbreaks, prompt injection, and data poisoning — a preview of Unit 3.
Deep Dive into LLMs like ChatGPT — Andrej Karpathy (YouTube, 2025) (opens in new tab)FreeA 3.5-hour, general-audience walkthrough of how ChatGPT-style models are built, with chapter timestamps: pretraining and tokenization; post-training on conversations, including the special tokens that mark each turn (1:01:06); hallucinations and tool use (1:20:32); reinforcement learning and DeepSeek-R1 thinking models (2:07:28); and RLHF (2:48:26). Required for Lecture 15: the "DeepSeek-R1" chapter (2:27:47–2:42:07). Recorded February 2025, so some provider details are dated.
Hugging Face — Chat Templates (opens in new tab)FreeRequired for Lecture 12 (optional for Lecture 10), from the top of the page through the add_generation_prompt section: how a list of chat messages becomes one token sequence with model-specific control tokens such as <|im_start|>, and why the wrong template hurts a model. Shows the same format as Lecture 10's special-token slides.

Post-Training, RLHF & Reasoning Models

Optional deeper reading behind Lecture 10's training-stage and reasoning-model slides and Lecture 15's thinking-token slides.

ResourceCostWhat Students Will Learn
RLHF: Reinforcement Learning from Human Feedback — Chip Huyen (2023) (opens in new tab)FreeOptional. Walks through the three phases behind ChatGPT-style models — pretraining, supervised fine-tuning, and RLHF with a reward model. Each phase includes the math, but the overview and the "why" sections read fine without it.
Illustrating Reinforcement Learning from Human Feedback (Hugging Face blog, 2022) (opens in new tab)FreeOptional. A diagram-led explanation of RLHF: train a reward model from human rankings, then fine-tune the language model against it, with a penalty that keeps it close to the original model.
Understanding Reasoning LLMs — Sebastian Raschka (2025) (opens in new tab)FreeOptional. What makes a model a "reasoning model," inference-time scaling, and how DeepSeek-R1 was trained with reinforcement learning and supervised fine-tuning. Goes deeper than Lecture 10's reasoning-model slides.
Reinforcement Learning from Human Feedback and LLM Post-Training — Nathan Lambert (opens in new tab)Free (online book)Optional reference. A free, regularly updated book on post-training: instruction tuning, reward models, preference optimization (including DPO), reinforcement learning for reasoning, and over-optimization. Background for Unit 3's alignment material.
Qwen2.5 Technical Report (arXiv:2412.15115) (opens in new tab)FreeOptional. Source of Lecture 10's training figures for the model family used in the Medical Knowledge Base arc: 18 trillion pretraining tokens, over 1 million supervised fine-tuning samples, and multistage reinforcement learning.

Prompt Engineering

ResourceCostWhat Students Will Learn
ChatGPT Prompt Engineering for Developers (DeepLearning.AI) (opens in new tab)Free (beta)Taught by Isa Fulford (OpenAI) and Andrew Ng. Covers zero-shot, few-shot, chain-of-thought, and structured output techniques.
PromptSet: A Programmer's Prompting Dataset — Pister, Paul, Brophy & Joshi (arXiv:2402.16932) (opens in new tab)FreeRequired for Lecture 12 (whole paper). A dataset of 61,000+ prompts that developers wrote in open-source Python projects, an analysis of what those prompts look like, and a proposed static linter for prompts — treating prompts as code that deserves the same checks as the rest of the codebase.
Anthropic Prompt Engineering Documentation (opens in new tab)FreeOfficial Anthropic guide on system prompts, structured outputs, reasoning, and best practices for Claude specifically.
Learn Prompting (Open Source Guide) (opens in new tab)FreeComprehensive open-source prompting guide covering 50+ techniques with examples. Maintained by the community.
Building Systems with the ChatGPT API (DeepLearning.AI) (opens in new tab)Free (beta)Follows up on prompt engineering — covers chain calls, input/output evaluation, and safety checks.

Local LLMs (Ollama) & Model Selection

ResourceCostWhat Students Will Learn
Ollama Official Documentation (opens in new tab)FreePrimary reference for installing and running local models. Covers model library, REST API, and programmatic usage.
Cohere LLM University (opens in new tab)FreeWell-structured curriculum covering embeddings, semantic search, and model selection trade-offs. Language-agnostic and practical.

Vector Databases & RAG

ResourceCostWhat Students Will Learn
Retrieval Augmented Generation (RAG) — DeepLearning.AI / Coursera (opens in new tab)Free to auditCovers retriever design, vector DBs, semantic search, BM25, Reciprocal Rank Fusion, and production RAG evaluation.
Fundamentals of Building AI Agents using RAG and LangChain (IBM / Coursera) (opens in new tab)Free to auditCovers FAISS, dense passage retrieval, tokenizers, and LangChain retrieval chains with hands-on cloud labs. (The course itself uses ChromaDB directly rather than LangChain — useful as a comparison of an alternative framework, not a match for the project stack.)
Hands-On RAG for Production (O'Reilly) (opens in new tab)Free (UW–Madison, via library)Covers agentic RAG fundamentals, tool calling, MCP, multi-agent systems, and evaluation/observability — directly relevant to Project 3's comparison-mechanism work.
12 Best RAG Courses in 2026 (Class Central Curated Guide) (opens in new tab)Free guideIndependent review comparing the best RAG learning resources — useful for students who want to go deeper beyond the course.
ACM Digital Library (opens in new tab) / IEEE Xplore (opens in new tab)Free (UW–Madison, via library)Optional — not required. For students who want to read the primary research behind RAG beyond the Lewis et al. paper already assigned (Lecture 11); both are searchable full-text past the free abstract most search engines show.
Infinity (GitHub — michaelfeil/infinity) (opens in new tab)FreeDocs and quickstart for the dedicated embeddings/rerank server this course uses instead of a general-purpose LLM server's embeddings endpoint — covers its OpenAI-compatible /embeddings API and how embedding model choice determines pooling strategy (mean/CLS/last-token). Required pre-class reading for Lecture 13.
RAGAS Documentation (RAG Evaluation Framework) (opens in new tab)FreeOfficial docs for the RAGAS open-source evaluation framework — covers faithfulness, answer relevance, and context recall metrics. Required pre-class reading for Lecture 14.

GitLab CI/CD Deployment & Secrets

ResourceCostWhat Students Will Learn
GitLab CI/CD Variables Documentation (Official) (opens in new tab)FreeRequired pre-class reading for Lecture 14. Covers custom, masked, and protected CI/CD variables — how to store secrets like SSH keys without committing them to the repository.

Cloud Deployment (GCP)

ResourceCostWhat Students Will Learn
Create and start a Compute Engine instance (Official Google Cloud Docs) (opens in new tab)FreeOfficial reference for creating a VM via the Console, gcloud, or the API — machine types, zones, boot disks, and startup options. Required-adjacent reading for Lecture 14's Compute Engine deployment activity; Lecture 19 redeploys using the exact same pattern, and the Final Project reuses it again later.
Google Cloud Free Program (Official) (opens in new tab)FreeWhat's covered by GCP's Always Free tier (including one non-preemptible e2-micro instance per billing account in us-central1, us-west1, or us-east1) versus what still bills — relevant for not accidentally burning through the course's education credit on an oversized VM.

Cloud LLM APIs & Tool Use

Lectures 15–19 (the Automated Customer Support Agent arc) and Project 4 (Course Copilot) all standardize on Google's Gemini models via the google-genai SDK, called against Vertex AI in "Express Mode" (a plain API key, funded by the same GCP for Education credit used for Project 3's deployment) — not the Anthropic API.

ResourceCostWhat Students Will Learn
Google Gen AI SDK (google-genai) Quickstart (opens in new tab)FreeOfficial reference for client initialization and content generation with the SDK this course uses starting Lecture 15. Required pre-class reading for Lecture 15.
Gemini API — Text Generation & Streaming Guide (opens in new tab)FreeCovers both blocking and streaming (generate_content_stream) calls, and the async client (client.aio) used for non-blocking calls in a web server. Required pre-class reading for Lecture 15.
Gemini API — Structured Output Guide (opens in new tab)FreeHow response_schema with a Pydantic model constrains Gemini's output to valid, type-safe JSON — no regex or markdown-fence stripping needed. Required pre-class reading for Lecture 16.
Gemini API — Function Calling Guide (opens in new tab)FreeHow to expose application functions to Gemini via FunctionDeclaration schemas and run the multi-turn tool-calling loop. Required pre-class reading for Lecture 17. Essential for Project 4.
A Guide to Structured Generation Using Constrained Decoding — Aidan Cooper (2024) (opens in new tab)FreeRequired for Lecture 16: the "What Is Structured Generation?" and "What Is Constrained Decoding and How Does It Work?" sections. Contrasts prompting and fine-tuning, which steer a model toward a format, with constrained decoding, which restricts each next token so the output always matches the structure.
Hugging Face — Tool Use (opens in new tab)FreeRequired for Lecture 17: the "Passing tools" and "Tool-calling Example" sections. Shows how tool schemas go into a chat template, the <tool_call> text a model generates, and how your code adds the result back as a tool message. Matches Lecture 17's "A Tool Call, as the Model Sees It" slide.
llama.cpp — GBNF Grammars README (opens in new tab)Free (open source)Optional. How llama.cpp constrains a local model's output with a grammar, including converting a JSON Schema into one — a concrete implementation of the constrained decoding taught in Lecture 16.
Gemini Developer API Pricing (opens in new tab)FreePer-model token prices. Output prices for thinking models such as gemini-2.5-flash include thinking tokens — why Lecture 15 and Project 4's cost tracking count thoughts_token_count as output.
Vertex AI Express Mode Overview (opens in new tab)FreeHow Express Mode authenticates with a plain API key instead of a full service-account credential file — the auth path this course uses on student laptops and in Project 4.
Anthropic API Documentation (opens in new tab)FreeReference for Claude's own models, tool use, streaming, and vision — useful for comparison (and still what Claude Code itself runs on), though Lectures 15–19 and Project 4 standardize on Google's Gemini API.
OpenAI API Documentation (opens in new tab)FreeCovers function calling, assistants, structured outputs, and batch processing — another useful point of comparison to the Gemini API this course actually uses.

AI Agents & Agentic Pipelines

ResourceCostWhat Students Will Learn
Introduction to Model Context Protocol (Anthropic Academy) (opens in new tab)FreeBuild MCP servers and clients in Python from scratch — tools, resources, and prompts, MCP's three core primitives. A natural extension of Lecture 17's tool-use content for students who want to go deeper.
Building AI Agents with LLMs, RAG, and Knowledge Graphs (O'Reilly) (opens in new tab)Free (UW–Madison, via library)Covers agent architectures combining RAG and knowledge graphs — relevant background for both Project 3's retrieval work and Project 4's multi-agent Course Copilot.
IBM RAG and Agentic AI Professional Certificate (Coursera) (opens in new tab)Free to auditRecently updated — covers LangGraph, CrewAI, AG2, MCP integration, and multimodal agentic systems.
LangChain Official Documentation & Tutorials (opens in new tab)FreeOfficial tutorials covering chains, agents, memory, and RAG. Includes the LCEL (LangChain Expression Language) overview. Not used directly in this course's projects, but a useful point of comparison to the raw Anthropic SDK approach taught here.
Anthropic's Guide to Building Effective Agents (opens in new tab)FreeAnthropic's own research-backed guidance on agent patterns, when to use agents vs. simpler pipelines, and safety considerations.

Frontend Design for Intelligent Apps

ResourceCostWhat Students Will Learn
The Weird Future Of User Interfaces (YouTube) (opens in new tab)FreeOptional for Lecture 18: the pros and cons of chat interfaces, and why simple actions suit controls while complex ones suit language — the source of the lecture's action-complexity spectrum.

Monitoring, Observability & Logging

ResourceCostWhat Students Will Learn
Sentry Documentation — Getting Started (opens in new tab)Free tier availableOfficial Sentry docs for setting up error tracking in Node.js or Python. Optional — not used in any project; useful industry context for Lecture 19's observability content.
OpenTelemetry Documentation (opens in new tab)FreeVendor-neutral observability standard. Covers distributed tracing, metrics, and structured logging in any language.
The Art of Monitoring (Free Online Book) (opens in new tab)Free partial / Paid fullConceptual foundation for why monitoring matters, what to instrument, and how to alert thoughtfully in production systems.

Performance Optimization & Cost Control

ResourceCostWhat Students Will Learn
Gemini API Pricing (Official) (opens in new tab)FreeUp-to-date per-model token pricing for the Gemini family, including gemini-2.5-flash-lite — the default model Project 4 uses for classification, generation, and verification calls. Essential for Project 4's per-AgentRun cost logging.
LLMOps Specialization (Duke University, Coursera) (opens in new tab)Free to auditCovers CI/CD for LLMs, monitoring, scaling, and optimization including quantization, caching, and batch inference strategies.
LLM Engineer's Handbook — Iusztin & Labonne (O'Reilly / Packt) (opens in new tab)Free (UW–Madison, via library)Covers the full LLM engineering stack: RAG, evals, LLMOps, fine-tuning, deployment, and production optimization.
Unit 3 — Security, Ethics & Harness Engineering   Weeks 11–15

Resources for AI-specific security vulnerabilities, responsible AI and ethics, harness engineering and evaluation frameworks — everything needed for Lectures 20–27 and the Final Project.

AI Security & Red Teaming

Lectures 20, 22, 23, and 27 form the Security Lab Arc, run on Vault — a hosted service built for this course. The tools below are the real, industry-standard tooling that arc's activities are graded with or modeled on.

ResourceCostWhat Students Will Learn
Red Teaming LLM Applications (DeepLearning.AI) (opens in new tab)Free (beta)Beginner-friendly hands-on course — attacks chatbots via prompt injection using the Giskard library. Ideal primer before the security lectures.
OWASP Top 10 for Large Language Model Applications (opens in new tab)FreeThe industry standard reference for LLM vulnerability taxonomy. Required pre-class reading for Lecture 20 (LLM01: Prompt Injection) and Lecture 22 (the architecture/governance whitepaper).
OWASP Threat Modeling Cheat Sheet (opens in new tab)FreeOptional for Lecture 22: the four questions of threat modeling (what are we building, what can go wrong, what will we do about it, did we do a good job), with a STRIDE table and examples. Useful for the Vault threat-model take-home.
Microsoft Learn — Threats (STRIDE model) (opens in new tab)FreeOptional for Lecture 22: one short page defining all six STRIDE categories — spoofing, tampering, repudiation, information disclosure, denial of service, elevation of privilege.
EchoLeak (CVE-2025-32711) — Original Disclosure (Aim Security) (opens in new tab)FreeThe real, zero-click indirect prompt injection that exfiltrated data from Microsoft 365 Copilot via a single crafted email — no user interaction required. Required pre-class reading for Lecture 22; Vault's own threat-modeling activity uses it as an anchor case.
promptfoo — Red Team Quickstart (opens in new tab)Free (open source)Official quickstart for the industry-standard red-teaming tool that grades Lecture 23's guardrail-gateway activity — a static eval pass plus a redteam pass using promptfoo's own OWASP LLM Top 10 plugins.
NVIDIA NeMo Guardrails — Documentation (opens in new tab)Free (open source)Suggested reading — not required. NVIDIA’s open-source toolkit for runtime guardrails: colang flow definitions that spell out the allowed dialog paths, plus input, output, and topical rails. Lecture 23 teaches its architecture in class, next to Llama Guard, as one of two real guardrail designs.
garak — LLM Vulnerability Scanner (NVIDIA) (opens in new tab)Free (open source)Official docs for the open-source scanner used as attacker tooling in Lecture 27's live red/blue finale — probes for prompt injection, jailbreaks, hallucination, and data leakage.
PyRIT — Python Risk Identification Toolkit (Microsoft) (opens in new tab)Free (open source)Official docs for Microsoft's red-teaming framework, also used as attacker tooling in Lecture 27 — multi-turn adversarial strategies (e.g. Crescendo) against a live conversational target.
Secure AI: Red-Teaming & Safety Filters (Coursera) (opens in new tab)Free to auditUses PyRIT, NVIDIA garak, and promptfoo to systematically identify and mitigate LLM threats before deployment — the same three tools Lectures 23 and 27 use directly.
HackAPrompt Playground (Learn Prompting) (opens in new tab)FreeInteractive prompt injection challenges used in the world's largest AI red teaming competition. Optional pre-class reading for Lecture 20, before Vault's own PvP rounds.
The Attacker Moves Second — Nasr, Carlini, Tramèr et al. (arXiv:2510.09023) (opens in new tab)FreeRequired pre-class reading for Lecture 23: Section 1 (Introduction), Section 6 (Lesson and Discussion, with its four numbered lessons), and Section 7 (Conclusion). The authors bypassed 12 published defenses against jailbreaks and prompt injection — prompting defenses, classifier (“filtering”) models, and models trained against known attacks — with over 90% success for most, though most had reported near-zero. The point: a defense tested only against a fixed set of known attacks says little about an attacker who adapts to it. Lecture 23’s guardrail is exactly this kind of defense, scored against exactly this kind of fixed test set. Sections 2–5 and the appendices are optimization detail and are not assigned.
Defeating Prompt Injections by Design (CaMeL) — Debenedetti, Carlini, Tramèr et al. (arXiv:2503.18813) (opens in new tab)FreeSuggested reading — not required. Instead of making the model resist injected instructions, CaMeL builds a system layer around it: a privileged LLM plans from the trusted user request, a quarantined LLM with no tool access reads the untrusted data, and capability tags enforce security policies before any tool call, so untrusted data can never change what the program does. The “secure by design” end of Lecture 22’s defensive-architecture patterns, and relevant to Project 4’s tool-calling agent. Read the Introduction and “Defeating Prompt Injections by Design” sections, and the Discussion’s “So, Are Prompt Injections Solved Now?”
Jailbroken: How Does LLM Safety Training Fail? — Wei, Haghtalab & Steinhardt (arXiv:2307.02483) (opens in new tab)FreeSuggested reading — not required. Names two reasons safety training fails: competing objectives, when a model's helpfulness conflicts with its safety goals, and mismatched generalization, when safety training doesn't cover inputs (like encoded text) the model can still understand. Explains why the attacks in Lecture 20's Vault rounds work.
ACM Digital Library (opens in new tab) / IEEE Xplore (opens in new tab)Free (UW–Madison, via library)Optional — not required. For students who want to go beyond the Greshake et al. and Llama Guard papers already assigned (Lectures 22 and 23) into the broader adversarial-ML and LLM-security literature.

Responsible AI & Ethics

ResourceCostWhat Students Will Learn
Generative AI for Beginners — Microsoft (GitHub, 21 lessons) (opens in new tab)FreeLesson 3 covers responsible AI principles; lessons throughout address bias, hallucinations, and ethical deployment. Widely used.
AI Fairness 360 (IBM / LF AI, Open Source) (opens in new tab)FreeOpen-source toolkit for measuring and mitigating bias in ML models. Includes interactive demo and educational resources.
Anthropic's Responsible Scaling Policy (opens in new tab)FreePrimary source reading — how a leading AI lab thinks about responsible deployment. Good discussion material for Lecture 24 (AI Ethics) and Lecture 27 (AI Governance).

LLM Evaluation Frameworks

ResourceCostWhat Students Will Learn
LLM Evaluation Course (Evidently AI, YouTube playlist) (opens in new tab)Free10 end-to-end code tutorials covering test datasets, custom LLM judges, RAG evals, and adversarial testing. 1 hour total.
Promptfoo — Open Source LLM Evaluation Tool (opens in new tab)Free (open source)Used by teams at OpenAI and Anthropic. Evaluates prompts, agents, and RAG apps via YAML config — integrates with CI/CD. This is the actual tool Lecture 23's guardrail-gateway activity is graded with (see the AI Security & Red Teaming table above for the red-team quickstart specifically).
Evals (OpenAI GitHub Repository) (opens in new tab)FreeOpenAI's open-source evaluation framework. Good reference for understanding how production evals pipelines are structured.

All external links verified August 2026. O'Reilly links require UW–Madison NetID login through the library's ezproxy; if a deep link ever breaks, search the title at digital.library.wisc.edu/1711.web/oreilly (opens in new tab) instead.