Content
<p align="center">
<img src="assets/banner.svg" alt="AI Engineering from Scratch" width="100%">
</p>
<p align="center">
<b>AI Engineering from Scratch</b><br/>
<sub>503 lessons · 20 phases · Python / TypeScript / Rust / Julia · Companion website <a href="https://aieng-zh.cn">aieng-zh.cn</a></sub>
</p>
<p align="center">
<a href="https://aieng-zh.cn"><img src="https://img.shields.io/badge/Read-online-aieng--zh.cn-3553ff?style=flat-square&labelColor=fafaf5" alt="Read online aieng-zh.cn"></a>
<a href="ROADMAP.md"><img src="https://img.shields.io/badge/lessons-503-3553ff?style=flat-square&labelColor=fafaf5" alt="503 lessons"></a>
<a href="#contents"><img src="https://img.shields.io/badge/phases-20-3553ff?style=flat-square&labelColor=fafaf5" alt="20 phases"></a>
<a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-1a1a1a?style=flat-square&labelColor=fafaf5" alt="MIT License"></a>
<a href="https://github.com/fancyboi999/ai-engineering-from-scratch-zh/stargazers"><img src="https://img.shields.io/github/stars/fancyboi999/ai-engineering-from-scratch-zh?style=flat-square&labelColor=fafaf5&color=3553ff&cacheSeconds=21600" alt="GitHub stars"></a>
</p>
```
░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒
```
> **84% of students are already using AI tools, but only 18% feel confident using them in professional scenarios.**
> This course aims to fill that gap.
>
> 503 lessons, 20 phases, approximately 320 hours. Python, TypeScript, Rust, Julia. Each lesson delivers a reusable product: a prompt, a skill, an agent, or an MCP server. Free, open-source, MIT license.
>
> You don't just learn AI; you build it from scratch. From start to finish, entirely hands-on.
> This project is a derivative of [AI Engineering from Scratch](https://github.com/rohitg00/ai-engineering-from-scratch) (author [Rohit Ghumare](https://github.com/rohitg00), MIT license). Sincere thanks to the original author for creating and open-sourcing this course.
### What's Different in This Chinese Version
Not just machine-translated. On top of faithful translation, we've done localization for Chinese readers:
| | |
|---|---|
| 🇨🇳 **Full-site Simplified Chinese** | 503 lesson texts, 83 term tables, quiz questions, `mermaid` flowcharts, interactive chart labels all in Chinese (technical terms like `agent`, `token`, `transformer` remain in English) |
| 🌐 **Independent Chinese Website [aieng-zh.cn](https://aieng-zh.cn)** | Searchable course directory, learning progress tracking, draggable interactive charts, command panel (`Cmd / Ctrl + K`), dark mode |
| 🎬 **Companion Animation Explainer Videos** | 3Blue1Brown-style animated explanations, put mathematical derivations and core intuitions into visual short films, with Chinese dubbing, embedded in course pages. Phase 1 (math foundations, 22 lessons) is online, with others in production. |
| 🔍 **Optimized for AI Retrieval** | Automatically generates `sitemap.xml` / `llms.txt` / structured data during build, making it easy for search engines and AI assistants to reference. |
| ✅ **Lesson Consistency Guardrails** | CI automatically checks lesson counts (`node site/build.js --check`), preventing drift between course lists and actual content on disk. |
> See [TRANSLATION.md](TRANSLATION.md) for translation guidelines. Course structure and code remain consistent with the upstream project, with translations continuously updated.
**Table of Contents** · [How It Works](#how-it-works) · [Course Structure](#course-structure) · [A Lesson Overview](#a-lesson-overview) · [Quick Start](#quick-start) · [Each Lesson Has a Deliverable](#each-lesson-has-a-deliverable) · [Course Directory](#contents) · [Toolbox](#toolbox) · [Contributing](#contributing)
## How It Works
Most AI curricula are fragmented. One paper here, a fine-tuning tip there, and a cool agent demo elsewhere. These fragments rarely fit together. You build a chatbot but can't explain its loss curve; you attach a function to an agent but can't describe what the model inside does, or how attention works.
This course provides that backbone. 20 phases, 503 lessons, four languages: Python, TypeScript, Rust, Julia. One end is linear algebra, the other is autonomous agent clusters. Each algorithm starts from raw mathematical derivations. Backpropagation, tokenizers, attention, agent loops—when PyTorch arrives, you know what it's doing under the hood.
Each lesson follows the same cycle: understand the problem, derive the math, write code, run tests, and produce a deliverable. No five-minute crash courses, no copy-paste deployments, no spoon-feeding. Free, open-source, runs on your laptop.
```
░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒
```
## Course Structure
Twenty phases build upon each other. Math is the foundation, agent and production deployment is the roof. If you've already mastered something, feel free to skip ahead; but don't skip and then wonder why the upper layers collapse.
```mermaid
%%{init: {'theme':'base','themeVariables':{'primaryColor':'#fafaf5','primaryTextColor':'#1a1a1a','primaryBorderColor':'#3553ff','lineColor':'#3553ff'}}}%%
flowchart TB
P0["Phase 0 · Setup and Toolchain"] --> P1["Phase 1 · Math Foundations"]
P1 --> P2["Phase 2 · Machine Learning Foundations"]
P2 --> P3["Phase 3 · Deep Learning Core"]
P3 --> P4["Phase 4 · Computer Vision"]
P3 --> P5["Phase 5 · NLP"]
P3 --> P6["Phase 6 · Speech and Audio"]
P3 --> P9["Phase 9 · Reinforcement Learning"]
P5 --> P7["Phase 7 · Transformer"]
P7 --> P8["Phase 8 · Generative AI"]
P7 --> P10["Phase 10 · Implementing LLM from Scratch"]
P10 --> P11["Phase 11 · LLM Engineering"]
P10 --> P12["Phase 12 · Multimodal AI"]
P11 --> P13["Phase 13 · Tools and Protocols"]
P13 --> P14["Phase 14 · Agent Engineering"]
P14 --> P15["Phase 15 · Autonomous Systems"]
P15 --> P16["Phase 16 · Multi-Agent and Clusters"]
P14 --> P17["Phase 17 · Infrastructure and Production"]
P15 --> P18["Phase 18 · Ethics, Safety, and Alignment"]
P16 --> P19["Phase 19 · Comprehensive Project"]
P17 --> P19
P18 --> P19
```
```
░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒
```
## A Lesson Overview
Each lesson resides in its own folder, with a consistent structure:
```
phases/<NN>-<phase-name>/<NN>-<lesson-name>/
├── code/ runnable implementations (Python, TypeScript, Rust, Julia)
├── docs/
│ └── zh.md lesson text
└── outputs/ deliverables: prompts, skills, agents, or MCP servers
```
Each lesson follows six beats. The *Build It / Use It* split is the spine of the lesson—you implement the algorithm from scratch, then use a production-grade library to do the same thing. You understand the framework because you wrote a smaller version yourself.
```mermaid
%%{init: {'theme':'base','themeVariables':{'primaryColor':'#fafaf5','primaryTextColor':'#1a1a1a','primaryBorderColor':'#3553ff','lineColor':'#3553ff'}}}%%
flowchart LR
M["Main Idea<br/>One-sentence core concept"] --> Pr["Problem Background<br/>Specific pain points"]
Pr --> C["Core Concepts<br/>Illustrations and intuition"]
C --> B["Build It<br/>Pure math, no frameworks"]
B --> U["Use It<br/>Do the same thing with PyTorch / sklearn"]
U --> S["Take It<br/>Prompts · Skills · Agents · MCP"]
```
## Quick Start
Three ways to get started. Pick one.
**Method A — Reading.** Open any completed lesson on [aieng-zh.cn](https://aieng-zh.cn), or expand a phase in the [directory](#contents). No setup required, no cloning.
**Method B — Clone and Run.**
```bash
git clone https://github.com/fancyboi999/ai-engineering-from-scratch-zh.git
cd ai-engineering-from-scratch-zh
python phases/01-math-foundations/01-linear-algebra-intuition/code/vectors.py
```
**Method C — Test Your Level *(recommended)*.** Smartly jump levels. In Claude, Cursor, Codex, OpenClaw, Hermes, or any agent with installed skills:
```bash
/find-your-level
```
Ten questions. Map your knowledge to a starting phase, generating a personalized path with estimated hours. After completing a phase:
```bash
/check-understanding 3 # test your understanding of phase 3
ls phases/03-deep-learning-core/05-loss-functions/outputs/
# ├── prompt-loss-function-selector.md
# └── prompt-loss-debugger.md
```
### Prerequisites
- You can write code (any language; Python is a plus).
- You want to understand how **AI actually works**, not just use APIs.
### Built-in Agent Skills (Claude, Cursor, Codex, OpenClaw, Hermes)
| Skill | Function |
|---|---|
| [`/find-your-level`](.claude/skills/find-your-level/SKILL.md) | Ten-question placement test. Maps your knowledge to a starting phase, generating a personalized path with estimated hours. |
| [`/check-understanding <phase>`](.claude/skills/check-understanding/SKILL.md) | Phase-specific quizzes, eight questions, with feedback and specific lessons to review. |
```
░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒
```
## Each Lesson Has a Deliverable
Other courses end with *"Congratulations, you learned X."* Here, each lesson ends with a **reusable tool** you can directly use or integrate into your workflow.
<table>
<tr>
<th align="left" width="25%"><img src="site/assets/figures/001-a-prompts.svg" width="96" height="96" alt="FIG_001.A prompts"/><br/><sub>FIG_001 · A</sub><br/><b>PROMPTS</b></th>
<th align="left" width="25%"><img src="site/assets/figures/001-b-skills.svg" width="96" height="96" alt="FIG_001.B skills"/><br/><sub>FIG_001 · B</sub><br/><b>SKILLS</b></th>
<th align="left" width="25%"><img src="site/assets/figures/001-c-agents.svg" width="96" height="96" alt="FIG_001.C agents"/><br/><sub>FIG_001 · C</sub><br/><b>AGENTS</b></th>
<th align="left" width="25%"><img src="site/assets/figures/001-d-mcp-servers.svg" width="96" height="96" alt="FIG_001.D MCP servers"/><br/><sub>FIG_001 · D</sub><br/><b>MCP SERVERS</b></th>
</tr>
<tr>
<td valign="top">Paste into any AI assistant for expert-level help on specific tasks.</td>
<td valign="top">Deploy in Claude, Cursor, Codex, OpenClaw, Hermes, or any agent that can read <code>SKILL.md</code>.</td>
<td valign="top">Deploy as autonomous workers—you wrote the loop in Phase 14.</td>
<td valign="top">Connect with any compatible MCP client—built from scratch in Phase 13.</td>
</tr>
</table>
> Install all skills at once with `python3 scripts/install_skills.py`. These are real tools, not homework.
> After completing the course, you'll have nearly 500 deliverables—you understand them because you built them.
### FIG_002 · An Example
Phase 14, Lesson 1: agent loop. About 120 lines of pure Python, zero dependencies.
<table>
<tr>
<td valign="top" width="50%">
**`code/agent_loop.py`** <sub><i>Build It</i></sub>
```python
def run(query, tools):
history = [user(query)]
for step in range(MAX_STEPS):
msg = llm(history)
if msg.tool_calls:
for call in msg.tool_calls:
result = tools[call.name](**call.args)
history.append(tool_result(call.id, result))
continue
return msg.content
raise StepLimitExceeded
```
</td>
<td valign="top" width="50%">
**`outputs/skill-agent-loop.md`** <sub><i>Deliverable</i></sub>
```markdown
---
name: agent-loop
description: ReAct-style loop for any tool list
phase: 14
lesson: 01
---
Implement a minimal agent loop that...
```
**`outputs/prompt-debug-agent.md`**
```markdown
You are an agent debugger. Given the trace
of an agent run, identify the step where
the agent went wrong and explain why...
```
</td>
</tr>
</table>
```
░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒
```
<a id="contents"></a>
## Course Directory
Twenty phases. Click on any phase to expand its lesson list.
<a id="phase-0"></a>
### Phase 0: Setup and Tooling `12 lessons`
> Get your environment ready for all the content to come.
| # | Lesson | Type | Lang |
|:---:|--------|:----:|------|
| 01 | [Development Environment](phases/00-setup-and-tooling/01-dev-environment/) | Build | Python |
| 02 | [Git and Collaboration](phases/00-setup-and-tooling/02-git-and-collaboration/) | Learn | — |
| 03 | [GPU Setup and Cloud](phases/00-setup-and-tooling/03-gpu-setup-and-cloud/) | Build | Python |
| 04 | [APIs and Keys](phases/00-setup-and-tooling/04-apis-and-keys/) | Build | Python |
| 05 | [Jupyter Notebook](phases/00-setup-and-tooling/05-jupyter-notebooks/) | Build | Python |
| 06 | [Python Environment Management](phases/00-setup-and-tooling/06-python-environments/) | Build | Shell |
| 07 | [Docker for AI](phases/00-setup-and-tooling/07-docker-for-ai/) | Build | Docker |
| 08 | [Editor Setup](phases/00-setup-and-tooling/08-editor-setup/) | Build | — |
| 09 | [Data Management](phases/00-setup-and-tooling/09-data-management/) | Build | Python |
| 10 | [Terminal and Shell](phases/00-setup-and-tooling/10-terminal-and-shell/) | Learn | — |
| 11 | [Linux for AI](phases/00-setup-and-tooling/11-linux-for-ai/) | Learn | — |
| 12 | [Debugging and Profiling](phases/00-setup-and-tooling/12-debugging-and-profiling/) | Build | Python |
<details id="phase-1">
<summary><b>Phase 1 — Math Foundations</b> <code>22 lessons</code> <em>The intuition behind every AI algorithm, explained with code.</em></summary>
<br/>
| # | Lesson | Type | Lang |
|:---:|--------|:----:|------|
| 01 | [Linear Algebra Intuition](phases/01-math-foundations/01-linear-algebra-intuition/) | Learn | Python, Julia |
| 02 | [Vectors, Matrices, and Operations](phases/01-math-foundations/02-vectors-matrices-operations/) | Build | Python, Julia |
| 03 | [Matrix Transformations and Eigenvalues](phases/01-math-foundations/03-matrix-transformations/) | Build | Python, Julia |
| 04 | [Calculus for ML: Derivatives and Gradients](phases/01-math-foundations/04-calculus-for-ml/) | Learn | Python |
| 05 | [Chain Rule and Automatic Differentiation](phases/01-math-foundations/05-chain-rule-and-autodiff/) | Build | Python |
| 06 | [Probability and Distributions](phases/01-math-foundations/06-probability-and-distributions/) | Learn | Python |
| 07 | [Bayes' Theorem and Statistical Thinking](phases/01-math-foundations/07-bayes-theorem/) | Build | Python |
| 08 | [Optimization: Gradient Descent Family](phases/01-math-foundations/08-optimization/) | Build | Python |
| 09 | [Information Theory: Entropy and KL Divergence](phases/01-math-foundations/09-information-theory/) | Learn | Python |
| 10 | [Dimensionality Reduction: PCA, t-SNE, UMAP](phases/01-math-foundations/10-dimensionality-reduction/) | Build | Python |
| 11 | [Singular Value Decomposition](phases/01-math-foundations/11-singular-value-decomposition/) | Build | Python, Julia |
| 12 | [Tensor Operations](phases/01-math-foundations/12-tensor-operations/) | Build | Python |
| 13 | [Numerical Stability](phases/01-math-foundations/13-numerical-stability/) | Build | Python |
| 14 | [Norms and Distances](phases/01-math-foundations/14-norms-and-distances/) | Build | Python |
| 15 | [Statistics for ML](phases/01-math-foundations/15-statistics-for-ml/) | Build | Python |
| 16 | [Sampling Methods](phases/01-math-foundations/16-sampling-methods/) | Build | Python |
| 17 | [Linear Systems](phases/01-math-foundations/17-linear-systems/) | Build | Python |
| 18 | [Convex Optimization](phases/01-math-foundations/18-convex-optimization/) | Build | Python |
| 19 | [Complex Numbers for AI](phases/01-math-foundations/19-complex-numbers/) | Learn | Python |
| 20 | [Fourier Transform](phases/01-math-foundations/20-fourier-transform/) | Build | Python |
| 21 | [Graph Theory for ML](phases/01-math-foundations/21-graph-theory/) | Build | Python |
| 22 | [Stochastic Processes](phases/01-math-foundations/22-stochastic-processes/) | Learn | Python |
</details>
<details id="phase-2">
<summary><b>Phase 2 — Machine Learning Fundamentals</b> <code>18 lessons</code> <em>Classical machine learning — still the backbone of most production AI.</em></summary>
<br/>
| # | Lesson | Type | Lang |
|:---:|--------|:----:|------|
| 01 | [What is Machine Learning](phases/02-ml-fundamentals/01-what-is-machine-learning/) | Learn | Python |
| 02 | [Linear Regression from Scratch](phases/02-ml-fundamentals/02-linear-regression/) | Build | Python |
| 03 | [Logistic Regression and Classification](phases/02-ml-fundamentals/03-logistic-regression/) | Build | Python |
| 04 | [Decision Trees and Random Forests](phases/02-ml-fundamentals/04-decision-trees/) | Build | Python |
| 05 | [Support Vector Machines](phases/02-ml-fundamentals/05-support-vector-machines/) | Build | Python |
| 06 | [KNN and Distance Metrics](phases/02-ml-fundamentals/06-knn-and-distances/) | Build | Python |
| 07 | [Unsupervised Learning: K-Means, DBSCAN](phases/02-ml-fundamentals/07-unsupervised-learning/) | Build | Python |
| 08 | [Feature Engineering and Selection](phases/02-ml-fundamentals/08-feature-engineering/) | Build | Python |
| 09 | [Model Evaluation: Metrics and Cross-Validation](phases/02-ml-fundamentals/09-model-evaluation/) | Build | Python |
| 10 | [Bias, Variance, and Learning Curves](phases/02-ml-fundamentals/10-bias-variance/) | Learn | Python |
| 11 | [Ensemble Methods: Boosting, Bagging, Stacking](phases/02-ml-fundamentals/11-ensemble-methods/) | Build | Python |
| 12 | [Hyperparameter Tuning](phases/02-ml-fundamentals/12-hyperparameter-tuning/) | Build | Python |
| 13 | [Machine Learning Pipelines and Experiment Tracking](phases/02-ml-fundamentals/13-ml-pipelines/) | Build | Python |
| 14 | [Naive Bayes](phases/02-ml-fundamentals/14-naive-bayes/) | Build | Python |
| 15 | [Time Series Fundamentals](phases/02-ml-fundamentals/15-time-series/) | Build | Python |
| 16 | [Anomaly Detection](phases/02-ml-fundamentals/16-anomaly-detection/) | Build | Python |
| 17 | [Handling Imbalanced Data](phases/02-ml-fundamentals/17-imbalanced-data/) | Build | Python |
| 18 | [Feature Selection](phases/02-ml-fundamentals/18-feature-selection/) | Build | Python |
</details>
<details id="phase-3">
<summary><b>Phase 3 — Deep Learning Core</b> <code>13 lessons</code> <em>Neural networks from first principles. Build your own before moving to frameworks.</em></summary>
<br/>
| # | Lesson | Type | Lang |
|:---:|--------|:----:|------|
| 01 | [The Perceptron: The Beginning](phases/03-deep-learning-core/01-the-perceptron/) | Build | Python |
| 02 | [Multi-Layer Networks and Forward Propagation](phases/03-deep-learning-core/02-multi-layer-networks/) | Build | Python |
| 03 | [Backpropagation from Scratch](phases/03-deep-learning-core/03-backpropagation/) | Build | Python |
| 04 | [Activation Functions: ReLU, Sigmoid, GELU, and Why](phases/03-deep-learning-core/04-activation-functions/) | Build | Python |
| 05 | [Loss Functions: MSE, Cross-Entropy, Contrastive Loss](phases/03-deep-learning-core/05-loss-functions/) | Build | Python |
| 06 | [Optimizers: SGD, Momentum, Adam, AdamW](phases/03-deep-learning-core/06-optimizers/) | Build | Python |
| 07 | [Regularization: Dropout, Weight Decay, BatchNorm](phases/03-deep-learning-core/07-regularization/) | Build | Python |
| 08 | [Weight Initialization and Training Stability](phases/03-deep-learning-core/08-weight-initialization/) | Build | Python |
| 09 | [Learning Rate Schedules and Warmup](phases/03-deep-learning-core/09-learning-rate-schedules/) | Build | Python |
| 10 | [Build Your Own Mini Framework](phases/03-deep-learning-core/10-mini-framework/) | Build | Python |
| 11 | [Introduction to PyTorch](phases/03-deep-learning-core/11-intro-to-pytorch/) | Build | Python |
| 12 | [Introduction to JAX](phases/03-deep-learning-core/12-intro-to-jax/) | Build | Python |
| 13 | [Debugging Neural Networks](phases/03-deep-learning-core/13-debugging-neural-networks/) | Build | Python |
</details>
<details id="phase-4">
<summary><b>Phase 4 — Computer Vision</b> <code>28 lessons</code> <em>From pixels to understanding — images, videos, 3D, VLM, and world models.</em></summary>
<br/>
# Tool List
| # | Lesson | Type | Lang |
|:---:|--------|:----:|------|
| 01 | [Image Fundamentals: Pixels, Channels, Color Space](phases/04-computer-vision/01-image-fundamentals/) | Learn | Python |
| 02 | [Implementing Convolutions from Scratch](phases/04-computer-vision/02-convolutions-from-scratch/) | Build | Python |
| 03 | [CNNs: From LeNet to ResNet](phases/04-computer-vision/03-cnns-lenet-to-resnet/) | Build | Python |
| 04 | [Image Classification](phases/04-computer-vision/04-image-classification/) | Build | Python |
| 05 | [Transfer Learning and Fine-Tuning](phases/04-computer-vision/05-transfer-learning/) | Build | Python |
| 06 | [Object Detection - Implementing YOLO from Scratch](phases/04-computer-vision/06-object-detection-yolo/) | Build | Python |
| 07 | [Semantic Segmentation - U-Net](phases/04-computer-vision/07-semantic-segmentation-unet/) | Build | Python |
| 08 | [Instance Segmentation - Mask R-CNN](phases/04-computer-vision/08-instance-segmentation-mask-rcnn/) | Build | Python |
| 09 | [Image Generation - GANs](phases/04-computer-vision/09-image-generation-gans/) | Build | Python |
| 10 | [Image Generation - Diffusion Models](phases/04-computer-vision/10-image-generation-diffusion/) | Build | Python |
| 11 | [Stable Diffusion - Architecture and Fine-Tuning](phases/04-computer-vision/11-stable-diffusion/) | Build | Python |
| 12 | [Video Understanding - Temporal Modeling](phases/04-computer-vision/12-video-understanding/) | Build | Python |
| 13 | [3D Vision: Point Clouds, NeRF](phases/04-computer-vision/13-3d-vision-nerf/) | Build | Python |
| 14 | [Vision Transformers (ViT)](phases/04-computer-vision/14-vision-transformers/) | Build | Python |
| 15 | [Real-Time Vision: Edge Deployment](phases/04-computer-vision/15-real-time-edge/) | Build | Python |
| 16 | [Building a Complete Visual Pipeline](phases/04-computer-vision/16-vision-pipeline-capstone/) | Build | Python |
| 17 | [Self-Supervised Vision - SimCLR, DINO, MAE](phases/04-computer-vision/17-self-supervised-vision/) | Build | Python |
| 18 | [Open-Vocabulary Vision - CLIP](phases/04-computer-vision/18-open-vocab-clip/) | Build | Python |
| 19 | [OCR and Document Understanding](phases/04-computer-vision/19-ocr-document-understanding/) | Build | Python |
| 20 | [Image Retrieval and Metric Learning](phases/04-computer-vision/20-image-retrieval-metric/) | Build | Python |
| 21 | [Keypoint Detection and Pose Estimation](phases/04-computer-vision/21-keypoint-pose/) | Build | Python |
| 22 | [Implementing 3D Gaussian Splatting from Scratch](phases/04-computer-vision/22-3d-gaussian-splatting/) | Build | Python |
| 23 | [Diffusion Transformers and Rectified Flow](phases/04-computer-vision/23-diffusion-transformers-rectified-flow/) | Build | Python |
| 24 | [SAM 3 and Open-Vocabulary Segmentation](phases/04-computer-vision/24-sam3-open-vocab-segmentation/) | Build | Python |
| 25 | [Vision Language Models (ViT-MLP-LLM)](phases/04-computer-vision/25-vision-language-models/) | Build | Python |
| 26 | [Monocular Depth and Geometry Estimation](phases/04-computer-vision/26-monocular-depth/) | Build | Python |
| 27 | [Multi-Object Tracking and Video Memory](phases/04-computer-vision/27-multi-object-tracking/) | Build | Python |
| 28 | [World Models and Video Diffusion](phases/04-computer-vision/28-world-models-video-diffusion/) | Build | Python |
<details id="phase-5">
<summary><b>Phase 5 — NLP: From Foundations to Advanced</b> <code>29 lessons</code> <em>Language is the interface to intelligence.</em></summary>
<br/>
| # | Lesson | Type | Lang |
|:---:|--------|:----:|------|
| 01 | [Text Processing: Tokenization, Stemming, Lemmatization](phases/05-nlp-foundations-to-advanced/01-text-processing/) | Build | Python |
| 02 | [Bag of Words, TF-IDF, and Text Representation](phases/05-nlp-foundations-to-advanced/02-bag-of-words-tfidf/) | Build | Python |
| 03 | [Word Embeddings: Implementing Word2Vec from Scratch](phases/05-nlp-foundations-to-advanced/03-word-embeddings-word2vec/) | Build | Python |
| 04 | [GloVe, FastText, and Subword Embeddings](phases/05-nlp-foundations-to-advanced/04-glove-fasttext-subword/) | Build | Python |
| 05 | [Sentiment Analysis](phases/05-nlp-foundations-to-advanced/05-sentiment-analysis/) | Build | Python |
| 06 | [Named Entity Recognition (NER)](phases/05-nlp-foundations-to-advanced/06-named-entity-recognition/) | Build | Python |
| 07 | [Part-of-Speech Tagging and Parsing](phases/05-nlp-foundations-to-advanced/07-pos-tagging-parsing/) | Build | Python |
| 08 | [Text Classification - CNNs and RNNs for Text](phases/05-nlp-foundations-to-advanced/08-cnns-rnns-for-text/) | Build | Python |
| 09 | [Sequence-to-Sequence Models](phases/05-nlp-foundations-to-advanced/09-sequence-to-sequence/) | Build | Python |
| 10 | [Attention Mechanism - The Breakthrough](phases/05-nlp-foundations-to-advanced/10-attention-mechanism/) | Build | Python |
| 11 | [Machine Translation](phases/05-nlp-foundations-to-advanced/11-machine-translation/) | Build | Python |
| 12 | [Text Summarization](phases/05-nlp-foundations-to-advanced/12-text-summarization/) | Build | Python |
| 13 | [Question Answering Systems](phases/05-nlp-foundations-to-advanced/13-question-answering/) | Build | Python |
| 14 | [Information Retrieval and Search](phases/05-nlp-foundations-to-advanced/14-information-retrieval-search/) | Build | Python |
| 15 | [Topic Modeling: LDA, BERTopic](phases/05-nlp-foundations-to-advanced/15-topic-modeling/) | Build | Python |
| 16 | [Text Generation](phases/05-nlp-foundations-to-advanced/16-text-generation-pre-transformer/) | Build | Python |
| 17 | [Chatbots: From Rules to Neural Networks](phases/05-nlp-foundations-to-advanced/17-chatbots-rule-to-neural/) | Build | Python |
| 18 | [Multilingual NLP](phases/05-nlp-foundations-to-advanced/18-multilingual-nlp/) | Build | Python |
| 19 | [Subword Tokenization: BPE, WordPiece, Unigram, SentencePiece](phases/05-nlp-foundations-to-advanced/19-subword-tokenization/) | Learn | Python |
| 20 | [Structured Outputs and Constrained Decoding](phases/05-nlp-foundations-to-advanced/20-structured-outputs-constrained-decoding/) | Build | Python |
| 21 | [Natural Language Inference and Textual Entailment](phases/05-nlp-foundations-to-advanced/21-nli-textual-entailment/) | Learn | Python |
| 22 | [Deep Dive into Embedding Models](phases/05-nlp-foundations-to-advanced/22-embedding-models-deep-dive/) | Learn | Python |
| 23 | [Chunking Strategies for RAG](phases/05-nlp-foundations-to-advanced/23-chunking-strategies-rag/) | Build | Python |
| 24 | [Coreference Resolution](phases/05-nlp-foundations-to-advanced/24-coreference-resolution/) | Learn | Python |
| 25 | [Entity Linking and Disambiguation](phases/05-nlp-foundations-to-advanced/25-entity-linking/) | Build | Python |
| 26 | [Relation Extraction and Knowledge Graph Construction](phases/05-nlp-foundations-to-advanced/26-relation-extraction-kg/) | Build | Python |
| 27 | [LLM Evaluation: RAGAS, DeepEval, G-Eval](phases/05-nlp-foundations-to-advanced/27-llm-evaluation-frameworks/) | Build | Python |
| 28 | [Long Context Evaluation: NIAH, RULER, LongBench, MRCR](phases/05-nlp-foundations-to-advanced/28-long-context-evaluation/) | Learn | Python |
| 29 | [Dialogue State Tracking](phases/05-nlp-foundations-to-advanced/29-dialogue-state-tracking/) | Build | Python |
</details>
<details id="phase-6">
<summary><b>Phase 6 — Speech and Audio</b> <code>17 lessons</code> <em>Hear, understand, and speak.</em></summary>
<br/>
| # | Lesson | Type | Lang |
|:---:|--------|:----:|------|
| 01 | [Audio Fundamentals: Waveforms, Sampling, FFT](phases/06-speech-and-audio/01-audio-fundamentals) | Learn | Python |
| 02 | [Spectrograms, Mel Scale, and Audio Features](phases/06-speech-and-audio/02-spectrograms-mel-features) | Build | Python |
| 03 | [Audio Classification](phases/06-speech-and-audio/03-audio-classification) | Build | Python |
| 04 | [Speech Recognition (ASR)](phases/06-speech-and-audio/04-speech-recognition-asr) | Build | Python |
| 05 | [Whisper: Architecture and Fine-Tuning](phases/06-speech-and-audio/05-whisper-architecture-finetuning) | Build | Python |
| 06 | [Speaker Recognition and Verification](phases/06-speech-and-audio/06-speaker-recognition-verification) | Build | Python |
| 07 | [Text-to-Speech (TTS)](phases/06-speech-and-audio/07-text-to-speech) | Build | Python |
| 08 | [Voice Cloning and Voice Conversion](phases/06-speech-and-audio/08-voice-cloning-conversion) | Build | Python |
| 09 | [Music Generation](phases/06-speech-and-audio/09-music-generation) | Build | Python |
| 10 | [Audio Language Models](phases/06-speech-and-audio/10-audio-language-models) | Build | Python |
| 11 | [Real-Time Audio Processing](phases/06-speech-and-audio/11-real-time-audio-processing) | Build | Python |
| 12 | [Building a Voice Assistant Pipeline](phases/06-speech-and-audio/12-voice-assistant-pipeline) | Build | Python |
| 13 | [Neural Audio Codecs - EnCodec, SNAC, Mimi, DAC](phases/06-speech-and-audio/13-neural-audio-codecs) | Learn | Python |
| 14 | [Voice Activity Detection and Turn-Taking](phases/06-speech-and-audio/14-voice-activity-detection-turn-taking) | Build | Python |
| 15 | [Streaming Speech-to-Speech - Moshi, Hibiki](phases/06-speech-and-audio/15-streaming-speech-to-speech-moshi-hibiki) | Learn | Python |
| 16 | [Audio Anti-Spoofing and Watermarking](phases/06-speech-and-audio/16-anti-spoofing-audio-watermarking) | Build | Python |
| 17 | [Audio Evaluation Metrics - WER, MOS, MMAU, Leaderboards](phases/06-speech-and-audio/17-audio-evaluation-metrics) | Learn | Python |
</details>
<details id="phase-7">
<summary><b>Phase 7 — Transformer Deep Dive</b> <code>16 lessons</code> <em>The architecture that changed everything.</em></summary>
<br/>
# Tool List
| # | Lesson | Type | Lang |
|:---:|--------|:----:|------|
| 01 | [Why Use Transformers: Problems with RNNs](phases/07-transformers-deep-dive/01-why-transformers/) | Learn | Python |
| 02 | [Implementing Self-Attention from Scratch](phases/07-transformers-deep-dive/02-self-attention-from-scratch/) | Build | Python |
| 03 | [Multi-Head Attention](phases/07-transformers-deep-dive/03-multi-head-attention/) | Build | Python |
| 04 | [Positional Encoding: Sinusoidal, RoPE, ALiBi](phases/07-transformers-deep-dive/04-positional-encoding/) | Build | Python |
| 05 | [Full Transformer: Encoder + Decoder](phases/07-transformers-deep-dive/05-full-transformer/) | Build | Python |
| 06 | [BERT — Masked Language Modeling](phases/07-transformers-deep-dive/06-bert-masked-language-modeling/) | Build | Python |
| 07 | [GPT — Causal Language Modeling](phases/07-transformers-deep-dive/07-gpt-causal-language-modeling/) | Build | Python |
| 08 | [T5, BART — Encoder-Decoder Models](phases/07-transformers-deep-dive/08-t5-bart-encoder-decoder/) | Learn | Python |
| 09 | [Vision Transformers (ViT)](phases/07-transformers-deep-dive/09-vision-transformers/) | Build | Python |
| 10 | [Audio Transformers — Whisper Architecture](phases/07-transformers-deep-dive/10-audio-transformers-whisper/) | Learn | Python |
| 11 | [Mixture of Experts (MoE)](phases/07-transformers-deep-dive/11-mixture-of-experts/) | Build | Python |
| 12 | [KV Cache, Flash Attention, and Inference Optimization](phases/07-transformers-deep-dive/12-kv-cache-flash-attention/) | Build | Python |
| 13 | [Scaling Laws](phases/07-transformers-deep-dive/13-scaling-laws/) | Learn | Python |
| 14 | [Building a Transformer from Scratch](phases/07-transformers-deep-dive/14-build-a-transformer-capstone/) | Build | Python |
| 15 | [Attention Variants — Sliding Window, Sparse, Differential](phases/07-transformers-deep-dive/15-attention-variants/) | Build | Python |
| 16 | [Speculative Decoding — Drafting, Verification, and Repetition](phases/07-transformers-deep-dive/16-speculative-decoding/) | Build | Python |
</details>
<details id="phase-8">
<summary><b>Phase 8 — Generative AI</b> <code>15 lessons</code> <em>Generating images, videos, audio, 3D, and more.</em></summary>
<br/>
| # | Lesson | Type | Lang |
|:---:|--------|:----:|------|
| 01 | [Generative Models: Taxonomy and History](phases/08-generative-ai/01-generative-models-taxonomy-history/) | Learn | Python |
| 02 | [Autoencoders and VAE](phases/08-generative-ai/02-autoencoders-vae/) | Build | Python |
| 03 | [GANs: Generators vs Discriminators](phases/08-generative-ai/03-gans-generator-discriminator/) | Build | Python |
| 04 | [Conditional GANs and Pix2Pix](phases/08-generative-ai/04-conditional-gans-pix2pix/) | Build | Python |
| 05 | [StyleGAN](phases/08-generative-ai/05-stylegan/) | Build | Python |
| 06 | [Diffusion Models — Implementing DDPM from Scratch](phases/08-generative-ai/06-diffusion-ddpm-from-scratch/) | Build | Python |
| 07 | [Latent Diffusion and Stable Diffusion](phases/08-generative-ai/07-latent-diffusion-stable-diffusion/) | Build | Python |
| 08 | [ControlNet, LoRA, and Conditional Control](phases/08-generative-ai/08-controlnet-lora-conditioning/) | Build | Python |
| 09 | [Image Inpainting, Outpainting, and Editing](phases/08-generative-ai/09-inpainting-outpainting-editing/) | Build | Python |
| 10 | [Video Generation](phases/08-generative-ai/10-video-generation/) | Build | Python |
| 11 | [Audio Generation](phases/08-generative-ai/11-audio-generation/) | Build | Python |
| 12 | [3D Generation](phases/08-generative-ai/12-3d-generation/) | Build | Python |
| 13 | [Flow Matching and Rectified Flow](phases/08-generative-ai/13-flow-matching-rectified-flows/) | Build | Python |
| 14 | [Evaluation: FID, CLIP Score](phases/08-generative-ai/14-evaluation-fid-clip-score/) | Build | Python |
| 19 | [Visual Autoregressive Modeling (VAR): Next Scale Prediction](phases/08-generative-ai/19-visual-autoregressive-var/) | Build | Python |
</details>
<details id="phase-9">
<summary><b>Phase 9 — Reinforcement Learning</b> <code>12 lessons</code> <em>The foundation for RLHF and AI that can play games.</em></summary>
<br/>
| # | Lesson | Type | Lang |
|:---:|--------|:----:|------|
| 01 | [MDPs, States, Actions, and Rewards](phases/09-reinforcement-learning/01-mdps-states-actions-rewards/) | Learn | Python |
| 02 | [Dynamic Programming](phases/09-reinforcement-learning/02-dynamic-programming/) | Build | Python |
| 03 | [Monte Carlo Methods](phases/09-reinforcement-learning/03-monte-carlo-methods/) | Build | Python |
| 04 | [Q-Learning, SARSA](phases/09-reinforcement-learning/04-q-learning-sarsa/) | Build | Python |
| 05 | [Deep Q Networks (DQN)](phases/09-reinforcement-learning/05-dqn/) | Build | Python |
| 06 | [Policy Gradients — REINFORCE](phases/09-reinforcement-learning/06-policy-gradients-reinforce/) | Build | Python |
| 07 | [Actor-Critic — A2C, A3C](phases/09-reinforcement-learning/07-actor-critic-a2c-a3c/) | Build | Python |
| 08 | [PPO](phases/09-reinforcement-learning/08-ppo/) | Build | Python |
| 09 | [Reward Modeling and RLHF](phases/09-reinforcement-learning/09-reward-modeling-rlhf/) | Build | Python |
| 10 | [Multi-Agent Reinforcement Learning](phases/09-reinforcement-learning/10-multi-agent-rl/) | Build | Python |
| 11 | [Sim-to-Real Transfer](phases/09-reinforcement-learning/11-sim-to-real-transfer/) | Build | Python |
| 12 | [Reinforcement Learning in Games](phases/09-reinforcement-learning/12-rl-for-games/) | Build | Python |
</details>
<details id="phase-10">
<summary><b>Phase 10 — Building LLMs from Scratch</b> <code>24 lessons</code> <em>Construct, train, and truly understand large language models.</em></summary>
<br/>
| # | Lesson | Type | Lang |
|:---:|--------|:----:|------|
| 01 | [Tokenizers: BPE, WordPiece, SentencePiece](phases/10-llms-from-scratch/01-tokenizers/) | Build | Python, Rust |
| 02 | [Building a Tokenizer from Scratch](phases/10-llms-from-scratch/02-building-a-tokenizer/) | Build | Python |
| 03 | [Pre-Training Data Pipelines](phases/10-llms-from-scratch/03-data-pipelines/) | Build | Python |
| 04 | [Pre-Training a Mini GPT (124M)](phases/10-llms-from-scratch/04-pre-training-mini-gpt/) | Build | Python |
| 05 | [Distributed Training, FSDP, DeepSpeed](phases/10-llms-from-scratch/05-scaling-distributed/) | Build | Python |
| 06 | [Instruction Tuning — SFT](phases/10-llms-from-scratch/06-instruction-tuning-sft/) | Build | Python |
| 07 | [RLHF — Reward Models + PPO](phases/10-llms-from-scratch/07-rlhf/) | Build | Python |
| 08 | [DPO — Direct Preference Optimization](phases/10-llms-from-scratch/08-dpo/) | Build | Python |
| 09 | [Constitutional AI and Self-Improvement](phases/10-llms-from-scratch/09-constitutional-ai-self-improvement/) | Build | Python |
| 10 | [Evaluation — Benchmarks and Evals](phases/10-llms-from-scratch/10-evaluation/) | Build | Python |
| 11 | [Quantization: INT8, GPTQ, AWQ, GGUF](phases/10-llms-from-scratch/11-quantization/) | Build | Python |
| 12 | [Inference Optimization](phases/10-llms-from-scratch/12-inference-optimization/) | Build | Python |
| 13 | [Building a Complete LLM Pipeline](phases/10-llms-from-scratch/13-building-complete-llm-pipeline/) | Build | Python |
| 14 | [Open Models: Architecture Walkthroughs](phases/10-llms-from-scratch/14-open-models-architecture-walkthroughs/) | Learn | Python |
| 15 | [Speculative Decoding and EAGLE-3](phases/10-llms-from-scratch/15-speculative-decoding-eagle3/) | Build | Python |
| 16 | [Differential Attention (V2)](phases/10-llms-from-scratch/16-differential-attention-v2/) | Build | Python |
| 17 | [Native Sparse Attention (DeepSeek NSA)](phases/10-llms-from-scratch/17-native-sparse-attention/) | Build | Python |
| 18 | [Multi-Token Prediction (MTP)](phases/10-llms-from-scratch/18-multi-token-prediction/) | Build | Python |
| 19 | [DualPipe Parallelism](phases/10-llms-from-scratch/19-dualpipe-parallelism/) | Learn | Python |
| 20 | [DeepSeek-V3 Architecture Walkthrough](phases/10-llms-from-scratch/20-deepseek-v3-walkthrough/) | Learn | Python |
| 21 | [Jamba — SSM-Transformer Hybrid Architecture](phases/10-llms-from-scratch/21-jamba-hybrid-ssm-transformer/) | Learn | Python |
| 22 | [Asynchronous and Hogwild! Inference](phases/10-llms-from-scratch/22-async-hogwild-inference/) | Build | Python |
| 25 | [Speculative Decoding and EAGLE](phases/10-llms-from-scratch/25-speculative-decoding/) | Build | Python |
| 34 | [Gradient Checkpointing and Activation Recomputation](phases/10-llms-from-scratch/34-gradient-checkpointing/) | Build | Python |
</details>
<details id="phase-11">
<summary><b>Phase 11 — LLM Engineering</b> <code>17 lessons</code> <em>Getting LLMs to work in production.</em></summary>
<br/>
Here is the translated document:
| # | Lesson | Type | Lang |
|:---:|--------|:----:|------|
| 01 | [Prompt Engineering](phases/11-llm-engineering/01-prompt-engineering/) | Build | Python |
| 02 | [Few-Shot、CoT、Tree-of-Thought](phases/11-llm-engineering/02-few-shot-cot/) | Build | Python |
| 03 | [Structured Outputs](phases/11-llm-engineering/03-structured-outputs/) | Build | Python |
| 04 | [Embeddings and Vector Representations](phases/11-llm-engineering/04-embeddings/) | Build | Python |
| 05 | [Context Engineering](phases/11-llm-engineering/05-context-engineering/) | Build | Python |
| 06 | [RAG: Retrieval-Augmented Generation](phases/11-llm-engineering/06-rag/) | Build | Python |
| 07 | [Advanced RAG: Chunking, Re-ranking](phases/11-llm-engineering/07-advanced-rag/) | Build | Python |
| 08 | [Fine-Tuning with LoRA and QLoRA](phases/11-llm-engineering/08-fine-tuning-lora/) | Build | Python |
| 09 | [Function Calling and Tool Use](phases/11-llm-engineering/09-function-calling/) | Build | Python |
| 10 | [Evaluation and Testing](phases/11-llm-engineering/10-evaluation/) | Build | Python |
| 11 | [Caching, Rate Limiting, and Cost](phases/11-llm-engineering/11-caching-cost/) | Build | Python |
| 12 | [Guardrails and Security](phases/11-llm-engineering/12-guardrails/) | Build | Python |
| 13 | [Building a Production-Grade LLM App](phases/11-llm-engineering/13-production-app/) | Build | Python |
| 14 | [Model Context Protocol (MCP)](phases/11-llm-engineering/14-model-context-protocol/) | Build | Python |
| 15 | [Prompt Caching and Context Caching](phases/11-llm-engineering/15-prompt-caching/) | Build | Python |
| 16 | [LangGraph: State Machines for Agents](phases/11-llm-engineering/16-langgraph-state-machines/) | Build | Python |
| 17 | [Agent Framework Tradeoffs](phases/11-llm-engineering/17-agent-framework-tradeoffs/) | Learn | Python |
</details>
<details id="phase-12">
<summary><b>Phase 12 — Multimodal AI</b> <code>25 lessons</code> <em>Cross-modal perception, understanding, and reasoning - from ViT patches to agents that operate on computers.</em></summary>
<br/>
| # | Lesson | Type | Lang |
|:---:|--------|:----:|------|
| 01 | [Vision Transformer and Patch Tokens](phases/12-multimodal-ai/01-vision-transformer-patch-tokens/) | Learn | Python |
| 02 | [CLIP and Contrastive Visual-Language Pre-training](phases/12-multimodal-ai/02-clip-contrastive-pretraining/) | Build | Python |
| 03 | [BLIP-2 Q-Former as a Modal Bridge](phases/12-multimodal-ai/03-blip2-qformer-bridge/) | Build | Python |
| 04 | [Flamingo and Gated Cross-Attention](phases/12-multimodal-ai/04-flamingo-gated-cross-attention/) | Learn | Python |
| 05 | [LLaVA and Visual Instruction Tuning](phases/12-multimodal-ai/05-llava-visual-instruction-tuning/) | Build | Python |
| 06 | [Arbitrary Resolution Vision - Patch-n'-Pack and NaFlex](phases/12-multimodal-ai/06-any-resolution-patch-n-pack/) | Build | Python |
| 07 | [Open-Weight VLM Recipes: What Matters](phases/12-multimodal-ai/07-open-weight-vlm-recipes/) | Learn | Python |
| 08 | [LLaVA-OneVision: Single Image, Multi-Image, Video](phases/12-multimodal-ai/08-llava-onevision-single-multi-video/) | Build | Python |
| 09 | [Qwen-VL Family and Dynamic FPS Video](phases/12-multimodal-ai/09-qwen-vl-family-dynamic-fps/) | Learn | Python |
| 10 | [InternVL3 Native Multimodal Pre-training](phases/12-multimodal-ai/10-internvl3-native-multimodal/) | Learn | Python |
| 11 | [Chameleon Early Fusion Tokens](phases/12-multimodal-ai/11-chameleon-early-fusion-tokens/) | Build | Python |
| 12 | [Emu3 Next Token for Generation](phases/12-multimodal-ai/12-emu3-next-token-for-generation/) | Learn | Python |
| 13 | [Transfusion: Autoregressive + Diffusion](phases/12-multimodal-ai/13-transfusion-autoregressive-diffusion/) | Build | Python |
| 14 | [Show-o Discrete Diffusion Unified Architecture](phases/12-multimodal-ai/14-show-o-discrete-diffusion-unified/) | Learn | Python |
| 15 | [Janus-Pro Decoupled Encoders](phases/12-multimodal-ai/15-janus-pro-decoupled-encoders/) | Build | Python |
| 16 | [MIO Any-to-Any Streaming](phases/12-multimodal-ai/16-mio-any-to-any-streaming/) | Learn | Python |
| 17 | [Video Language Temporal Grounding](phases/12-multimodal-ai/17-video-language-temporal-grounding/) | Build | Python |
| 18 | [Long Video with Million-Token Context](phases/12-multimodal-ai/18-long-video-million-token/) | Build | Python |
| 19 | [Audio Language Models: From Whisper to AF3](phases/12-multimodal-ai/19-audio-language-whisper-to-af3/) | Build | Python |
| 20 | [Omni Models: Thinker-Talker Streaming](phases/12-multimodal-ai/20-omni-models-thinker-talker/) | Build | Python |
| 21 | [Embodied VLA: RT-2, OpenVLA, π0, GR00T](phases/12-multimodal-ai/21-embodied-vlas-openvla-pi0-groot/) | Learn | Python |
| 22 | [Document and Diagram Understanding](phases/12-multimodal-ai/22-document-diagram-understanding/) | Build | Python |
| 23 | [ColPali Vision-Native Document RAG](phases/12-multimodal-ai/23-colpali-vision-native-rag/) | Build | Python |
| 24 | [Multimodal RAG and Cross-Modal Retrieval](phases/12-multimodal-ai/24-multimodal-rag-cross-modal/) | Build | Python |
| 25 | [Multimodal Agents and Computer Use (Capstone Project)](phases/12-multimodal-ai/25-multimodal-agents-computer-use/) | Build | Python |
</details>
<details id="phase-13">
<summary><b>Phase 13 — Tools and Protocols</b> <code>23 lessons</code> <em>The interface between AI and the real world.</em></summary>
<br/>
| # | Lesson | Type | Lang |
|:---:|--------|:----:|------|
| 01 | [The Tool Interface](phases/13-tools-and-protocols/01-the-tool-interface/) | Learn | Python |
| 02 | [Function Calling Deep Dive](phases/13-tools-and-protocols/02-function-calling-deep-dive/) | Build | Python |
| 03 | [Parallel and Streaming Tool Calls](phases/13-tools-and-protocols/03-parallel-and-streaming-tool-calls/) | Build | Python |
| 04 | [Structured Output](phases/13-tools-and-protocols/04-structured-output/) | Build | Python |
| 05 | [Tool Schema Design](phases/13-tools-and-protocols/05-tool-schema-design/) | Learn | Python |
| 06 | [MCP Fundamentals](phases/13-tools-and-protocols/06-mcp-fundamentals/) | Learn | Python |
| 07 | [Building an MCP Server](phases/13-tools-and-protocols/07-building-an-mcp-server/) | Build | Python |
| 08 | [Building an MCP Client](phases/13-tools-and-protocols/08-building-an-mcp-client/) | Build | Python |
| 09 | [MCP Transport Layer](phases/13-tools-and-protocols/09-mcp-transports/) | Learn | Python |
| 10 | [MCP Resources and Prompts](phases/13-tools-and-protocols/10-mcp-resources-and-prompts/) | Build | Python |
| 11 | [MCP Sampling](phases/13-tools-and-protocols/11-mcp-sampling/) | Build | Python |
| 12 | [MCP Roots and Elicitation](phases/13-tools-and-protocols/12-mcp-roots-and-elicitation/) | Build | Python |
| 13 | [MCP Async Tasks](phases/13-tools-and-protocols/13-mcp-async-tasks/) | Build | Python |
| 14 | [MCP Apps](phases/13-tools-and-protocols/14-mcp-apps/) | Build | Python |
| 15 | [MCP Security I — Tool Poisoning](phases/13-tools-and-protocols/15-mcp-security-tool-poisoning/) | Learn | Python |
| 16 | [MCP Security II — OAuth 2.1](phases/13-tools-and-protocols/16-mcp-security-oauth-2-1/) | Build | Python |
| 17 | [MCP Gateways and Registries](phases/13-tools-and-protocols/17-mcp-gateways-and-registries/) | Learn | Python |
| 18 | [Production-Ready MCP Authentication — DCR + JWKS on iii](phases/13-tools-and-protocols/18-mcp-auth-production/) | Build | Python |
| 19 | [A2A Protocol](phases/13-tools-and-protocols/19-a2a-protocol/) | Build | Python |
| 20 | [OpenTelemetry GenAI](phases/13-tools-and-protocols/20-opentelemetry-genai/) | Build | Python |
| 21 | [LLM Routing Layer](phases/13-tools-and-protocols/21-llm-routing-layer/) | Learn | Python |
| 22 | [Skills and Agent SDKs](phases/13-tools-and-protocols/22-skills-and-agent-sdks/) | Learn | Python |
| 23 | [Capstone Project — Tool Ecosystem](phases/13-tools-and-protocols/23-capstone-tool-ecosystem/) | Build | Python |
</details>
<details id="phase-14">
<summary><b>Phase 14 — Agent Engineering</b> <code>42 lessons</code> <em>Building agents from first principles — loops, memory, planning, frameworks, benchmarks, production, and workbench.</em></summary>
<br/>
# Tool List
| # | Lesson | Type | Lang |
|:---:|--------|:----:|------|
| 01 | [The Agent Loop](phases/14-agent-engineering/01-the-agent-loop/) | Build | Python |
| 02 | [ReWOO and Plan-and-Execute](phases/14-agent-engineering/02-rewoo-plan-and-execute/) | Build | Python |
| 03 | [Reflexion and Verbal Reinforcement Learning](phases/14-agent-engineering/03-reflexion-verbal-rl/) | Build | Python |
| 04 | [Tree of Thoughts and LATS](phases/14-agent-engineering/04-tree-of-thoughts-lats/) | Build | Python |
| 05 | [Self-Refine and CRITIC](phases/14-agent-engineering/05-self-refine-and-critic/) | Build | Python |
| 06 | [Tool Use and Function Calling](phases/14-agent-engineering/06-tool-use-and-function-calling/) | Build | Python |
| 07 | [Memory — Virtual Context and MemGPT](phases/14-agent-engineering/07-memory-virtual-context-memgpt/) | Build | Python |
| 08 | [Memory Blocks and Sleep-Time Compute](phases/14-agent-engineering/08-memory-blocks-sleep-time-compute/) | Build | Python |
| 09 | [Hybrid Memory — Mem0 Vector + Graph + KV](phases/14-agent-engineering/09-hybrid-memory-mem0/) | Build | Python |
| 10 | [Skill Libraries and Lifelong Learning — Voyager](phases/14-agent-engineering/10-skill-libraries-voyager/) | Build | Python |
| 11 | [Planning with HTN and Evolutionary Search](phases/14-agent-engineering/11-planning-htn-and-evolutionary/) | Build | Python |
| 12 | [Anthropic's Workflow Patterns](phases/14-agent-engineering/12-anthropic-workflow-patterns/) | Build | Python |
| 13 | [LangGraph — Stateful Graphs and Durable Execution](phases/14-agent-engineering/13-langgraph-stateful-graphs/) | Build | Python |
| 14 | [AutoGen v0.4 — Actor Model](phases/14-agent-engineering/14-autogen-actor-model/) | Build | Python |
| 15 | [CrewAI — Role-Based Crews and Processes](phases/14-agent-engineering/15-crewai-role-based-crews/) | Build | Python |
| 16 | [OpenAI Agents SDK — Handoffs, Guardrails, and Tracing](phases/14-agent-engineering/16-openai-agents-sdk/) | Build | Python |
| 17 | [Claude Agent SDK — Sub-Agents and Session Storage](phases/14-agent-engineering/17-claude-agent-sdk/) | Build | Python |
| 18 | [Agno and Mastra — Production-Grade Runtimes](phases/14-agent-engineering/18-agno-and-mastra-runtimes/) | Learn | Python |
| 19 | [Benchmarks — SWE-bench, GAIA, AgentBench](phases/14-agent-engineering/19-benchmarks-swebench-gaia/) | Learn | Python |
| 20 | [Benchmarks — WebArena and OSWorld](phases/14-agent-engineering/20-benchmarks-webarena-osworld/) | Learn | Python |
| 21 | [Operating Computers — Claude, OpenAI CUA, Gemini](phases/14-agent-engineering/21-computer-use-agents/) | Build | Python |
| 22 | [Voice Agents — Pipecat and LiveKit](phases/14-agent-engineering/22-voice-agents-pipecat-livekit/) | Build | Python |
| 23 | [OpenTelemetry GenAI Semantic Conventions](phases/14-agent-engineering/23-otel-genai-conventions/) | Build | Python |
| 24 | [Agent Observability — Langfuse, Phoenix, Opik](phases/14-agent-engineering/24-agent-observability-platforms/) | Learn | Python |
| 25 | [Multi-Agent Debate and Collaboration](phases/14-agent-engineering/25-multi-agent-debate/) | Build | Python |
| 26 | [Failure Modes — Why Agents Crash](phases/14-agent-engineering/26-failure-modes-agentic/) | Build | Python |
| 27 | [Prompt Injection and PVE Defense](phases/14-agent-engineering/27-prompt-injection-defense/) | Build | Python |
| 28 | [Orchestration Patterns — Supervisor, Swarm, Hierarchical](phases/14-agent-engineering/28-orchestration-patterns/) | Build | Python |
| 29 | [Production-Grade Runtimes — Queues, Events, Cron](phases/14-agent-engineering/29-production-runtimes/) | Learn | Python |
| 30 | [Eval-Driven Agent Development](phases/14-agent-engineering/30-eval-driven-agent-development/) | Build | Python |
| 31 | [Agent Workbench: Why Capable Models Still Fail](phases/14-agent-engineering/31-agent-workbench-why-models-fail/) | Learn | Python |
| 32 | [Minimal Agent Workbench](phases/14-agent-engineering/32-minimal-agent-workbench/) | Build | Python |
| 33 | [Writing Agent Instructions as Executable Constraints](phases/14-agent-engineering/33-instructions-as-executable-constraints/) | Build | Python |
| 34 | [Repository Memory and Persistent State](phases/14-agent-engineering/34-repo-memory-and-state/) | Build | Python |
| 35 | [Initialization Scripts for Agents](phases/14-agent-engineering/35-initialization-scripts/) | Build | Python |
| 36 | [Scope Contracts and Task Boundaries](phases/14-agent-engineering/36-scope-contracts/) | Build | Python |
| 37 | [Runtime Feedback Loops](phases/14-agent-engineering/37-runtime-feedback-loops/) | Build | Python |
| 38 | [Verification Gates](phases/14-agent-engineering/38-verification-gates/) | Build | Python |
| 39 | [Reviewer Agents: Separating Builders and Judges](phases/14-agent-engineering/39-reviewer-agent/) | Build | Python |
| 40 | [Multi-Session Handoffs](phases/14-agent-engineering/40-multi-session-handoff/) | Build | Python |
| 41 | [Running Workbenches on Real Repositories](phases/14-agent-engineering/41-workbench-for-real-repos/) | Build | Python |
| 42 | [Capstone Project: Delivering a Reusable Agent Workbench Package](phases/14-agent-engineering/42-agent-workbench-capstone/) | Build | Python |
Each workbench lesson (31-42) in Phase 14 comes with a `mission.md` file that provides a brief overview to the agent before it opens the full lesson documentation.
</details>
<details id="phase-15">
<summary><b>Phase 15 — Autonomous Systems</b> <code>22 lessons</code> <em>Long-horizon agents, self-improvement, and 2026 security tech stack.</em></summary>
<br/>
| # | Lesson | Type | Lang |
|:---:|--------|:----:|------|
| 01 | [From Chatbots to Long-Horizon Agents (METR)](phases/15-autonomous-systems/01-long-horizon-agents/) | Learn | Python |
| 02 | [STaR, V-STaR, Quiet-STaR: Self-Study Reasoning](phases/15-autonomous-systems/02-star-family-reasoning/) | Learn | Python |
| 03 | [AlphaEvolve: Evolutionary Coding Agents](phases/15-autonomous-systems/03-alphaevolve-evolutionary-coding/) | Learn | Python |
| 04 | [Darwin Gödel Machine: Self-Modifying Agents](phases/15-autonomous-systems/04-darwin-godel-machine/) | Learn | Python |
| 05 | [AI Scientist v2: Workshop-Level Research](phases/15-autonomous-systems/05-ai-scientist-v2/) | Learn | Python |
| 06 | [Automated Alignment Research (Anthropic AAR)](phases/15-autonomous-systems/06-automated-alignment-research/) | Learn | Python |
| 07 | [Recursive Self-Improvement: Capabilities vs Alignment](phases/15-autonomous-systems/07-recursive-self-improvement/) | Learn | Python |
| 08 | [Designing Bounded Self-Improvement](phases/15-autonomous-systems/08-bounded-self-improvement/) | Learn | Python |
| 09 | [Autonomous Coding Agent Landscape (SWE-bench, CodeAct)](phases/15-autonomous-systems/09-coding-agent-landscape/) | Learn | Python |
| 10 | [Claude Code's Permission Modes and Auto Modes](phases/15-autonomous-systems/10-claude-code-permission-modes/) | Learn | Python |
| 11 | [Browser Agents and Indirect Prompt Injection](phases/15-autonomous-systems/11-browser-agents/) | Learn | Python |
| 12 | [Durable Execution for Long-Running Agents](phases/15-autonomous-systems/12-durable-execution/) | Learn | Python |
| 13 | [Action Governors, Iteration Limits, and Cost Control](phases/15-autonomous-systems/13-cost-governors/) | Learn | Python |
| 14 | [Kill Switches, Canaries, and Token](phases/15-autonomous-systems/14-kill-switches-canaries/) | Learn | Python |
| 15 | [Human-in-the-Loop: Propose-Then-Commit](phases/15-autonomous-systems/15-propose-then-commit/) | Learn | Python |
| 16 | [Checkpoints and Rollbacks](phases/15-autonomous-systems/16-checkpoints-rollback/) | Learn | Python |
| 17 | [Constitutional AI and Rule Coverage](phases/15-autonomous-systems/17-constitutional-ai/) | Learn | Python |
| 18 | [Llama Guard and Input/Output Classification](phases/15-autonomous-systems/18-llama-guard/) | Learn | Python |
| 19 | [Anthropic's Responsible Scaling Policy v3.0](phases/15-autonomous-systems/19-anthropic-rsp/) | Learn | Python |
| 20 | [OpenAI Preparedness Framework and DeepMind FSF](phases/15-autonomous-systems/20-openai-preparedness-deepmind-fsf/) | Learn | Python |
| 21 | [METR Time Horizons and External Evaluation](phases/15-autonomous-systems/21-metr-external-evaluation/) | Learn | Python |
| 22 | [CAIS, CAISI, and Societal-Scale Risk](phases/15-autonomous-systems/22-cais-caisi-societal-risk/) | Learn | Python |
</details>
<details id="phase-16">
<summary><b>Phase 16 — Multi-Agent and Swarms</b> <code>25 lessons</code> <em>Coordination, emergence, and collective intelligence.</em></summary>
<br/>
| # | Lesson | Type | Lang |
|:---:|--------|:----:|------|
| 01 | [Why Multi-Agent](phases/16-multi-agent-and-swarms/01-why-multi-agent/) | Learn | TypeScript |
| 02 | [FIPA-ACL Heritage and Speech Acts](phases/16-multi-agent-and-swarms/02-fipa-acl-heritage/) | Learn | Python |
| 03 | [Communication Protocols](phases/16-multi-agent-and-swarms/03-communication-protocols/) | Build | TypeScript |
| 04 | [Primitive Model of Multi-Agent](phases/16-multi-agent-and-swarms/04-primitive-model/) | Learn | Python |
| 05 | [Supervisor / Orchestrator - Worker Pattern](phases/16-multi-agent-and-swarms/05-supervisor-orchestrator-pattern/) | Build | Python |
| 06 | [Hierarchical Architecture and Decomposition Drift](phases/16-multi-agent-and-swarms/06-hierarchical-architecture/) | Learn | Python |
| 07 | [Society of Mind and Multi-Agent Debate](phases/16-multi-agent-and-swarms/07-society-of-mind-debate/) | Build | Python |
| 08 | [Role Specialization - Planner / Critic / Executor / Verifier](phases/16-multi-agent-and-swarms/08-role-specialization/) | Build | Python |
| 09 | [Parallel Swarm and Networked Architecture](phases/16-multi-agent-and-swarms/09-parallel-swarm-networks/) | Build | Python |
| 10 | [Group Chat and Speaker Selection](phases/16-multi-agent-and-swarms/10-group-chat-speaker-selection/) | Build | Python |
| 11 | [Handoffs and Routines (Stateless Orchestration)](phases/16-multi-agent-and-swarms/11-handoffs-and-routines/) | Build | Python |
| 12 | [A2A - Agent to Agent Protocol](phases/16-multi-agent-and-swarms/12-a2a-protocol/) | Build | Python |
| 13 | [Shared Memory and Blackboard Pattern](phases/16-multi-agent-and-swarms/13-shared-memory-blackboard/) | Build | Python |
| 14 | [Consensus and Byzantine Fault Tolerance](phases/16-multi-agent-and-swarms/14-consensus-and-bft/) | Build | Python |
| 15 | [Voting, Self-Consistency, and Debate Topology](phases/16-multi-agent-and-swarms/15-voting-debate-topology/) | Build | Python |
| 16 | [Negotiation and Bargaining](phases/16-multi-agent-and-swarms/16-negotiation-bargaining/) | Build | Python |
| 17 | [Generative Agents and Emergent Simulation](phases/16-multi-agent-and-swarms/17-generative-agents-simulation/) | Build | Python |
| 18 | [Theory of Mind and Emergent Coordination](phases/16-multi-agent-and-swarms/18-theory-of-mind-coordination/) | Build | Python |
| 19 | [Swarm Optimization (PSO, ACO)](phases/16-multi-agent-and-swarms/19-swarm-optimization-pso-aco/) | Build | Python |
| 20 | [MARL - MADDPG, QMIX, MAPPO](phases/16-multi-agent-and-swarms/20-marl-maddpg-qmix-mappo/) | Learn | Python |
| 21 | [Agent Economies, Token Incentives, Reputation](phases/16-multi-agent-and-swarms/21-agent-economies/) | Learn | Python |
| 22 | [Production Scaling - Queues, Checkpoints, Persistence](phases/16-multi-agent-and-swarms/22-production-scaling-queues-checkpoints/) | Build | Python |
| 23 | [Failure Modes - MAST, Groupthink, Single Culture](phases/16-multi-agent-and-swarms/23-failure-modes-mast-groupthink/) | Learn | Python |
| 24 | [Evaluation and Coordination Benchmarks](phases/16-multi-agent-and-swarms/24-evaluation-coordination-benchmarks/) | Learn | Python |
| 25 | [Case Studies and 2026 State of the Art](phases/16-multi-agent-and-swarms/25-case-studies-2026-sota/) | Learn | Python |
</details>
<details id="phase-17">
<summary><b>Phase 17 — Infrastructure and Production</b> <code>28 lessons</code> <em>Deliver AI to the real world.</em></summary>
<br/>
| # | Lesson | Type | Lang |
|:---:|--------|:----:|------|
| 01 | [Managed LLM Platforms — Bedrock, Azure OpenAI, Vertex AI](phases/17-infrastructure-and-production/01-managed-llm-platforms/) | Learn | Python |
| 02 | [Inference Platform Economics — Fireworks, Together, Baseten, Modal](phases/17-infrastructure-and-production/02-inference-platform-economics/) | Learn | Python |
| 03 | [GPU Autoscaling on Kubernetes — Karpenter, KAI Scheduler](phases/17-infrastructure-and-production/03-gpu-autoscaling-kubernetes/) | Learn | Python |
| 04 | [vLLM Serving Internals — PagedAttention, Continuous Batching, Chunked Prefilling](phases/17-infrastructure-and-production/04-vllm-serving-internals/) | Learn | Python |
| 05 | [EAGLE-3 Speculative Decoding in Production](phases/17-infrastructure-and-production/05-eagle3-speculative-decoding/) | Learn | Python |
| 06 | [SGLang and RadixAttention for Prefix-Intensive Loads](phases/17-infrastructure-and-production/06-sglang-radixattention/) | Learn | Python |
| 07 | [TensorRT-LLM on Blackwell with FP8 and NVFP4](phases/17-infrastructure-and-production/07-tensorrt-llm-blackwell/) | Learn | Python |
| 08 | [Inference Metrics — TTFT, TPOT, ITL, Goodput, P99](phases/17-infrastructure-and-production/08-inference-metrics-goodput/) | Learn | Python |
| 09 | [Production Quantization — AWQ, GPTQ, GGUF, FP8, NVFP4](phases/17-infrastructure-and-production/09-production-quantization/) | Learn | Python |
| 10 | [Cold Start Mitigation for Serverless LLM](phases/17-infrastructure-and-production/10-cold-start-mitigation/) | Learn | Python |
| 11 | [Multi-Region LLM Serving and KV Cache Locality](phases/17-infrastructure-and-production/11-multi-region-kv-locality/) | Learn | Python |
| 12 | [Edge Inference — ANE, Hexagon, WebGPU, Jetson](phases/17-infrastructure-and-production/12-edge-inference/) | Learn | Python |
| 13 | [LLM Observability Tech Stack Selection](phases/17-infrastructure-and-production/13-llm-observability/) | Learn | Python |
| 14 | [Prompt Caching and Semantic Caching Economics](phases/17-infrastructure-and-production/14-prompt-semantic-caching/) | Learn | Python |
| 15 | [Batch API — 50% Discount as Industry Standard](phases/17-infrastructure-and-production/15-batch-apis/) | Learn | Python |
| 16 | [Model Routing as Cost-Reducing Primitive](phases/17-infrastructure-and-production/16-model-routing/) | Learn | Python |
| 17 | [Disaggregated Prefill/Decode — NVIDIA Dynamo and llm-d](phases/17-infrastructure-and-production/17-disaggregated-prefill-decode/) | Learn | Python |
| 18 | [vLLM Production Stack with LMCache KV Offloading](phases/17-infrastructure-and-production/18-vllm-production-stack-lmcache/) | Learn | Python |
| 19 | [AI Gateways — LiteLLM, Portkey, Kong, Bifrost](phases/17-infrastructure-and-production/19-ai-gateways/) | Learn | Python |
| 20 | [Shadow, Canary, and Progressive Deployment](phases/17-infrastructure-and-production/20-shadow-canary-progressive/) | Learn | Python |
| 21 | [A/B Testing LLM Features — GrowthBook and Statsig](phases/17-infrastructure-and-production/21-ab-testing-llm-features/) | Learn | Python |
| 22 | [Load Testing LLM APIs — k6, LLMPerf, GenAI-Perf](phases/17-infrastructure-and-production/22-load-testing-llm-apis/) | Build | Python |
| 23 | [SRE for AI — Multi-Agent Incident Response](phases/17-infrastructure-and-production/23-sre-for-ai/) | Learn | Python |
| 24 | [Chaos Engineering for LLM Production](phases/17-infrastructure-and-production/24-chaos-engineering-llm/) | Learn | Python |
| 25 | [Security — Secrets, PII Redaction, Audit Logs](phases/17-infrastructure-and-production/25-security-secrets-audit/) | Learn | Python |
| 26 | [Compliance — SOC 2, HIPAA, GDPR, EU AI Act, ISO 42001](phases/17-infrastructure-and-production/26-compliance-frameworks/) | Learn | Python |
| 27 | [FinOps for LLM — Unit Economics and Multi-Tenant Attribution](phases/17-infrastructure-and-production/27-finops-llms/) | Learn | Python |
| 28 | [Self-Hosted Serving Selection — llama.cpp, Ollama, TGI, vLLM, SGLang](phases/17-infrastructure-and-production/28-self-hosted-serving-selection/) | Learn | Python |
</details>
<details id="phase-18">
<summary><b>Phase 18 — Ethics, Safety, and Alignment</b> <code>30 lessons</code> <em>Build AI that benefits humanity. This is not optional.</em></summary>
<br/>
# Tool List
| # | Lesson | Type | Lang |
|:---:|--------|:----:|------|
| 01 | [Instruction Following as an Alignment Signal](phases/18-ethics-safety-alignment/01-instruction-following-alignment-signal/) | Learn | Python |
| 02 | [Reward Hacking and Goodhart's Law](phases/18-ethics-safety-alignment/02-reward-hacking-goodhart/) | Learn | Python |
| 03 | [Direct Preference Optimization Family](phases/18-ethics-safety-alignment/03-direct-preference-optimization-family/) | Learn | Python |
| 04 | [Sycophancy: Amplification Effects of RLHF](phases/18-ethics-safety-alignment/04-sycophancy-rlhf-amplification/) | Learn | Python |
| 05 | [Constitutional AI and RLAIF](phases/18-ethics-safety-alignment/05-constitutional-ai-rlaif/) | Learn | Python |
| 06 | [Mesa-Optimization and Deceptive Alignment](phases/18-ethics-safety-alignment/06-mesa-optimization-deceptive-alignment/) | Learn | Python |
| 07 | [Sleeper Agents: Persistent Deception](phases/18-ethics-safety-alignment/07-sleeper-agents-persistent-deception/) | Learn | Python |
| 08 | [In-Context Scheming in Frontier Models](phases/18-ethics-safety-alignment/08-in-context-scheming-frontier-models/) | Learn | Python |
| 09 | [Alignment Faking](phases/18-ethics-safety-alignment/09-alignment-faking/) | Learn | Python |
| 10 | [AI Control: Safety Even Under Subversion](phases/18-ethics-safety-alignment/10-ai-control-subversion/) | Learn | Python |
| 11 | [Scalable Oversight and Weak-to-Strong](phases/18-ethics-safety-alignment/11-scalable-oversight-weak-to-strong/) | Learn | Python |
| 12 | [Red Teaming: PAIR and Automated Attacks](phases/18-ethics-safety-alignment/12-red-teaming-pair-automated-attacks/) | Build | Python |
| 13 | [Many-Shot Jailbreaking](phases/18-ethics-safety-alignment/13-many-shot-jailbreaking/) | Learn | Python |
| 14 | [ASCII Art and Visual Jailbreaks](phases/18-ethics-safety-alignment/14-ascii-art-visual-jailbreaks/) | Build | Python |
| 15 | [Indirect Prompt Injection](phases/18-ethics-safety-alignment/15-indirect-prompt-injection/) | Build | Python |
| 16 | [Red Team Tooling: Garak, Llama Guard, PyRIT](phases/18-ethics-safety-alignment/16-red-team-tooling-garak-llamaguard-pyrit/) | Build | Python |
| 17 | [WMDP and Dual-Use Capability Evaluation](phases/18-ethics-safety-alignment/17-wmdp-dual-use-evaluation/) | Learn | Python |
| 18 | [Frontier Safety Frameworks: RSP, PF, FSF](phases/18-ethics-safety-alignment/18-frontier-safety-frameworks-rsp-pf-fsf/) | Learn | Python |
| 19 | [Model Welfare Research](phases/18-ethics-safety-alignment/19-model-welfare-research/) | Learn | Python |
| 20 | [Bias and Representational Harm](phases/18-ethics-safety-alignment/20-bias-representational-harm/) | Build | Python |
| 21 | [Fairness Criteria: Group, Individual, Counterfactual](phases/18-ethics-safety-alignment/21-fairness-criteria-group-individual-counterfactual/) | Learn | Python |
| 22 | [Differential Privacy for LLMs](phases/18-ethics-safety-alignment/22-differential-privacy-for-llms/) | Build | Python |
| 23 | [Watermarking: SynthID, Stable Signature, C2PA](phases/18-ethics-safety-alignment/23-watermarking-synthid-stable-signature-c2pa/) | Build | Python |
| 24 | [Regulatory Frameworks: EU, US, UK, Korea](phases/18-ethics-safety-alignment/24-regulatory-frameworks-eu-us-uk-korea/) | Learn | Python |
| 25 | [EchoLeak and CVEs for AI](phases/18-ethics-safety-alignment/25-echoleak-cves-for-ai/) | Learn | Python |
| 26 | [Model Cards, System Cards, and Dataset Cards](phases/18-ethics-safety-alignment/26-model-system-dataset-cards/) | Build | Python |
| 27 | [Data Provenance and Training Data Governance](phases/18-ethics-safety-alignment/27-data-provenance-training-governance/) | Learn | Python |
| 28 | [Alignment Research Ecosystem: MATS, Redwood, Apollo, METR](phases/18-ethics-safety-alignment/28-alignment-research-ecosystem/) | Learn | Python |
| 29 | [Moderation Systems: OpenAI, Perspective, Llama Guard](phases/18-ethics-safety-alignment/29-moderation-systems-openai-perspective-llamaguard/) | Build | Python |
| 30 | [Dual-Use Risk: Cyber, Bio, Chemical, Nuclear](phases/18-ethics-safety-alignment/30-dual-use-risk-cyber-bio-chem-nuclear/) | Learn | Python |
</details>
<details id="phase-19">
<summary><b>Phase 19 — Comprehensive Projects</b> <code>85 projects</code> <em>End-to-end deliverables for 2026, each 20-40 hours.</em></summary>
<br/>
# Tool List
| # | Project | Combines | Lang |
|:---:|---------|----------|------|
| 01 | [Terminal Native Coding Agent](phases/19-capstone-projects/01-terminal-native-coding-agent/) | P0 P5 P7 P10 P11 P13 P14 P15 P17 P18 | Python |
| 02 | [RAG over Codebase](phases/19-capstone-projects/02-rag-over-codebase/) | P5 P7 P11 P13 P17 | Python |
| 03 | [Real-time Voice Assistant (ASR → LLM → TTS)](phases/19-capstone-projects/03-realtime-voice-assistant/) | P6 P7 P11 P13 P14 P17 | Python |
| 04 | [Multimodal Document QA (Vision-centric)](phases/19-capstone-projects/04-multimodal-document-qa/) | P4 P5 P7 P11 P12 P17 | Python |
| 05 | [Autonomous Research Agent (AI-Scientist level)](phases/19-capstone-projects/05-autonomous-research-agent/) | P0 P2 P3 P7 P10 P14 P15 P16 P18 | Python |
| 06 | [DevOps Troubleshooting Agent for Kubernetes](phases/19-capstone-projects/06-devops-troubleshooting-agent/) | P11 P13 P14 P15 P17 P18 | Python |
| 07 | [End-to-end Fine-tuning Pipeline](phases/19-capstone-projects/07-end-to-end-fine-tuning-pipeline/) | P2 P3 P7 P10 P11 P17 P18 | Python |
| 08 | [Production-grade RAG Chatbot (Regulated Verticals)](phases/19-capstone-projects/08-production-rag-chatbot/) | P5 P7 P11 P12 P17 P18 | Python |
| 09 | [Code Migration Agent (Repository-level Upgrade)](phases/19-capstone-projects/09-code-migration-agent/) | P5 P7 P11 P13 P14 P15 P17 | Python |
| 10 | [Multi-agent Software Engineering Team](phases/19-capstone-projects/10-multi-agent-software-team/) | P11 P13 P14 P15 P16 P17 | Python |
| 11 | [LLM Observability & Eval Dashboard](phases/19-capstone-projects/11-llm-observability-dashboard/) | P11 P13 P17 P18 | Python |
| 12 | [Video Understanding Pipeline (Scene → QA)](phases/19-capstone-projects/12-video-understanding-pipeline/) | P4 P6 P7 P11 P12 P17 | Python |
| 13 | [MCP Server with Registry](phases/19-capstone-projects/13-mcp-server-with-registry/) | P11 P13 P14 P17 P18 | Python |
| 14 | [Speculative Decoding Inference Server](phases/19-capstone-projects/14-speculative-decoding-server/) | P3 P7 P10 P17 | Python |
| 15 | [Constitutional Safety Harness + Red Team Range](phases/19-capstone-projects/15-constitutional-safety-harness/) | P10 P11 P13 P14 P18 | Python |
| 16 | [GitHub Issue to PR Autonomous Agent](phases/19-capstone-projects/16-github-issue-to-pr-agent/) | P11 P13 P14 P15 P17 | Python |
| 17 | [Personal AI Tutor (Adaptive, Multimodal)](phases/19-capstone-projects/17-personal-ai-tutor/) | P5 P6 P11 P12 P14 P17 P18 | Python |
| 20 | [Agent Harness Loop Contract](phases/19-capstone-projects/20-agent-harness-loop-contract/) | A. Agent harness | Python |
| 21 | [Tool Registry with Schema Validation](phases/19-capstone-projects/21-tool-registry-schema-validation/) | A. Agent harness | Python |
| 22 | [JSON-RPC 2.0 over stdio with Line Separator](phases/19-capstone-projects/22-jsonrpc-stdio-transport/) | A. Agent harness | Python |
| 23 | [Function Call Dispatcher](phases/19-capstone-projects/23-function-call-dispatcher/) | A. Agent harness | Python |
| 24 | [Plan-Execute Control Flow](phases/19-capstone-projects/24-plan-execute-control-flow/) | A. Agent harness | Python |
| 25 | [Verification Gates & Observation Budget](phases/19-capstone-projects/25-verification-gates-observation-budget/) | A. Agent harness | Python |
| 26 | [Sandbox Runner with Denylist & Path Jail](phases/19-capstone-projects/26-sandbox-runner-denylist/) | A. Agent harness | Python |
| 27 | [Eval Harness with Fixture Tasks](phases/19-capstone-projects/27-eval-harness-fixture-tasks/) | A. Agent harness | Python |
| 28 | [Observability with OTel GenAI Span & Prometheus](phases/19-capstone-projects/28-observability-otel-traces/) | A. Agent harness | Python |
| 29 | [End-to-end Coding Agent Demo](phases/19-capstone-projects/29-end-to-end-coding-task-demo/) | A. Agent harness | Python |
| 30 | [BPE Tokenizer from Scratch](phases/19-capstone-projects/30-bpe-tokenizer-from-scratch/) | B. NLP LLM | Python |
| 31 | [Tokenized Dataset with Sliding Window](phases/19-capstone-projects/31-tokenized-dataset-sliding-window/) | B. NLP LLM | Python |
| 32 | [Token & Positional Embeddings](phases/19-capstone-projects/32-token-positional-embeddings/) | B. NLP LLM | Python |
| 33 | [Multi-Head Self-Attention](phases/19-capstone-projects/33-multihead-self-attention/) | B. NLP LLM | Python |
| 34 | [Transformer Block from Scratch](phases/19-capstone-projects/34-transformer-block/) | B. NLP LLM | Python |
| 35 | [GPT Model Assembly](phases/19-capstone-projects/35-gpt-model-assembly/) | B. NLP LLM | Python |
| 36 | [Training Loop & Evaluation](phases/19-capstone-projects/36-training-loop-eval/) | B. NLP LLM | Python |
| 37 | [Loading Pre-trained Weights](phases/19-capstone-projects/37-loading-pretrained-weights/) | B. NLP LLM | Python |
| 38 | [Classification Finetuning via Head Replacement](phases/19-capstone-projects/38-classifier-finetuning/) | B. NLP LLM | Python |
| 39 | [Instruction Tuning via SFT](phases/19-capstone-projects/39-instruction-tuning-sft/) | B. NLP LLM | Python |
| 40 | [DPO from Scratch](phases/19-capstone-projects/40-dpo-from-scratch/) | B. NLP LLM | Python |
| 41 | [Complete Evaluation Pipeline](phases/19-capstone-projects/41-eval-pipeline/) | B. NLP LLM | Python |
| 42 | [Large Corpus Downloader](phases/19-capstone-projects/42-large-corpus-downloader/) | C. End-to-end Training | Python |
| 43 | [HDF5 Tokenized Corpus](phases/19-capstone-projects/43-hdf5-tokenized-corpus/) | C. End-to-end Training | Python |
| 44 | [Cosine LR Schedule with Linear Warmup](phases/19-capstone-projects/44-cosine-lr-warmup/) | C. End-to-end Training | Python |
| 45 | [Gradient Clipping & Mixed Precision Training](phases/19-capstone-projects/45-gradient-clipping-amp/) | C. End-to-end Training | Python |
| 46 | [Gradient Accumulation](phases/19-capstone-projects/46-gradient-accumulation/) | C. End-to-end Training | Python |
| 47 | [Checkpoint Saving & Resuming](phases/19-capstone-projects/47-checkpoint-save-resume/) | C. End-to-end Training | Python |
| 48 | [Distributed Training with FSDP & DDP](phases/19-capstone-projects/48-distributed-fsdp-ddp/) | C. End-to-end Training | Python |
| 49 | [Language Model Evaluation Harness](phases/19-capstone-projects/49-lm-eval-harness/) | C. End-to-end Training | Python |
| 50 | [Hypothesis Generator](phases/19-capstone-projects/50-hypothesis-generator/) | D. Autonomous Research | Python |
| 51 | [Literature Retrieval](phases/19-capstone-projects/51-literature-retrieval/) | D. Autonomous Research | Python |
| 52 | [Experiment Runner](phases/19-capstone-projects/52-experiment-runner/) | D. Autonomous Research | Python |
| 53 | [Result Evaluator](phases/19-capstone-projects/53-result-evaluator/) | D. Autonomous Research | Python |
| 54 | [Paper Writer](phases/19-capstone-projects/54-paper-writer/) | D. Autonomous Research | Python |
| 55 | [Critic Loop](phases/19-capstone-projects/55-critic-loop/) | D. Autonomous Research | Python |
| 56 | [Iteration Scheduler](phases/19-capstone-projects/56-iteration-scheduler/) | D. Autonomous Research | Python |
| 57 | [End-to-end Research Demo](phases/19-capstone-projects/57-end-to-end-research-demo/) | D. Autonomous Research | Python |
| 58 | [Vision Encoder Patching](phases/19-capstone-projects/58-vision-encoder-patches/) | E. Multimodal | Python |
| 59 | [Vision Transformer Encoder (ViT)](phases/19-capstone-projects/59-vit-transformer/) | E. Multimodal | Python |
| 60 | [Modal Alignment with Projection Layer](phases/19-capstone-projects/60-projection-layer-modality-align/) | E. Multimodal | Python |
| 61 | [Cross-Attention Fusion](phases/19-capstone-projects/61-cross-attention-fusion/) | E. Multimodal | Python |
| 62 | [Vision-Language Pretraining](phases/19-capstone-projects/62-vision-language-pretraining/) | E. Multimodal | Python |
| 63 | [Multimodal Evaluation](phases/19-capstone-projects/63-multimodal-eval/) | E. Multimodal | Python |
| 64 | [Chunking Strategies](phases/19-capstone-projects/64-chunking-strategies-advanced/) | F. Advanced RAG | Python |
| 65 | [Hybrid Retrieval with BM25 & Dense Embedding](phases/19-capstone-projects/65-hybrid-retrieval-bm25-dense/) | F. Advanced RAG | Python |
| 66 | [Cross-Encoder Reranker](phases/19-capstone-projects/66-reranker-cross-encoder/) | F. Advanced RAG | Python |
| 67 | [Query Rewriting: HyDE, Multi-Query & Decomposition](phases/19-capstone-projects/67-query-rewriting-hyde/) | F. Advanced RAG | Python |
| 68 | [RAG Evaluation: Precision, Recall, MRR, nDCG, etc.](phases/19-capstone-projects/68-rag-eval-precision-recall/) | F. Advanced RAG | Python |
| 69 | [End-to-end RAG System](phases/19-capstone-projects/69-end-to-end-rag-system/) | F. Advanced RAG | Python |
| 70 | [Task Specification Format](phases/19-capstone-projects/70-task-spec-format/) | G. Evaluation System | Python |
| 71 | [Classical Evaluation Metrics](phases/19-capstone-projects/71-classical-metrics/) | G. Evaluation System | Python |
| 72 | [Code Execution Evaluation Metrics](phases/19-capstone-projects/72-code-exec-metric/) | G. Evaluation System | Python |
| 73 | [Perplexity & Calibration](phases/19-capstone-projects/73-perplexity-calibration/) | G. Evaluation System | Python |
| 74 | [Leaderboard Aggregation](phases/19-capstone-projects/74-leaderboard-aggregation/) | G. Evaluation System | Python |
| 75 | [End-to-end Evaluation Runner](phases/19-capstone-projects/75-end-to-end-eval-runner/) | G. Evaluation System | Python |
| 76 | [Collective Communication from Scratch](phases/19-capstone-projects/76-collective-ops-from-scratch/) | H. Distributed Training | Python |
| 77 | [Data Parallelism with DDP](phases/19-capstone-projects/77-data-parallel-ddp/) | H. Distributed Training | Python |
| 78 | [ZeRO Optimizer State Sharding](phases/19-capstone-projects/78-zero-parameter-sharding/) | H. Distributed Training | Python |
| 79 | [Pipeline Parallelism & Bubble Analysis](phases/19-capstone-projects/79-pipeline-parallel/) | H. Distributed Training | Python |
| 80 | [Sharded Checkpointing & Atomic Recovery](phases/19-capstone-projects/80-checkpoint-sharded-resume/) | H. Distributed Training | Python |
| 81 | [End-to-end Distributed Training](phases/19-capstone-projects/81-end-to-end-distributed-train/) | H. Distributed Training | Python |
| 82 | [Jailbreak Taxonomy](phases/19-capstone-projects/82-jailbreak-taxonomy/) | I. Safety Harness | Python |
# Tool List
| 83 | [Prompt Injection Detector](phases/19-capstone-projects/83-prompt-injection-detector/) | I. Safety Guardrails | Python |
| 84 | [Refusal Evaluation](phases/19-capstone-projects/84-refusal-evaluation/) | I. Safety Guardrails | Python |
| 85 | [Content Classifier Integration](phases/19-capstone-projects/85-content-classifier-integration/) | I. Safety Guardrails | Python |
| 86 | [Constitutional Rules Engine](phases/19-capstone-projects/86-constitutional-rules-engine/) | I. Safety Guardrails | Python |
| 87 | [End-to-End Safety Gate](phases/19-capstone-projects/87-end-to-end-safety-gate/) | I. Safety Guardrails | Python |
</details>
```
░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒
```
## Toolbox
Each lesson produces a reusable artifact. By the end, you'll have:
```
outputs/
├── prompts/ Prompt templates covering every type of AI task
└── skills/ SKILL.md files for AI coding agents
```
Install using `npx skills add`. Integrate them into Claude, Cursor, Codex, OpenClaw, Hermes,
or any agent that reads SKILL.md / AGENTS.md directories. They're real, not homework.
### Equip Your Agent with All Course Skills
The repository delivers 388 skills and 99 prompts under `phases/**/outputs/`.
**Recommended: Install via [skills.sh](https://skills.sh).** No cloning, no Python,
automatic detection of your agent's skill directory:
```bash
npx skills add fancyboi999/ai-engineering-from-scratch-zh # All skills
npx skills add fancyboi999/ai-engineering-from-scratch-zh --skill agent-loop # Single skill
npx skills add fancyboi999/ai-engineering-from-scratch-zh --phase 14 # Single phase
```
`skills` writes to the directory your agent actually reads: `.claude/skills/`, `.cursor/skills/`,
`.codex/skills/`, OpenClaw's skills folder, Hermes's bundle path, or any tool that recognizes SKILL.md.
One command, covering all agents.
**Advanced: Use `scripts/install_skills.py` for offline / custom layouts.** Requires cloning the repository.
Useful when you need to filter by tags, dry-run, or non-default layouts:
```bash
python3 scripts/install_skills.py <target> # All skills, default --layout skills (nested)
python3 scripts/install_skills.py <target> --layout skills # Same as above, explicit
python3 scripts/install_skills.py <target> --type all # Skills + prompts + agent
python3 scripts/install_skills.py <target> --phase 14 # Install one phase
python3 scripts/install_skills.py <target> --tag rag # Filter by tag
python3 scripts/install_skills.py <target> --layout flat # Flat file layout
python3 scripts/install_skills.py <target> --dry-run # Preview only, no writes
python3 scripts/install_skills.py <target> --force # Overwrite existing files
```
`<target>` is your agent's skill directory (e.g.,
`~/.claude/skills/`, `~/.cursor/skills/`, `~/.config/openclaw/skills/`,
`.skills/`, or any path your agent reads).
By default, the script refuses to overwrite existing targets, listing conflicts and exiting with code 1.
Use `--dry-run` to preview conflicts or `--force` to overwrite. Each non-dry-run run writes a `manifest.json`
in the target, listing the complete inventory by type and phase. Choose a layout your agent supports:
| `--layout` | Write Path |
|---|---|
| `skills` | `<target>/<name>/SKILL.md` (nested convention, supported by Claude / Cursor / Codex / OpenClaw / Hermes) |
| `by-phase` | `<target>/phase-NN/<name>.md` |
| `flat` | `<target>/<name>.md` |
### Install Agent Workbench into Your Own Repository
The Phase 14 capstone project delivers a reusable Agent Workbench package (AGENTS.md, schema,
init / verify / handoff scripts). Scaffold it into any repository with:
```bash
python3 scripts/scaffold_workbench.py path/to/your-repo # Full package + seed files
python3 scripts/scaffold_workbench.py path/to/your-repo --minimal # Skip docs/
python3 scripts/scaffold_workbench.py path/to/your-repo --dry-run # Preview only
python3 scripts/scaffold_workbench.py path/to/your-repo --force # Overwrite existing files
```
You'll get seven wired-up workbench interfaces, a starter `task_board.json`,
and a fresh `agent_state.json` with `schema_version: 1`. From here: edit tasks,
edit `AGENTS.md`, run `scripts/init_agent.py`, and hand off contracts to your agent. The package's source is in
`phases/14-agent-engineering/42-agent-workbench-capstone/outputs/agent-workbench-pack/`.
### Course Data and Lesson Count Verification
`site/build.js` parses READMEs, ROADMAP, and each lesson's `docs/zh.md` to generate course data (phases, lessons, glossary, artifacts) in `site/data.js`.
Counts are based on the **file system**.
```bash
node site/build.js # Generate site/data.js (+ sitemap.xml / llms.txt)
node site/build.js --check # Verify lesson count consistency only, no file writes
```
`--check` verifies counts against the on-disk lesson directory, ensuring README tables, badges, prose, phase headers,
and ROADMAP totals match. Any discrepancies exit with code 1. A GitHub Action (`.github/workflows/build.yml`)
runs the build + this check on every PR, blocking lesson count drift (caught 435, 498 vs 503).
When adding lessons, update the README + ROADMAP tables and phase headers; site templates' counts are synced automatically by `build.js`.
> Note: Upstream uses `scripts/build_catalog.py` + `catalog.json` + `.github/workflows/curriculum.yml`
> for the same purpose, but those scripts hardcode `docs/en.md` + English README regex, incompatible with this Chinese translation repo.
### Smoke Check Every Lesson's Python Code
`scripts/lesson_run.py` compiles every `.py` file in each lesson's `code/` directory, byte-for-byte.
The default mode only checks syntax — no execution, no API keys, no heavy ML dependencies. It catches common contributor-introduced regressions (indentation errors, f-string issues, accidental changes).
```bash
python3 scripts/lesson_run.py # Syntax check entire course
python3 scripts/lesson_run.py --phase 14 # Check one phase only
python3 scripts/lesson_run.py --json # Output JSON report to stdout
python3 scripts/lesson_run.py --strict # Exit 1 on any lesson failure
python3 scripts/lesson_run.py --execute # Actually run, 10-second timeout per lesson
```
`--execute` runs each lesson's `code/main.py` (or the first `.py` file), with a 10-second timeout.
Lessons with `# requires: pkg1, pkg2` comments (listing non-stdlib dependencies) are skipped, marked as `needs <deps>`.
This script is optional and not integrated into CI.
Pure Python 3.10+. Set `LINK_CHECK_SKIP=domain1,domain2` to override the default skip list
(`twitter.com`, `x.com`, `linkedin.com`, `instagram.com`, `medium.com` — domains that block automated HEAD/GET requests).
## Where to Start
| Your Background | Start Here | Estimated Time |
|---|---|---|
| New to programming and AI | Phase 0 — Setup and Toolchain | ~306 hours |
| Python-savvy, new to ML | Phase 1 — Math Foundations | ~270 hours |
| Familiar with ML, new to deep learning | Phase 3 — Core Deep Learning | ~200 hours |
| Know deep learning, want to learn LLMs and agents | Phase 10 — LLM Implementation from Scratch | ~100 hours |
| Seasoned engineer, only wants agent engineering | Phase 14 — Agent Engineering | ~60 hours |
```
░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒
```
## Why This Matters Now
<table>
<tr>
<th align="left" width="50%"><sub>FIG_003 · A</sub><br/><b>THE INDUSTRY SIGNAL</b></th>
<th align="left" width="50%"><sub>FIG_003 · B</sub><br/><b>FOUNDATIONAL PAPERS COVERED</b></th>
</tr>
<tr>
<td valign="top">
> *"The hottest new programming language is English."*<br/>
> — **Andrej Karpathy** ([tweet](https://x.com/karpathy/status/1617979122625712128))
> *"Software engineering is being rewritten before our eyes."*<br/>
> — **Boris Cherny**, creator of Claude Code
> *"Models will only get stronger. The skill that will compound is **knowing what to build**."*<br/>
> — Industry consensus, 2026
</td>
<td valign="top">
- *Attention Is All You Need* — Vaswani et al., 2017 → [Phase 7](#phase-7)
- *Language Models are Few-Shot Learners* (GPT-3) → [Phase 10](#phase-10)
- *Denoising Diffusion Probabilistic Models* → [Phase 8](#phase-8)
- *InstructGPT / RLHF* → [Phase 10](#phase-10)
- *Direct Preference Optimization* → [Phase 10](#phase-10)
- *Chain-of-Thought Prompting* → [Phase 11](#phase-11)
- *ReAct: Reasoning + Acting in LLMs* → [Phase 14](#phase-14)
- *Model Context Protocol* — Anthropic → [Phase 13](#phase-13)
</td>
</tr>
</table>
```
░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒
```
## Contributing
| Goal | Read |
|---|---|
| Contribute a lesson or fix | [CONTRIBUTING.md](CONTRIBUTING.md) |
| Fork for your team or school | [FORKING.md](FORKING.md) |
| Lesson template | [LESSON_TEMPLATE.md](LESSON_TEMPLATE.md) |
| Track progress | [ROADMAP.md](ROADMAP.md) |
| Glossary | [glossary/terms.md](glossary/terms.md) |
| Code of Conduct | [CODE_OF_CONDUCT.md](CODE_OF_CONDUCT.md) |
Before submitting a lesson, run the invariant checks:
```bash
python3 scripts/audit_lessons.py # Entire course
python3 scripts/audit_lessons.py --phase 14 # Single phase
python3 scripts/audit_lessons.py --json # CI-friendly output
```
Exit code non-zero if any rule fails. Rules (L001–L010) verify directory structure, `docs/zh.md` existence,
H1 presence, non-empty `code/`, `quiz.json` schema (rejecting old #102-style `q/choices/answer` keys),
and relative links in lesson docs.
## Star History
<a href="https://star-history.com/#fancyboi999/ai-engineering-from-scratch-zh&Date">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=fancyboi999/ai-engineering-from-scratch-zh&type=Date&theme=dark">
<img alt="Star history" src="https://api.star-history.com/svg?repos=fancyboi999/ai-engineering-from-scratch-zh&type=Date" width="100%">
</picture>
</a>
If this guide helped you, star the repository. This keeps the project going.
## License
MIT. Use it as you like — fork, teach, sell, deliver. Attribution is appreciated but not required.
Maintained by [Rohit Ghumare](https://github.com/rohitg00) and community.
<sub>
<a href="https://aieng-zh.cn">aieng-zh.cn</a> ·
<a href="https://github.com/fancyboi999/ai-engineering-from-scratch-zh/issues/new/choose">Report / Suggest</a>
</sub>
Connection Info
You Might Also Like
everything-claude-code
Complete Claude Code configuration collection - agents, skills, hooks,...
markitdown
MarkItDown-MCP is a lightweight server for converting URIs to Markdown.
cc-switch
All-in-One Assistant for Claude Code, Codex & Gemini CLI across platforms.
servers
Model Context Protocol Servers
servers
Model Context Protocol Servers
Time
A Model Context Protocol server for time and timezone conversions.