rohitg00/ai-engineering-from-scratch — stars, momentum and ranking

AI Engineering from Scratch

Implement model internals, retrieval pipelines, and agent runtimes. Test them, inspect failures, and keep the code and evaluation results.

Start learning · Choose a path · Try a lab · Build a project · Browse the curriculum

Free, open source, MIT. Learn on the website, with a coding agent, or by running local code.

528 lessons. 20 phases. Python, TypeScript, Rust, Julia.

Read in your language

🇬🇧 English · 🇨🇳 简体中文 · 🇹🇼 繁體中文（台灣） · 🇯🇵 日本語 · 🇰🇷 한국어 · 🇵🇹 Português · 🇧🇷 Português (Brasil) · 🇪🇸 Español · 🇩🇪 Deutsch · 🇫🇷 Français · 🇮🇹 Italiano · 🇳🇱 Nederlands · 🇵🇱 Polski · 🇨🇿 Čeština · 🇷🇴 Română · 🇭🇺 Magyar · 🇬🇷 Ελληνικά · 🇸🇪 Svenska · 🇩🇰 Dansk · 🇳🇴 Norsk · 🇫🇮 Suomi · 🇷🇺 Русский · 🇺🇦 Українська · 🇹🇷 Türkçe · 🇮🇱 עברית · 🇸🇦 العربية · 🇮🇷 فارسی · 🇮🇳 हिन्दी · 🇧🇩 বাংলা · 🇵🇰 اردو · 🇹🇭 ไทย · 🇻🇳 Tiếng Việt · 🇮🇩 Bahasa Indonesia · 🇵🇭 Tagalog

Learning paths

Route	Starting lesson
Model foundations	Setup and tooling
LLM systems	Prompt engineering
Agents and delivery	The agent loop

Compare career paths · Prerequisites and study time

Gradient descent

Twenty starting points follow gradient descent on a quadratic loss. The graph shows their positions and mean loss after each update.

Adjust the learning rate in the lesson · Compare GD, momentum, and Adam in code

Projects

Three projects with staged starters, reference implementations, and local graders. Run commands from the repository root after setup. Starters fail until you implement the stages.

01 · Retrieval Evaluation Lab · Python · Ranking metrics and regression checks

A candidate improves mean NDCG while one query ranks its most relevant evidence lower. Build a query-by-query comparison that reports the regression and can fail a release check.

Use Python 3.10+. Review RAG and model evaluation. Implement ranking validation, precision and recall, rank-sensitive metrics, then system comparison.

python3 scripts/project_test.py retrieval-evaluation-lab \
  --init learning-artifacts/retrieval-evaluation-lab
python3 scripts/project_test.py retrieval-evaluation-lab \
  --stage 1 --path learning-artifacts/retrieval-evaluation-lab --strict
python3 scripts/project_test.py retrieval-evaluation-lab \
  --all --path learning-artifacts/retrieval-evaluation-lab --strict

Keep: a reproducible comparison with per-query deltas and the judgments used to score them. Metrics describe those judgments; they do not establish answer correctness.

Start the project · Inspect the reference · Run on your own inputs

02 · Agent Trace Debugger · TypeScript · Trace parsing and timing

A supplied trace still takes 100 ms, but total token usage rises by 200 and one span starts failing. Separate overlapping child work from parent execution time, then produce a report that exposes the change.

Use Node.js 22.18+ and Python 3 for the grader. Implement JSONL parsing, parent validation, interval arithmetic, then an inspectable timeline.

python3 scripts/project_test.py agent-trace-debugger \
  --init learning-artifacts/agent-trace-debugger
python3 scripts/project_test.py agent-trace-debugger \
  --stage 1 --path learning-artifacts/agent-trace-debugger --strict
python3 scripts/project_test.py agent-trace-debugger \
  --all --path learning-artifacts/agent-trace-debugger --strict

Keep: the input trace, an HTML timeline, and a JSON regression report. Preserve exclusive per-span token counts so parent and child usage are not counted twice.

Start the project · Inspect the reference · Explore timing interactively

03 · Tool Call Firewall · Rust · Role checks and approval receipts

A write changes after review, or an approval is replayed. Validate the call envelope, check the caller's role and path, then consume an approval bound to the exact request and content.

Use Rust and Python 3.10+. Review tool schema design and security boundaries. The caller application supplies identity; the model proposes an operation.

python3 scripts/project_test.py tool-call-firewall \
  --init learning-artifacts/tool-call-firewall
python3 scripts/project_test.py tool-call-firewall \
  --stage 1 --path learning-artifacts/tool-call-firewall --strict
python3 scripts/project_test.py tool-call-firewall \
  --all --path learning-artifacts/tool-call-firewall --strict

Keep: an audit receipt showing the requested operation and the policy decision. Approvals are single-use within one invocation; this project does not provide persistent authorization or an operating-system sandbox.

Start the project · Inspect the reference · Explore approval boundaries

Browse all projects · Career practice guide

Choose how to learn

On the website

Open any completed lesson on aiengineeringfromscratch.com or expand a phase under Contents. No setup, no cloning.

With an AI tutor

If Node.js, npx, and a skill-capable coding agent are already installed, your coding agent can become your tutor. A repository clone is not needed to install or read the tutor. Runnable focused-path labs need python3. Agent Skills host labs also need a selected host and a writable user or project skill scope.

npx skills add rohitg00/ai-engineering-from-scratch

Choose the host and scope when the installer asks. Use start-learning in Codex, /start-learning in Claude Code, or ask your host to use the skill by name.

Tutor setup and host commands

Check the local requirements first:

node --version
npx --version
python3 --version

skills writes to the host and scope selected during installation, such as .claude/skills/, .cursor/skills/, .codex/skills/, or another supported skills folder. Verify that the selected host discovers that exact destination.

Invocation syntax belongs to the host, not to the portable SKILL.md format:

Host	Start the course	Start Model Context Protocol (MCP)	Start Agent Skills	Run a phase quiz
Codex	`start-learning`, or choose it from `/skills`	`learn-mcp`, or choose it from `/skills`	`learn-agent-skills`, or choose it from `/skills`	`check-understanding 13`, or choose it from `/skills`
Claude Code	`/start-learning`	`/learn-mcp`	`/learn-agent-skills`	`/check-understanding 13`
Other compatible hosts	`Use start-learning to begin the course.`	`Use learn-mcp to start the Model Context Protocol (MCP) path.`	`Use learn-agent-skills to start the Agent Skills Engineering path.`	`Use check-understanding to quiz me on Phase 13.`

A ten-question placement quiz maps what you already know to a starting phase and saves a personalized study plan to LEARNING.md. From there, the learn skill teaches one lesson per session: concept, math, code, quiz. It streams lessons straight from this repo, and the course-guide skill jumps you to the exact lesson that covers anything you are stuck on. In Codex, invoke these skills with learn and course-guide; in Claude Code, use /learn and /course-guide; in other compatible hosts, ask to use the skill by name.

Only want Model Context Protocol (MCP)? Use the MCP invocation for your host. It creates MCP-LEARNING.md and follows one 17-lesson route through stateless requests, transports, bidirectional work, security, reliability, registry governance, and conformance evidence. The exact order and checkpoints live in the Model Context Protocol (MCP) manifest.

Only want Agent Skills? Use the Agent Skills invocation for your host. It creates AGENT-SKILLS-LEARNING.md and follows one coherent five-lesson route: contract, discovery, invocation, sandbox boundaries, then release evals and real-host portability. Start on the web with the Agent Skills path.

The installer lists the hosts it can configure and asks where to install. If you do not have Node.js, npx, python3, a supported host, or a writable scope yet, use the website or read docs/en.md manually. That path teaches the concepts, but real-host discovery, invocation, script, and uninstall evidence remains pending until the preflight is available. Read the lessons at aiengineeringfromscratch.com.

The learning skills

Skill	What it does
`start-learning`	One-time onboarding: why you're learning, placement quiz, personalized plan saved to `LEARNING.md`.
`learn`	The tutor loop. Warm-up recall, then the next lesson taught interactively, then its quiz; records progress and a review queue.
`course-guide`	Topic router. "Where do I learn attention?" or "my loss is NaN" → the exact lessons, with links.
`learn-mcp`	Focused Model Context Protocol (MCP) tutor. Creates `MCP-LEARNING.md`, follows the 17-lesson manifest, and records wire, security, reliability, and conformance evidence.
`learn-agent-skills`	Focused Agent Skills tutor. Creates `AGENT-SKILLS-LEARNING.md`, teaches lessons 22, 24, 25, 26, and 27, and records real-host evidence.
`claude-certification`	Certification tutor. Chooses CCAO-F, CCDV-F, CCAR-F, or CCAR-P; teaches each lesson; runs labs; reviews artifacts; administers diagnostics and mocks; saves progress.
`mcpa-certification`	MCPA tutor. Follows the 34-lesson `mcpa-f` route on the 2026-07-28 protocol; teaches each lesson; runs labs and the wire checker; administers the diagnostic and three mocks; saves progress.
`find-your-level`	Ten-question placement quiz. Maps your knowledge to a starting phase and produces a personalized path with hour estimates.
`check-understanding`	Per-phase quiz, eight questions, with feedback and specific lessons to review. Use the Codex, Claude Code, or natural-language form in the invocation table above.

Run local code

git clone https://github.com/rohitg00/ai-engineering-from-scratch.git
cd ai-engineering-from-scratch
python3 phases/00-setup-and-tooling/01-dev-environment/code/verify.py --route beginner
python3 phases/01-math-foundations/01-linear-algebra-intuition/code/vectors.py

The preflight separates requirements needed now from tools needed later. Every required failure includes the detected reason and a corrective command. The vectors.py command is a dependency-free lesson and ends by showing that a matrix times a vector is the operation inside a neural network layer. Save that terminal output as your first evidence.

Use every lesson the same way

Read docs/en.md and explain the core idea in your own words.
Type and build the important code instead of treating the code block as decoration.
Run the lesson command from the repository root, the directory containing README.md and phases/.
Keep evidence: the command, working directory, exit code, meaningful output, and the artifact you changed or produced.
Continue only when you can explain the output and make one small change without guessing.

Commands in lesson pages are paths from the repository root unless the lesson explicitly says to change directories. If a lesson offers several languages, run the implementation for the language you are learning.

Choose a learning path

You do not need to scan 528 lessons before beginning. Pick one goal. Each link opens the same curriculum on GitHub or the website, and both versions use the same lesson code.

Your goal	Learn on GitHub	Learn on the website
I am new and want the complete foundation	Phase 0: Setup and Tooling	Dev Environment
I know Python and want math plus ML foundations	Phase 1: Math Foundations	Linear Algebra Intuition
I want to build production LLM applications	Phase 11: LLM Engineering	Prompt Engineering
I want to build agents	Phase 14: Agent Engineering	The Agent Loop
I want to use coding agents on real repositories	Agent-Assisted Engineering path	Agent-Assisted Engineering
I want to shape the right build before implementation	Product Judgment and Delivery path	Product Judgment and Delivery

Not sure where you fit? Use the start-learning placement tutor or the website prerequisites guide.

Compare four core domains and six career routes in the AI Engineering Learning Paths.

Focused MCP and Agent Skills paths

Your goal	Learn on GitHub	Learn on the website
I want to build with Model Context Protocol (MCP)	Model Context Protocol (MCP) route	Model Context Protocol (MCP) path
I want to write and ship Agent Skills	Focused Agent Skills route	Agent Skills path

Prerequisites and study time

Prerequisites

You can write code (any language; Python helps).
You want to understand how AI actually works, not just call APIs.

Where to start

Background	Start at	Estimated time
New to programming and AI	Phase 0 — Setup	~306 hours
Know Python, new to ML	Phase 1 — Math Foundations	~270 hours
Know ML, new to deep learning	Phase 3 — Deep Learning Core	~200 hours
Know deep learning, want LLMs and agents	Phase 10 — LLMs from Scratch	~100 hours
Senior engineer, only want agent engineering	Phase 14 — Agent Engineering	~60 hours
Only want to build production MCP systems	Model Context Protocol (MCP) path	~23 hours 15 min
Only want to build production Agent Skills	Agent Skills Engineering path	~9.5 hours

The shape of the curriculum

Twenty phases stack on top of each other. Math is the floor. Agents and production are the roof. Skip ahead if you already know the lower layers, but don't skip and then wonder why something at the top is breaking.

%%{init: {'theme':'base','themeVariables':{'primaryColor':'#fafaf5','primaryTextColor':'#1a1a1a','primaryBorderColor':'#3553ff','lineColor':'#3553ff','fontFamily':'JetBrains Mono','fontSize':'12px'}}}%%
flowchart TB
  P0["Phase 0 — Setup &amp; Tooling"] --> P1["Phase 1 — Math Foundations"]
  P1 --> P2["Phase 2 — ML Fundamentals"]
  P2 --> P3["Phase 3 — Deep Learning Core"]
  P3 --> P4["Phase 4 — Vision"]
  P3 --> P5["Phase 5 — NLP"]
  P3 --> P6["Phase 6 — Speech &amp; Audio"]
  P3 --> P9["Phase 9 — RL"]
  P5 --> P7["Phase 7 — Transformers"]
  P7 --> P8["Phase 8 — GenAI"]
  P7 --> P10["Phase 10 — LLMs from Scratch"]
  P10 --> P11["Phase 11 — LLM Engineering"]
  P10 --> P12["Phase 12 — Multimodal"]
  P11 --> P13["Phase 13 — Tools &amp; Protocols"]
  P13 --> P14["Phase 14 — Agent Engineering"]
  P14 --> P15["Phase 15 — Autonomous Systems"]
  P15 --> P16["Phase 16 — Multi-Agent &amp; Swarms"]
  P14 --> P17["Phase 17 — Infrastructure &amp; Production"]
  P15 --> P18["Phase 18 — Ethics &amp; Alignment"]
  P16 --> P19["Phase 19 — Capstone Projects"]
  P17 --> P19
  P18 --> P19

Twenty phases. Click any phase to expand its lesson list.

Phase 0: Setup & Tooling `13 lessons`

Get your environment ready for everything that follows.

#	Lesson	Type	Lang
01	Dev Environment	Build	Python
02	Git & Collaboration	Learn	—
03	GPU Setup & Cloud	Build	Python
04	APIs & Keys	Build	Python
05	Jupyter Notebooks	Build	Python
06	Python Environments	Build	Shell
07	Docker for AI	Build	Docker
08	Editor Setup	Build	—
09	Data Management	Build	Python
10	Terminal & Shell	Learn	—
11	Linux for AI	Learn	—
12	Debugging & Profiling	Build	Python
13	Python for AI Engineering	Build	Python

Phase 1 — Math Foundations 22 lessons The intuition behind every AI algorithm, through code.

#	Lesson	Type	Lang
01	Linear Algebra Intuition	Learn	Python, Julia
02	Vectors, Matrices & Operations	Build	Python, Julia
03	Matrix Transformations & Eigenvalues	Build	Python, Julia
04	Calculus for ML: Derivatives & Gradients	Learn	Python
05	Chain Rule & Automatic Differentiation	Build	Python
06	Probability & Distributions	Learn	Python
07	Bayes' Theorem & Statistical Thinking	Build	Python
08	Optimization: Gradient Descent Family	Build	Python
09	Information Theory: Entropy, KL Divergence	Learn	Python
10	Dimensionality Reduction: PCA, t-SNE, UMAP	Build	Python
11	Singular Value Decomposition	Build	Python, Julia
12	Tensor Operations	Build	Python
13	Numerical Stability	Build	Python
14	Norms & Distances	Build	Python
15	Statistics for ML	Build	Python
16	Sampling Methods	Build	Python
17	Linear Systems	Build	Python
18	Convex Optimization	Build	Python
19	Complex Numbers for AI	Learn	Python
20	The Fourier Transform	Build	Python
21	Graph Theory for ML	Build	Python
22	Stochastic Processes	Learn	Python

Phase 2 — ML Fundamentals 21 lessons Classical ML — still the backbone of most production AI.

#	Lesson	Type	Lang
01	What Is Machine Learning	Learn	Python
02	Linear Regression from Scratch	Build	Python
03	Logistic Regression & Classification	Build	Python
04	Decision Trees & Random Forests	Build	Python
05	Support Vector Machines	Build	Python
06	KNN & Distance Metrics	Build	Python
07	Unsupervised Learning: K-Means, DBSCAN	Build	Python
08	Feature Engineering & Selection	Build	Python
09	Model Evaluation: Metrics, Cross-Validation	Build	Python
10	Bias, Variance & the Learning Curve	Learn	Python
11	Ensemble Methods: Boosting, Bagging, Stacking	Build	Python
12	Hyperparameter Tuning	Build	Python
13	ML Pipelines & Experiment Tracking	Build	Python
14	Naive Bayes	Build	Python
15	Time Series Fundamentals	Build	Python
16	Anomaly Detection	Build	Python
17	Handling Imbalanced Data	Build	Python
18	Feature Selection	Build	Python
19	ML System Design — From Problem to Deployed Model	Build	Python
20	Monitoring Models in Production — Data Drift and Concept Drift	Build	Python
21	Feature Stores and Training-Serving Skew	Build	Python

Phase 3 — Deep Learning Core 13 lessons Neural networks from first principles. No frameworks until you build one.

#	Lesson	Type	Lang
01	The Perceptron: Where It All Started	Build	Python
02	Multi-Layer Networks & Forward Pass	Build	Python
03	Backpropagation from Scratch	Build	Python
04	Activation Functions: ReLU, Sigmoid, GELU & Why	Build	Python
05	Loss Functions: MSE, Cross-Entropy, Contrastive	Build	Python
06	Optimizers: SGD, Momentum, Adam, AdamW	Build	Python
07	Regularization: Dropout, Weight Decay, BatchNorm	Build	Python
08	Weight Initialization & Training Stability	Build	Python
09	Learning Rate Schedules & Warmup	Build	Python
10	Build Your Own Mini Framework	Build	Python
11	Introduction to PyTorch	Build	Python
12	Introduction to JAX	Build	Python
13	Debugging Neural Networks	Build	Python

Phase 4 — Computer Vision 28 lessons From pixels to understanding — image, video, 3D, VLMs, and world models.

#	Lesson	Type	Lang
01	Image Fundamentals: Pixels, Channels, Color Spaces	Learn	Python
02	Convolutions from Scratch	Build	Python
03	CNNs: LeNet to ResNet	Build	Python
04	Image Classification	Build	Python
05	Transfer Learning & Fine-Tuning	Build	Python
06	Object Detection — YOLO from Scratch	Build	Python
07	Semantic Segmentation — U-Net	Build	Python
08	Instance Segmentation — Mask R-CNN	Build	Python
09	Image Generation — GANs	Build	Python
10	Image Generation — Diffusion Models	Build	Python
11	Stable Diffusion — Architecture & Fine-Tuning	Build	Python
12	Video Understanding — Temporal Modeling	Build	Python
13	3D Vision: Point Clouds, NeRFs	Build	Python
14	Vision Transformers (ViT)	Build	Python
15	Real-Time Vision: Edge Deployment	Build	Python
16	Build a Complete Vision Pipeline	Build	Python
17	Self-Supervised Vision — SimCLR, DINO, MAE	Build	Python
18	Open-Vocabulary Vision — CLIP	Build	Python
19	OCR & Document Understanding	Build	Python
20	Image Retrieval & Metric Learning	Build	Python
21	Keypoint Detection & Pose Estimation	Build	Python
22	3D Gaussian Splatting from Scratch	Build	Python
23	Diffusion Transformers & Rectified Flow	Build	Python
24	SAM 3 & Open-Vocabulary Segmentation	Build	Python
25	Vision-Language Models (ViT-MLP-LLM)	Build	Python
26	Monocular Depth & Geometry Estimation	Build	Python
27	Multi-Object Tracking & Video Memory	Build	Python
28	World Models & Video Diffusion	Build	Python

Phase 5 — NLP: Foundations to Advanced 29 lessons Language is the interface to intelligence.

#	Lesson	Type	Lang
01	Text Processing: Tokenization, Stemming, Lemmatization	Build	Python
02	Bag of Words, TF-IDF & Text Representation	Build	Python
03	Word Embeddings: Word2Vec from Scratch	Build	Python
04	GloVe, FastText & Subword Embeddings	Build	Python
05	Sentiment Analysis	Build	Python
06	Named Entity Recognition (NER)	Build	Python
07	POS Tagging & Syntactic Parsing	Build	Python
08	Text Classification — CNNs & RNNs for Text	Build	Python
09	Sequence-to-Sequence Models	Build	Python
10	Attention Mechanism — The Breakthrough	Build	Python
11	Machine Translation	Build	Python
12	Text Summarization	Build	Python
13	Question Answering Systems	Build	Python
14	Information Retrieval & Search	Build	Python
15	Topic Modeling: LDA, BERTopic	Build	Python
16	Text Generation	Build	Python
17	Chatbots: Rule-Based to Neural	Build	Python
18	Multilingual NLP	Build	Python
19	Subword Tokenization: BPE, WordPiece, Unigram, SentencePiece	Learn	Python
20	Structured Outputs & Constrained Decoding	Build	Python
21	NLI & Textual Entailment	Learn	Python
22	Embedding Models Deep Dive	Learn	Python
23	Chunking Strategies for RAG	Build	Python
24	Coreference Resolution	Learn	Python
25	Entity Linking & Disambiguation	Build	Python
26	Relation Extraction & Knowledge Graph Construction	Build	Python
27	LLM Evaluation: RAGAS, DeepEval, G-Eval	Build	Python
28	Long-Context Evaluation: NIAH, RULER, LongBench, MRCR	Learn	Python
29	Dialogue State Tracking	Build	Python

Phase 6 — Speech & Audio 17 lessons Hear, understand, speak.

#	Lesson	Type	Lang
01	Audio Fundamentals: Waveforms, Sampling, FFT	Learn	Python
02	Spectrograms, Mel Scale & Audio Features	Build	Python
03	Audio Classification	Build	Python
04	Speech Recognition (ASR)	Build	Python
05	Whisper: Architecture & Fine-Tuning	Build	Python
06	Speaker Recognition & Verification	Build	Python
07	Text-to-Speech (TTS)	Build	Python
08	Voice Cloning & Voice Conversion	Build	Python
09	Music Generation	Build	Python
10	Audio-Language Models	Build	Python
11	Real-Time Audio Processing	Build	Python
12	Build a Voice Assistant Pipeline	Build	Python
13	Neural Audio Codecs — EnCodec, SNAC, Mimi, DAC	Learn	Python
14	Voice Activity Detection & Turn-Taking	Build	Python
15	Streaming Speech-to-Speech — Moshi, Hibiki	Learn	Python
16	Voice Anti-Spoofing & Audio Watermarking	Build	Python
17	Audio Evaluation — WER, MOS, MMAU, Leaderboards	Learn	Python

Phase 7 — Transformers Deep Dive 16 lessons The architecture that changed everything.

#	Lesson	Type	Lang
01	Why Transformers: The Problems with RNNs	Learn	Python
02	Self-Attention from Scratch	Build	Python
03	Multi-Head Attention	Build	Python
04	Positional Encoding: Sinusoidal, RoPE, ALiBi	Build	Python
05	The Full Transformer: Encoder + Decoder	Build	Python
06	BERT — Masked Language Modeling	Build	Python
07	GPT — Causal Language Modeling	Build	Python
08	T5, BART — Encoder-Decoder Models	Learn	Python
09	Vision Transformers (ViT)	Build	Python
10	Audio Transformers — Whisper Architecture	Learn	Python
11	Mixture of Experts (MoE)	Build	Python
12	KV Cache, Flash Attention & Inference Optimization	Build	Python
13	Scaling Laws	Learn	Python
14	Build a Transformer from Scratch	Build	Python
15	Attention Variants — Sliding Window, Sparse, Differential	Build	Python
16	Speculative Decoding — Draft, Verify, Repeat	Build	Python

Phase 8 — Generative AI 15 lessons Create images, video, audio, 3D, and more.

#	Lesson	Type	Lang
01	Generative Models: Taxonomy & History	Learn	Python
02	Autoencoders & VAE	Build	Python
03	GANs: Generator vs Discriminator	Build	Python
04	Conditional GANs & Pix2Pix	Build	Python
05	StyleGAN	Build	Python
06	Diffusion Models — DDPM from Scratch	Build	Python
07	Latent Diffusion & Stable Diffusion	Build	Python
08	ControlNet, LoRA & Conditioning	Build	Python
09	Inpainting, Outpainting & Editing	Build	Python
10	Video Generation	Build	Python
11	Audio Generation	Build	Python
12	3D Generation	Build	Python
13	Flow Matching & Rectified Flows	Build	Python
14	Evaluation: FID, CLIP Score	Build	Python
19	Visual Autoregressive Modeling (VAR): Next-Scale Prediction	Build	Python

Phase 9 — Reinforcement Learning 12 lessons The foundation of RLHF and game-playing AI.

#	Lesson	Type	Lang
01	MDPs, States, Actions & Rewards	Learn	Python
02	Dynamic Programming	Build	Python
03	Monte Carlo Methods	Build	Python
04	Q-Learning, SARSA	Build	Python
05	Deep Q-Networks (DQN)	Build	Python
06	Policy Gradients — REINFORCE	Build	Python
07	Actor-Critic — A2C, A3C	Build	Python
08	PPO	Build	Python
09	Reward Modeling & RLHF	Build	Python
10	Multi-Agent RL	Build	Python
11	Sim-to-Real Transfer	Build	Python
12	RL for Games	Build	Python

Phase 10 — LLMs from Scratch 24 lessons Build, train, and understand large language models.

#	Lesson	Type	Lang
01	Tokenizers: BPE, WordPiece, SentencePiece	Build	Python, Rust
02	Building a Tokenizer from Scratch	Build	Python
03	Data Pipelines for Pre-Training	Build	Python
04	Pre-Training a Mini GPT (124M)	Build	Python
05	Distributed Training, FSDP, DeepSpeed	Build	Python
06	Instruction Tuning — SFT	Build	Python
07	RLHF — Reward Model + PPO	Build	Python
08	DPO — Direct Preference Optimization	Build	Python
09	Constitutional AI & Self-Improvement	Build	Python
10	Evaluation — Benchmarks, Evals	Build	Python
11	Quantization: INT8, GPTQ, AWQ, GGUF	Build	Python
12	Inference Optimization	Build	Python
13	Building a Complete LLM Pipeline	Build	Python
14	Open Models: Architecture Walkthroughs	Learn	Python
15	Speculative Decoding and EAGLE-3	Build	Python
16	Differential Attention (V2)	Build	Python
17	Native Sparse Attention (DeepSeek NSA)	Build	Python
18	Multi-Token Prediction (MTP)	Build	Python
19	DualPipe Parallelism	Learn	Python
20	DeepSeek-V3 Architecture Walkthrough	Learn	Python
21	Jamba — Hybrid SSM-Transformer	Learn	Python
22	Async and Hogwild! Inference	Build	Python
25	Speculative Decoding and EAGLE	Build	Python
34	Gradient Checkpointing and Activation Recomputation	Build	Python

Phase 11 — LLM Engineering 17 lessons Put LLMs to work in production.

#	Lesson	Type	Lang
01	Prompt Engineering: Techniques & Patterns	Build	Python
02	Few-Shot, CoT, Tree-of-Thought	Build	Python
03	Structured Outputs	Build	Python
04	Embeddings & Vector Representations	Build	Python
05	Context Engineering	Build	Python
06	RAG: Retrieval-Augmented Generation	Build	Python
07	Advanced RAG: Chunking, Reranking	Build	Python
08	Fine-Tuning with LoRA & QLoRA	Build	Python
09	Function Calling & Tool Use	Build	Python
10	Evaluation & Testing	Build	Python
11	Caching, Rate Limiting & Cost	Build	Python
12	Guardrails & Safety	Build	Python
13	Building a Production LLM App	Build	Python
14	Model Context Protocol (MCP)	Build	Python
15	Prompt Caching & Context Caching	Build	Python
16	Agent State Machines — Graphs, Nodes, Checkpoints	Build	Python
17	Agent Framework Tradeoffs	Learn	Python

Phase 12 — Multimodal AI 25 lessons See, hear, read, and reason across modalities — from ViT patches to computer-use agents.

#	Lesson	Type	Lang
01	Vision Transformers and the Patch-Token Primitive	Learn	Python
02	CLIP and Contrastive Vision-Language Pretraining	Build	Python
03	BLIP-2 Q-Former as Modality Bridge	Build	Python
04	Flamingo and Gated Cross-Attention	Learn	Python
05	LLaVA and Visual Instruction Tuning	Build	Python
06	Any-Resolution Vision — Patch-n'-Pack and NaFlex	Build	Python
07	Open-Weight VLM Recipes: What Actually Matters	Learn	Python
08	LLaVA-OneVision: Single, Multi, Video	Build	Python
09	Qwen-VL Family and Dynamic-FPS Video	Learn	Python
10	InternVL3 Native Multimodal Pretraining	Learn	Python
11	Chameleon Early-Fusion Token-Only	Build	Python
12	Emu3 Next-Token Prediction for Generation	Learn	Python
13	Transfusion Autoregressive + Diffusion	Build	Python
14	Show-o Discrete-Diffusion Unified	Learn	Python
15	Janus-Pro Decoupled Encoders	Build	Python
16	MIO Any-to-Any Streaming	Learn	Python
17	Video-Language Temporal Grounding	Build	Python
18	Long-Video at Million-Token Context	Build	Python
19	Audio-Language Models: Whisper to AF3	Build	Python
20	Omni Models: Thinker-Talker Streaming	Build	Python
21	Embodied VLAs: RT-2, OpenVLA, π0, GR00T	Learn	Python
22	Document and Diagram Understanding	Build	Python
23	ColPali Vision-Native Document RAG	Build	Python
24	Multimodal RAG and Cross-Modal Retrieval	Build	Python
25	Multimodal Agents and Computer-Use (Capstone)	Build	Python

Phase 13 — Tools & Protocols 31 lessons The interfaces between AI and the real world.

#	Lesson	Type	Lang
01	The Tool Interface	Learn	Python
02	Function Calling Deep Dive	Build	Python
03	Parallel and Streaming Tool Calls	Build	Python
04	Structured Output	Build	Python
05	Tool Schema Design	Learn	Python
06	MCP Fundamentals: Stateless Requests and JSON-RPC	Learn	Python
07	Building an MCP Server: Stateless Python and TypeScript	Build	Python, TypeScript
08	Building an MCP Client: Discovery, Routing, and Dual-Era Fallback	Build	Python
09	MCP Transports: stdio and Stateless Streamable HTTP	Learn	Python
10	MCP Resources and Prompts: Addressable Context for Stateless Servers	Build	Python
11	MCP Model Input: Sampling Migration and Stateless MRTR	Build	Python
12	Explicit Scope and Stateless Elicitation	Build	Python
13	MCP Tasks Extension: Durable Work on a Stateless Core	Build	Python
14	MCP Apps on the Stateless Protocol	Build	Python
15	MCP Security: Poisoned Metadata, Routing, and MRTR State	Learn	Python
16	MCP Authorization: CIMD, Issuer Binding, PKCE, and Step-Up	Build	Python
17	Stateless MCP Gateways and Registry Admission	Learn	Python
18	MCP Auth in Production: Issuer-Bound Enrollment and Tokens	Build	Python
19	A2A Protocol	Build	Python
20	OpenTelemetry GenAI	Build	Python
21	LLM Routing Layer	Learn	Python
22	Agent Skills: Portable Contract and Runtime Boundary	Build	Python
23	Capstone: Stateless Tool Ecosystem	Build	Python
24	Skill Discovery and Progressive Disclosure	Build	Python
25	Skill Invocation and Routing	Build	Python
26	Skill Permissions, Sandboxes, and Trust	Build	Python
27	Skill Evals, Packaging, and Portability	Build	Python
28	MCP Tool Contracts and Content	Build	Python
29	MCP Reliability, Cancellation, and Flow Control	Build	Python
30	MCP Registry Supply Chain: Admission, Drift, and Rollback	Build	Python
31	MCP Conformance Engineering: Versioning, Evidence, and Operations	Build	Python

Lessons 06-18 and 28-31 form the focused Model Context Protocol (MCP) path. Its manifest order is 06, 07, 08, 09, 10, 11, 12, 13, 14, 15, 16, 18, 17, 28, 29, 30, 31. Start it with the host-specific learn-mcp invocation above. Lesson 23 is its only optional capstone and also requires Lessons 19 and 20.

Lessons 22 and 24-27 form the focused Agent Skills learning path, from package contract through real-host release gates. Start it with the host-specific learn-agent-skills invocation shown above; do not follow numeric next navigation from 22 to 23.

Phase 14 — Agent Engineering 54 lessons Build agents from first principles, use coding agents reliably, and shape the work before implementation.

#	Lesson	Type	Lang
01	The Agent Loop	Build	Python
02	ReWOO and Plan-and-Execute	Build	Python
03	Reflexion and Verbal Reinforcement Learning	Build	Python
04	Tree of Thoughts and LATS	Build	Python
05	Self-Refine and CRITIC	Build	Python
06	Tool Use and Function Calling	Build	Python
07	Agent Memory — Virtual Context and Memory Paging	Build	Python
08	Memory Blocks and Sleep-Time Compute	Build	Python
09	Hybrid Memory — Vector + Graph + KV	Build	Python
10	Skill Libraries and Lifelong Learning (Voyager)	Build	Python
11	Planning with HTN and Evolutionary Search	Build	Python
12	Anthropic's Workflow Patterns	Build	Python
13	Stateful Graph Orchestration — Durable Execution and Checkpoints	Build	Python
14	The Actor Model for Agents	Build	Python
15	Role-Based Agent Teams — Roles, Tasks, Processes	Build	Python
16	OpenAI Agents SDK — Handoffs, Guardrails, Tracing	Build	Python
17	The Harness as a Library — Subagents and Session Store	Build	Python
18	Production Agent Runtimes	Learn	Python
19	Benchmarks — SWE-bench, GAIA, AgentBench	Learn	Python
20	Benchmarks — WebArena and OSWorld	Learn	Python
21	Computer Use — Claude, OpenAI CUA, Gemini	Build	Python
22	Voice Agents — Pipecat and LiveKit	Build	Python
23	OpenTelemetry GenAI Semantic Conventions	Build	Python
24	Agent Observability — Langfuse, Phoenix, Opik	Learn	Python
25	Multi-Agent Debate and Collaboration	Build	Python
26	Failure Modes — Why Agents Break	Build	Python
27	Prompt Injection and the PVE Defense	Build	Python
28	Orchestration Patterns — Supervisor, Swarm, Hierarchical	Build	Python
29	Production Runtimes — Queue, Event, Cron	Learn	Python
30	Eval-Driven Agent Development	Build	Python
31	Agent Workbench: Why Capable Models Still Fail	Learn	Python
32	The Minimal Agent Workbench	Build	Python
33	Agent Instructions as Executable Constraints	Build	Python
34	Repo Memory and Durable State	Build	Python
35	Initialization Scripts for Agents	Build	Python
36	Scope Contracts and Task Boundaries	Build	Python
37	Runtime Feedback Loops	Build	Python
38	Verification Gates	Build	Python
39	Reviewer Agent: Separate Builder from Marker	Build	Python
40	Multi-Session Handoff	Build	Python
41	The Workbench on a Real Repo	Build	Python
42	Capstone: Ship a Reusable Agent Workbench Pack	Build	Python
43	Frame the Task Before the Agent Writes Code	Build	Python
44	Build an Evidence-Backed Execution Plan	Build	Python
45	Delegate Agent Work with Isolation and Merge Contracts	Build	Python
46	Turn Every Agent Correction into a System Improvement	Build	Python
47	Define the Outcome Before You Choose the Output	Build	Python
48	Discover the Workflow People Actually Perform	Build	Python
49	Map Assumptions and Resolve the Riskiest One First	Build	Python
50	Choose the Smallest Slice That Can Change the Decision	Build	Python
51	Write Specifications That Preserve Judgment	Build	Python
52	Design Success Metrics Before the Result Exists	Build	Python
53	Choose Prototype, Pilot, or Production Deliberately	Build	Python
54	Build a Feedback Ratchet with Ownership and Retirement	Build	Python

Each Phase 14 workbench lesson (31-42) ships a mission.md briefing the agent before it opens the full lesson docs.

Lessons 31-46 form the Agent-Assisted Engineering path. Its manifest order combines the workbench foundation with task framing, planning, delegation, and durable feedback. Lessons 47-54 form the Product Judgment and Delivery path, from outcome framing through evidence, risk, scope, measurement, staged release, and feedback ownership.

Phase 15 — Autonomous Systems 22 lessons Long-horizon agents, self-improvement, and the 2026 safety stack.

#	Lesson	Type	Lang
01	From Chatbots to Long-Horizon Agents (METR)	Learn	Python
02	STaR, V-STaR, Quiet-STaR: Self-Taught Reasoning	Learn	Python
03	AlphaEvolve: Evolutionary Coding Agents	Learn	Python
04	Darwin Gödel Machine: Self-Modifying Agents	Learn	Python
05	AI Scientist v2: Workshop-Level Research	Learn	Python
06	Automated Alignment Research (Anthropic AAR)	Learn	Python
07	Recursive Self-Improvement: Capability vs Alignment	Learn	Python
08	Bounded Self-Improvement Designs	Learn	Python
09	Autonomous Coding Agent Landscape (SWE-bench, CodeAct)	Learn	Python
10	Permission Modes for Autonomous Agents	Learn	Python
11	Browser Agents and Indirect Prompt Injection	Learn	Python
12	Durable Execution for Long-Running Agents	Learn	Python
13	Action Budgets, Iteration Caps, Cost Governors	Learn	Python
14	Kill Switches, Circuit Breakers, Canary Tokens	Learn	Python
15	HITL: Propose-Then-Commit	Learn	Python
16	Checkpoints and Rollback	Learn	Python
17	Constitutional AI and Rule Overrides	Learn	Python
18	Llama Guard and Input/Output Classification	Learn	Python
19	Anthropic Responsible Scaling Policy v3.0	Learn	Python
20	OpenAI Preparedness Framework and DeepMind FSF	Learn	Python
21	METR Time Horizons and External Evaluation	Learn	Python
22	CAIS, CAISI, and Societal-Scale Risk	Learn	Python

Phase 16 — Multi-Agent & Swarms 25 lessons Coordination, emergence, and collective intelligence.

#	Lesson	Type	Lang
01	Why Multi-Agent	Learn	TypeScript
02	FIPA-ACL Heritage and Speech Acts	Learn	Python
03	Communication Protocols	Build	TypeScript
04	The Multi-Agent Primitive Model	Learn	Python
05	Supervisor / Orchestrator-Worker Pattern	Build	Python
06	Hierarchical Architecture and Decomposition Drift	Learn	Python
07	Society of Mind and Multi-Agent Debate	Build	Python
08	Role Specialization — Planner / Critic / Executor / Verifier	Build	Python
09	Parallel Swarm and Networked Architectures	Build	Python
10	Group Chat and Speaker Selection	Build	Python
11	Handoffs and Routines (Stateless Orchestration)	Build	Python
12	A2A — The Agent-to-Agent Protocol	Build	Python
13	Shared Memory and Blackboard Patterns	Build	Python
14	Consensus and Byzantine Fault Tolerance	Build	Python
15	Voting, Self-Consistency, and Debate Topology	Build	Python
16	Negotiation and Bargaining	Build	Python
17	Generative Agents and Emergent Simulation	Build	Python
18	Theory of Mind and Emergent Coordination	Build	Python
19	Swarm Optimization (PSO, ACO)	Build	Python
20	MARL — MADDPG, QMIX, MAPPO	Learn	Python
21	Agent Economies, Token Incentives, Reputation	Learn	Python
22	Production Scaling — Queues, Checkpoints, Durability	Build	Python
23	Failure Modes — MAST, Groupthink, Monoculture	Learn	Python
24	Evaluation and Coordination Benchmarks	Learn	Python
25	Case Studies and 2026 State of the Art	Learn	Python

Phase 17 — Infrastructure & Production 29 lessons Ship AI to the real world.

#	Lesson	Type	Lang
01	Managed LLM Platforms — Bedrock, Azure OpenAI, Vertex AI	Learn	Python
02	Inference Platform Economics — Fireworks, Together, Baseten, Modal	Learn	Python
03	GPU Autoscaling on Kubernetes — Karpenter, KAI Scheduler	Learn	Python
04	Serving Engine Internals — PagedAttention, Continuous Batching, Chunked Prefill	Learn	Python
05	EAGLE-3 Speculative Decoding in Production	Learn	Python
06	Prefix-Cache Serving — RadixAttention and KV Reuse	Learn	Python
07	Hardware-Specialized Inference Compilation — FP8 and NVFP4 on Blackwell	Learn	Python
08	Inference Metrics — TTFT, TPOT, ITL, Goodput, P99	Learn	Python
09	Production Quantization — AWQ, GPTQ, GGUF, FP8, NVFP4	Learn	Python
10	Cold Start Mitigation for Serverless LLMs	Learn	Python
11	Multi-Region LLM Serving and KV Cache Locality	Learn	Python
12	Edge Inference — ANE, Hexagon, WebGPU, Jetson	Learn	Python
13	LLM Observability Stack Selection	Learn	Python
14	Prompt Caching and Semantic Caching Economics	Learn	Python
15	Batch APIs — the 50% Discount as Industry Standard	Learn	Python
16	Model Routing as a Cost-Reduction Primitive	Learn	Python
17	Disaggregated Prefill/Decode — NVIDIA Dynamo and llm-d	Learn	Python
18	Production Serving Stack — KV Offloading and Cache-Aware Routing	Learn	Python
19	AI Gateways — LiteLLM, Portkey, Kong, Bifrost	Learn	Python
20	Shadow, Canary, and Progressive Deployment	Learn	Python
21	A/B Testing LLM Features — GrowthBook and Statsig	Learn	Python
22	Load Testing LLM APIs — k6, LLMPerf, GenAI-Perf	Build	Python
23	SRE for AI — Multi-Agent Incident Response	Learn	Python
24	Chaos Engineering for LLM Production	Learn	Python
25	Security — Secrets, PII Scrubbing, Audit Logs	Learn	Python
26	Compliance — SOC 2, HIPAA, GDPR, EU AI Act, ISO 42001	Learn	Python
27	FinOps for LLMs — Unit Economics and Multi-Tenant Attribution	Learn	Python
28	Self-Hosted Serving Selection — Matching Engine to Hardware and Scale	Learn	Python
29	Model Demo Interfaces — From a Function to a Shareable App	Build	Python

Phase 18 — Ethics, Safety & Alignment 30 lessons Build AI that helps humanity. Not optional.

#	Lesson	Type	Lang
01	Instruction-Following as Alignment Signal	Learn	Python
02	Reward Hacking & Goodhart's Law	Learn	Python
03	Direct Preference Optimization Family	Learn	Python
04	Sycophancy as RLHF Amplification	Learn	Python
05	Constitutional AI & RLAIF	Learn	Python
06	Mesa-Optimization & Deceptive Alignment	Learn	Python
07	Sleeper Agents — Persistent Deception	Learn	Python
08	In-Context Scheming in Frontier Models	Learn	Python
09	Alignment Faking	Learn	Python
10	AI Control — Safety Despite Subversion	Learn	Python
11	Scalable Oversight & Weak-to-Strong	Learn	Python
12	Red-Teaming: PAIR & Automated Attacks	Build	Python
13	Many-Shot Jailbreaking	Learn	Python
14	ASCII Art & Visual Jailbreaks	Build	Python
15	Indirect Prompt Injection	Build	Python
16	Red-Team Tooling: Garak, Llama Guard, PyRIT	Build	Python
17	WMDP & Dual-Use Capability Evaluation	Learn	Python
18	Frontier Safety Frameworks — RSP, PF, FSF	Learn	Python
19	Model Welfare Research	Learn	Python
20	Bias & Representational Harm	Build	Python
21	Fairness Criteria: Group, Individual, Counterfactual	Learn	Python
22	Differential Privacy for LLMs	Build	Python
23	Watermarking: SynthID, Stable Signature, C2PA	Build	Python
24	Regulatory Frameworks: EU, US, UK, Korea	Learn	Python
25	EchoLeak & CVEs for AI	Learn	Python
26	Model, System & Dataset Cards	Build	Python
27	Data Provenance & Training-Data Governance	Learn	Python
28	Alignment Research Ecosystem: MATS, Redwood, Apollo, METR	Learn	Python
29	Moderation Systems: OpenAI, Perspective, Llama Guard	Build	Python
30	Dual-Use Risk: Cyber, Bio, Chem, Nuclear	Learn	Python

Phase 19 — Capstone Projects 85 lessons 17 end-to-end products + 9 deep-build tracks. 20-40 hours per project; 4-12 lessons per track.

#	Project	Combines	Lang
01	Terminal-Native Coding Agent	P0 P5 P7 P10 P11 P13 P14 P15 P17 P18	Python
02	RAG over Codebase (Cross-Repo Semantic Search)	P5 P7 P11 P13 P17	Python
03	Real-Time Voice Assistant (ASR → LLM → TTS)	P6 P7 P11 P13 P14 P17	Python
04	Multimodal Document QA (Vision-First)	P4 P5 P7 P11 P12 P17	Python
05	Autonomous Research Agent (AI-Scientist Class)	P0 P2 P3 P7 P10 P14 P15 P16 P18	Python
06	DevOps Troubleshooting Agent for Kubernetes	P11 P13 P14 P15 P17 P18	Python
07	End-to-End Fine-Tuning Pipeline	P2 P3 P7 P10 P11 P17 P18	Python
08	Production RAG Chatbot (Regulated Vertical)	P5 P7 P11 P12 P17 P18	Python
09	Code Migration Agent (Repo-Level Upgrade)	P5 P7 P11 P13 P14 P15 P17	Python
10	Multi-Agent Software Engineering Team	P11 P13 P14 P15 P16 P17	Python
11	LLM Observability & Eval Dashboard	P11 P13 P17 P18	Python
12	Video Understanding Pipeline (Scene → QA)	P4 P6 P7 P11 P12 P17	Python
13	Stateless MCP Server with Registry and Governance	P11 P13 P14 P17 P18	Python
14	Speculative-Decoding Inference Server	P3 P7 P10 P17	Python
15	Constitutional Safety Harness + Red-Team Range	P10 P11 P13 P14 P18	Python
16	GitHub Issue-to-PR Autonomous Agent	P11 P13 P14 P15 P17	Python
17	Personal AI Tutor (Adaptive, Multimodal)	P5 P6 P11 P12 P14 P17 P18	Python

Deep-build tracks — multi-lesson series that build a complete subsystem from scratch.

#	Project	Combines	Lang
20	Agent Harness Loop Contract	A. Agent harness	Python
21	Tool Registry with Schema Validation	A. Agent harness	Python
22	JSON-RPC 2.0 Over Newline-Delimited Stdio	A. Agent harness	Python
23	Function Call Dispatcher	A. Agent harness	Python
24	Plan-Execute Control Flow	A. Agent harness	Python
25	Verification Gates and Observation Budget	A. Agent harness	Python
26	Sandbox Runner with Denylist and Path Jail	A. Agent harness	Python
27	Eval Harness with Fixture Tasks	A. Agent harness	Python
28	Observability with OTel GenAI Spans and Prometheus Metrics	A. Agent harness	Python
29	End-to-End Coding Agent on the Harness	A. Agent harness	Python
30	BPE Tokenizer From Scratch	B. NLP LLM	Python
31	Tokenized Dataset with Sliding Window	B. NLP LLM	Python
32	Token and Positional Embeddings	B. NLP LLM	Python
33	Multi-Head Self-Attention	B. NLP LLM	Python
34	Transformer Block from Scratch	B. NLP LLM	Python
35	GPT Model Assembly	B. NLP LLM	Python
36	Training Loop and Evaluation	B. NLP LLM	Python
37	Loading Pretrained Weights	B. NLP LLM	Python
38	Classifier Fine-Tuning by Head Swap	B. NLP LLM	Python
39	Instruction Tuning by Supervised Fine-Tuning	B. NLP LLM	Python
40	Direct Preference Optimization from Scratch	B. NLP LLM	Python
41	Full Evaluation Pipeline	B. NLP LLM	Python
42	Large Corpus Downloader	C. Train end-to-end	Python
43	HDF5 Tokenized Corpus	C. Train end-to-end	Python
44	Cosine LR with Linear Warmup	C. Train end-to-end	Python
45	Gradient Clipping and Mixed Precision	C. Train end-to-end	Python
46	Gradient Accumulation	C. Train end-to-end	Python
47	Checkpoint Save and Resume	C. Train end-to-end	Python
48	Distributed Data Parallel and FSDP from Scratch	C. Train end-to-end	Python
49	Language Model Evaluation Harness	C. Train end-to-end	Python
50	Hypothesis Generator	D. Auto research	Python
51	Literature Retrieval	D. Auto research	Python
52	Experiment Runner	D. Auto research	Python
53	Result Evaluator	D. Auto research	Python
54	Paper Writer	D. Auto research	Python
55	Critic Loop	D. Auto research	Python
56	Iteration Scheduler	D. Auto research	Python
57	End-to-End Research Demo	D. Auto research	Python
58	Vision Encoder Patches	E. Multimodal VLM	Python
59	Vision Transformer Encoder	E. Multimodal VLM	Python
60	Projection Layer for Modality Alignment	E. Multimodal VLM	Python
61	Cross-Attention Fusion	E. Multimodal VLM	Python
62	Vision-Language Pretraining	E. Multimodal VLM	Python
63	Multimodal Evaluation	E. Multimodal VLM	Python
64	Chunking Strategies, Compared	F. Advanced RAG	Python
65	Hybrid Retrieval with BM25 and Dense Embeddings	F. Advanced RAG	Python
66	Cross-Encoder Reranker	F. Advanced RAG	Python
67	Query Rewriting: HyDE, Multi-Query, and Decomposition	F. Advanced RAG	Python
68	RAG Evaluation: Precision, Recall, MRR, nDCG, Faithfulness, Answer Relevance	F. Advanced RAG	Python
69	End-to-End RAG System	F. Advanced RAG	Python
70	Task Spec Format	G. Eval framework	Python
71	Classical Metrics	G. Eval framework	Python
72	Code Exec Metric	G. Eval framework	Python
73	Perplexity and Calibration	G. Eval framework	Python
74	Leaderboard Aggregation	G. Eval framework	Python
75	End-to-End Eval Runner	G. Eval framework	Python
76	Collective Ops From Scratch	H. Distributed train	Python
77	Data Parallel DDP From Scratch	H. Distributed train	Python
78	ZeRO Optimizer State Sharding	H. Distributed train	Python
79	Pipeline Parallel and Bubble Analysis	H. Distributed train	Python
80	Sharded Checkpoint and Atomic Resume	H. Distributed train	Python
81	End-to-End Distributed Training	H. Distributed train	Python
82	Jailbreak Taxonomy	I. Safety harness	Python
83	Prompt Injection Detector	I. Safety harness	Python
84	Refusal Evaluation	I. Safety harness	Python
85	Content Classifier Integration	I. Safety harness	Python
86	Constitutional Rules Engine	I. Safety harness	Python, YAML
87	End-to-End Safety Gate	I. Safety harness	Python

Books and certifications

Read the core curriculum as a book

The 20-phase core curriculum under phases/ compiles into a six-volume book series. EPUB and PDF are built by CI from the same core lesson sources and attached to every GitHub release; the links below always resolve to the newest release. Volume numbers index the series, not versions: each copy carries a dated edition stamp, and older editions stay downloadable from their release.

Certification curricula are intentionally not converted into the books. Their AI tutor state, runnable labs, interactive figures, diagnostics, and timed mocks remain first-class on GitHub and the website.

Vol	Title	Phases	Download
1	Foundations · Math, Tooling, and Classical Machine Learning	00-02	EPUB · PDF
2	Deep Learning · Networks, Vision, and Speech	03, 04, 06	EPUB · PDF
3	Language · NLP Foundations and the Transformer	05, 07	EPUB · PDF
4	Large Language Models · Generation, Reinforcement, Pretraining, and Engineering	08-11	EPUB · PDF
5	Agents · Multimodality, Protocols, Autonomy, and Swarms	12-16	EPUB · PDF
6	Production · Infrastructure, Safety, and Capstones	17-19	EPUB · PDF

The book is the snapshot; this repository is the living edition. Every chapter ends with links back to the lesson's animated figures, quiz, and runnable code. Build locally with python3 scripts/build_book.py (pandoc required); pipeline details in book/README.md.

Prepare for Claude certifications

The Claude Certification Academy is a free, open-source preparation program for all four official Claude certification tracks: Associate Foundations, Developer Foundations, Architect Foundations, and Architect Professional. Each route combines blueprint-mapped lessons, runnable labs, a diagnostic, capstone work, and a full-length original practice exam.

Use the AI-native GitHub onboarding guide with Claude Code, Codex, ChatGPT, Cursor, or another agent. Run claude-certification in Codex, /claude-certification in Claude Code, or ask another host to use claude-certification. It chooses a track, creates a persistent route in CLAUDE-CERTIFICATION.md, teaches one step at a time, runs the real labs, and gives artifact-based feedback. The same curriculum remains available on the certification website.

The academy is independent study material based on public exam objectives. It is not affiliated with Anthropic, does not reproduce live exam questions, and cannot guarantee a passing score.

Prepare for MCP Associate (MCPA)

The MCPA Certification Curriculum is a free, open-source preparation program for the Model Context Protocol Associate exam from the Agentic AI Foundation, delivered through Linux Foundation Training. Its 34 lessons teach the stateless 2026-07-28 protocol across the five exam domains: per-request _meta and server/discover in place of the old handshake, multi round-trip requests, subscriptions, caching, the tasks and MCP Apps extensions, OAuth authorization, and the registry and SDK tiers. Every lesson ships a runnable standard-library lab whose transcript is checked for the current wire shape, and the track adds a diagnostic, a capstone, and three full-length original practice exams whose question mix follows the published blueprint weights.

Use the AI-native GitHub onboarding guide with Claude Code, Codex, ChatGPT, Cursor, or another agent. Run mcpa-certification in Codex, /mcpa-certification in Claude Code, or ask another host to use mcpa-certification. It creates a persistent route in MCPA-CERTIFICATION.md, teaches one step at a time, runs the real labs, and gives artifact-based feedback. The same curriculum is available on the MCPA track page.

This curriculum is independent study material based on public exam objectives. It is not affiliated with the Agentic AI Foundation or the Linux Foundation, does not reproduce live exam questions, and cannot guarantee a passing score.

The toolkit

Every lesson produces a reusable artifact. Install one in your agent or use the scripts below from the repository root.

Lesson structure and reusable artifacts

The shape of a lesson

Each lesson lives in its own folder, with the same structure across the entire curriculum:

phases/-/-/
├── code/      runnable implementations (Python, TypeScript, Rust, Julia)
├── docs/
│   └── en.md  lesson narrative
└── outputs/   prompts, skills, agents, or MCP servers this lesson produces

Every lesson follows six beats. The Build It / Use It split is the spine — you implement the algorithm from scratch first, then run the same thing through the production library. You understand what the framework is doing because you wrote the smaller version yourself.

%%{init: {'theme':'base','themeVariables':{'primaryColor':'#fafaf5','primaryTextColor':'#1a1a1a','primaryBorderColor':'#3553ff','lineColor':'#3553ff','fontFamily':'JetBrains Mono','fontSize':'13px'}}}%%
flowchart LR
  M["MOTTO  
one-line core idea"] --> Pr["PROBLEM  
concrete pain"]
  Pr --> C["CONCEPT  
diagrams &amp; intuition"]
  C --> B["BUILD IT  
raw math, no frameworks"]
  B --> U["USE IT  
same thing in PyTorch / sklearn"]
  U --> S["SHIP IT  
prompt · skill · agent · MCP"]

Every lesson ships something

Other curricula end with "congratulations, you learned X." Each lesson here ends with a reusable tool you can install or paste into your daily workflow.

FIG_001.A prompts
FIG_001 · A
PROMPTS

FIG_001.B skills
FIG_001 · B
SKILLS

FIG_001.C agents
FIG_001 · C
AGENTS

FIG_001.D MCP servers
FIG_001 · D
MCP SERVERS

Paste into any AI assistant for expert-level help on a narrow task.

Drop into Claude, Cursor, Codex, OpenClaw, Hermes, or any agent that reads SKILL.md.

Deploy as autonomous workers — you wrote the loop yourself in Phase 14.

Plug into any MCP-compatible client. Built end-to-end in Phase 13.

Install lesson artifacts

The lesson artifacts. The repo ships 400 skills and 100 prompts under phases/**/outputs/; install them via scripts/install_skills.py. Requires cloning the repo. Supports tag filters, dry-runs, and per-agent layouts:

python3 scripts/install_skills.py                                  # every skill, default --layout skills (nested)
python3 scripts/install_skills.py  --layout skills                 # same as above, explicit
python3 scripts/install_skills.py  --type all                      # skills + prompts + agents
python3 scripts/install_skills.py  --phase 14                      # one phase only
python3 scripts/install_skills.py  --tag rag                       # filter by tag
python3 scripts/install_skills.py  --layout flat                   # flat files
python3 scripts/install_skills.py  --dry-run                       # preview without writing
python3 scripts/install_skills.py  --force                         # overwrite existing files

`` is the skills directory for your agent (examples: ~/.claude/skills/, ~/.cursor/skills/, ~/.config/openclaw/skills/, .skills/, or any path your agent reads).

By default the script refuses to overwrite an existing destination and exits with code 1 after listing every colliding path. Use --dry-run to preview collisions or --force to overwrite. Every non-dry-run run writes a manifest.json in the target with the full inventory grouped by type and phase. Pick the layout your agent reads:

`--layout`	Path written
`skills`	`//SKILL.md` (nested convention, supported by Claude / Cursor / Codex / OpenClaw / Hermes)
`by-phase`	`/phase-NN/.md`
`flat`	`/.md`

Drop the agent workbench into your own repo

The Phase 14 capstone ships a reusable Agent Workbench pack (AGENTS.md, schemas, init / verify / handoff scripts). Scaffold it into any repo with:

python3 scripts/scaffold_workbench.py path/to/your-repo            # full pack + seeds
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

You get the seven workbench surfaces wired up, a starter task_board.json, and a fresh agent_state.json at schema_version: 1. From there: edit the task, edit AGENTS.md, run scripts/init_agent.py, hand the contract to your agent. The pack source lives at phases/14-agent-engineering/42-agent-workbench-capstone/outputs/agent-workbench-pack/.

Browse the entire course as JSON

scripts/build_catalog.py walks every phase, every lesson, every artifact on disk and writes catalog.json at the repo root. One file, every course truth.

python3 scripts/build_catalog.py               # writes /catalog.json
python3 scripts/build_catalog.py --stdout      # to stdout, do not touch repo
python3 scripts/build_catalog.py --out path/to/file.json

The catalog is filesystem-derived, not README-derived, so counts always match what is actually on disk. Use it for site builds, downstream tooling, or to verify the README counts have not drifted. Schema is documented at the top of the script.

The curriculum workflow builds catalog.json as an ephemeral, gitignored artifact. Do not commit it. The same workflow runs audit_lessons.py as a blocking check.

Smoke-check every lesson's Python code

scripts/lesson_run.py byte-compiles every .py file under each lesson's code/ directory. Default mode is syntax-check only — no execution, no API keys, no heavy ML deps required. Catches the regressions contributors introduce most often (bad indentation, broken f-strings, stray edits).

python3 scripts/lesson_run.py                  # syntax-check the whole curriculum
python3 scripts/lesson_run.py --phase 14       # one phase only
python3 scripts/lesson_run.py --json           # JSON report on stdout
python3 scripts/lesson_run.py --strict         # exit 1 if any lesson fails
python3 scripts/lesson_run.py --execute        # actually run, 10s timeout per lesson

--execute runs each lesson's code/main.py (or the first .py file) with a 10-second timeout. Lessons whose entry file starts with a # requires: pkg1, pkg2 comment listing non-stdlib deps are skipped with reason needs . The script is opt-in and not wired into CI.

Stdlib only, 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 aggressively block automated HEAD/GET).

Foundational papers and protocols

Attention Is All You Need — Vaswani et al., 2017 → Phase 7
Language Models are Few-Shot Learners (GPT-3) → Phase 10
Denoising Diffusion Probabilistic Models → Phase 8
InstructGPT / RLHF → Phase 10
Direct Preference Optimization → Phase 10
Chain-of-Thought Prompting → Phase 11
ReAct: Reasoning + Acting in LLMs → Phase 14
Model Context Protocol — Anthropic → Phase 13

Contributing

Goal	Read
Contribute a lesson or fix	CONTRIBUTING.md
Fork for your team or school	FORKING.md
Lesson template	LESSON_TEMPLATE.md
Track progress	ROADMAP.md
Glossary	glossary/terms.md
Code of conduct	CODE_OF_CONDUCT.md

Before submitting a lesson, run the invariant check:

python3 scripts/audit_lessons.py           # full curriculum
python3 scripts/audit_lessons.py --phase 14  # single phase
python3 scripts/audit_lessons.py --json    # CI-friendly output

Exit code is non-zero when any rule fails. Rules (L001–L010) validate directory shape, docs/en.md presence + H1, code/ non-emptiness, quiz.json schema (rejects the legacy q/choices/answer keys that caused issue #102), and relative links inside lesson docs.

Sponsor the work

114,584 readers · 181,995 page views in the last 30 days · as of 2026-08-29

Free, MIT-licensed, 528 lessons. Thank you to the sponsors and backers who make the work possible. See all sponsors and backers.

Want to support the work? See sponsorship options, including hardware sponsorships, or sponsor on GitHub.

If this manual helped you, star the repo. It keeps the project alive.

License

MIT. Use it however you want — fork it, teach it, sell it, ship it. Attribution appreciated, not required.

Maintained by Rohit Ghumare and the community.

@ghumare64 · aiengineeringfromscratch.com · Report / Suggest

ai-engineering-from-scratch

Sponsors