rohitg00--ai-engineering-from-scratch/ROADMAP.md

# Roadmap

Status tracker for every phase and lesson. The status glyphs in this file feed
the website (`site/build.js` parses them into `site/data.js`); do not change
their shape.

Total estimated time: ~314 hours, at your own pace.

**Legend:** ✅ Complete  ·  🚧 In Progress  ·  ⬚ Planned

## Phase 0: Setup & Tooling — ✅ (~14 hours)

| # | Lesson | Status | Est. |
|---|--------|--------|------|
| 01 | Dev Environment | ✅ | ~75 min |
| 02 | Git & Collaboration | ✅ | ~45 min |
| 03 | GPU Setup & Cloud | ✅ | ~75 min |
| 04 | APIs & Keys | ✅ | ~75 min |
| 05 | Jupyter Notebooks | ✅ | ~75 min |
| 06 | Python Environments | ✅ | ~75 min |
| 07 | Docker for AI | ✅ | ~75 min |
| 08 | Editor Setup | ✅ | ~75 min |
| 09 | Data Management | ✅ | ~75 min |
| 10 | Terminal & Shell | ✅ | ~45 min |
| 11 | Linux for AI | ✅ | ~45 min |
| 12 | Debugging & Profiling | ✅ | ~75 min |

## Phase 1: Math Foundations — ✅ (~23 hours)

| # | Lesson | Status | Est. |
|---|--------|--------|------|
| 01 | Linear Algebra Intuition | ✅ | ~45 min |
| 02 | Vectors, Matrices & Operations | ✅ | ~75 min |
| 03 | Matrix Transformations & Eigenvalues | ✅ | ~75 min |
| 04 | Calculus for ML — Derivatives & Gradients | ✅ | ~45 min |
| 05 | Chain Rule & Automatic Differentiation | ✅ | ~75 min |
| 06 | Probability & Distributions | ✅ | ~45 min |
| 07 | Bayes' Theorem & Statistical Thinking | ✅ | ~75 min |
| 08 | Optimization — Gradient Descent Family | ✅ | ~75 min |
| 09 | Information Theory — Entropy, KL Divergence | ✅ | ~45 min |
| 10 | Dimensionality Reduction — PCA, t-SNE, UMAP | ✅ | ~75 min |
| 11 | Singular Value Decomposition | ✅ | ~75 min |
| 12 | Tensor Operations | ✅ | ~75 min |
| 13 | Numerical Stability | ✅ | ~45 min |
| 14 | Norms & Distances | ✅ | ~45 min |
| 15 | Statistics for ML | ✅ | ~45 min |
| 16 | Sampling Methods | ✅ | ~75 min |
| 17 | Linear Systems | ✅ | ~75 min |
| 18 | Convex Optimization | ✅ | ~75 min |
| 19 | Complex Numbers for AI | ✅ | ~45 min |
| 20 | The Fourier Transform | ✅ | ~75 min |
| 21 | Graph Theory for ML | ✅ | ~45 min |
| 22 | Stochastic Processes | ✅ | ~45 min |

## Phase 2: ML Fundamentals — ✅ (~21 hours)

| # | Lesson | Status | Est. |
|---|--------|--------|------|
| 01 | What Is Machine Learning — Types & Taxonomy | ✅ | ~45 min |
| 02 | Linear Regression from Scratch | ✅ | ~75 min |
| 03 | Logistic Regression & Classification | ✅ | ~75 min |
| 04 | Decision Trees & Random Forests | ✅ | ~75 min |
| 05 | Support Vector Machines | ✅ | ~75 min |
| 06 | K-Nearest Neighbors & Distance Metrics | ✅ | ~75 min |
| 07 | Unsupervised Learning — K-Means, DBSCAN | ✅ | ~75 min |
| 08 | Feature Engineering & Selection | ✅ | ~75 min |
| 09 | Model Evaluation — Metrics, Cross-Validation | ✅ | ~75 min |
| 10 | Bias, Variance & the Learning Curve | ✅ | ~45 min |
| 11 | Ensemble Methods — Boosting, Bagging, Stacking | ✅ | ~75 min |
| 12 | Hyperparameter Tuning & AutoML | ✅ | ~75 min |
| 13 | ML Pipelines & Experiment Tracking | ✅ | ~75 min |
| 14 | Naive Bayes — Multinomial, Gaussian, Bernoulli | ✅ | ~75 min |
| 15 | Time Series Fundamentals | ✅ | ~45 min |
| 16 | Anomaly Detection | ✅ | ~75 min |
| 17 | Handling Imbalanced Data | ✅ | ~75 min |
| 18 | Feature Selection | ✅ | ~75 min |

## Phase 3: Deep Learning Core — ✅ (~15 hours)

| # | Lesson | Status | Est. |
|---|--------|--------|------|
| 01 | The Perceptron — Where It All Started | ✅ | ~45 min |
| 02 | Multi-Layer Networks & Forward Pass | ✅ | ~75 min |
| 03 | Backpropagation from Scratch | ✅ | ~75 min |
| 04 | Activation Functions — ReLU, Sigmoid, GELU & Why | ✅ | ~45 min |
| 05 | Loss Functions — MSE, Cross-Entropy, Contrastive | ✅ | ~45 min |
| 06 | Optimizers — SGD, Momentum, Adam, AdamW | ✅ | ~75 min |
| 07 | Regularization — Dropout, Weight Decay, BatchNorm | ✅ | ~75 min |
| 08 | Weight Initialization & Training Stability | ✅ | ~45 min |
| 09 | Learning Rate Schedules & Warmup | ✅ | ~45 min |
| 10 | Build Your Own Mini Framework | ✅ | ~120 min |
| 11 | Introduction to PyTorch | ✅ | ~75 min |
| 12 | Introduction to JAX | ✅ | ~75 min |
| 13 | Debugging Neural Networks | ✅ | ~75 min |

## Phase 4: Computer Vision — ✅ (~27 hours)

| # | Lesson | Status | Est. |
|---|--------|--------|------|
| 01 | Image Fundamentals — Pixels, Channels, Color Spaces | ✅ | ~45 min |
| 02 | Convolutions from Scratch | ✅ | ~75 min |
| 03 | CNNs — LeNet to ResNet | ✅ | ~75 min |
| 04 | Image Classification | ✅ | ~75 min |
| 05 | Transfer Learning & Fine-Tuning | ✅ | ~75 min |
| 06 | Object Detection — YOLO from Scratch | ✅ | ~75 min |
| 07 | Semantic Segmentation — U-Net | ✅ | ~75 min |
| 08 | Instance Segmentation — Mask R-CNN | ✅ | ~75 min |
| 09 | Image Generation — GANs | ✅ | ~75 min |
| 10 | Image Generation — Diffusion Models | ✅ | ~75 min |
| 11 | Stable Diffusion — Architecture & Fine-Tuning | ✅ | ~75 min |
| 12 | Video Understanding — Temporal Modeling | ✅ | ~45 min |
| 13 | 3D Vision — Point Clouds, NeRFs | ✅ | ~45 min |
| 14 | Vision Transformers (ViT) | ✅ | ~45 min |
| 15 | Real-Time Vision — Edge Deployment | ✅ | ~75 min |
| 16 | Build a Complete Vision Pipeline | ✅ | ~120 min |
| 17 | Self-Supervised Vision — SimCLR, DINO, MAE | ✅ | ~75 min |
| 18 | Open-Vocabulary Vision — CLIP | ✅ | ~45 min |
| 19 | OCR & Document Understanding | ✅ | ~45 min |
| 20 | Image Retrieval & Metric Learning | ✅ | ~45 min |
| 21 | Keypoint Detection & Pose Estimation | ✅ | ~45 min |
| 22 | 3D Gaussian Splatting from Scratch | ✅ | ~90 min |
| 23 | Diffusion Transformers & Rectified Flow | ✅ | ~75 min |
| 24 | SAM 3 & Open-Vocabulary Segmentation | ✅ | ~60 min |
| 25 | Vision-Language Models (ViT-MLP-LLM) | ✅ | ~75 min |
| 26 | Monocular Depth & Geometry Estimation | ✅ | ~60 min |
| 27 | Multi-Object Tracking & Video Memory | ✅ | ~60 min |
| 28 | World Models & Video Diffusion | ✅ | ~75 min |

## Phase 5: NLP — Foundations to Advanced — ✅ (~30 hours)

| # | Lesson | Status | Est. |
|---|--------|--------|------|
| 01 | [Text Processing — Tokenization, Stemming, Lemmatization](phases/05-nlp-foundations-to-advanced/01-text-processing) | ✅ | ~45 min |
| 02 | [Bag of Words, TF-IDF & Text Representation](phases/05-nlp-foundations-to-advanced/02-bag-of-words-tfidf) | ✅ | ~75 min |
| 03 | [Word Embeddings — Word2Vec from Scratch](phases/05-nlp-foundations-to-advanced/03-word-embeddings-word2vec) | ✅ | ~75 min |
| 04 | [GloVe, FastText & Subword Embeddings](phases/05-nlp-foundations-to-advanced/04-glove-fasttext-subword) | ✅ | ~45 min |
| 05 | [Sentiment Analysis](phases/05-nlp-foundations-to-advanced/05-sentiment-analysis) | ✅ | ~75 min |
| 06 | [Named Entity Recognition (NER)](phases/05-nlp-foundations-to-advanced/06-named-entity-recognition) | ✅ | ~75 min |
| 07 | [POS Tagging & Syntactic Parsing](phases/05-nlp-foundations-to-advanced/07-pos-tagging-parsing) | ✅ | ~45 min |
| 08 | [Text Classification — CNNs & RNNs for Text](phases/05-nlp-foundations-to-advanced/08-cnns-rnns-for-text) | ✅ | ~75 min |
| 09 | [Sequence-to-Sequence Models](phases/05-nlp-foundations-to-advanced/09-sequence-to-sequence) | ✅ | ~75 min |
| 10 | [Attention Mechanism — The Breakthrough](phases/05-nlp-foundations-to-advanced/10-attention-mechanism) | ✅ | ~45 min |
| 11 | [Machine Translation](phases/05-nlp-foundations-to-advanced/11-machine-translation) | ✅ | ~75 min |
| 12 | [Text Summarization](phases/05-nlp-foundations-to-advanced/12-text-summarization) | ✅ | ~75 min |
| 13 | [Question Answering Systems](phases/05-nlp-foundations-to-advanced/13-question-answering) | ✅ | ~75 min |
| 14 | [Information Retrieval & Search](phases/05-nlp-foundations-to-advanced/14-information-retrieval-search) | ✅ | ~75 min |
| 15 | [Topic Modeling — LDA, BERTopic](phases/05-nlp-foundations-to-advanced/15-topic-modeling) | ✅ | ~45 min |
| 16 | [Text Generation — Language Models Before Transformers](phases/05-nlp-foundations-to-advanced/16-text-generation-pre-transformer) | ✅ | ~45 min |
| 17 | [Chatbots — Rule-Based to Neural](phases/05-nlp-foundations-to-advanced/17-chatbots-rule-to-neural) | ✅ | ~75 min |
| 18 | [Multilingual NLP](phases/05-nlp-foundations-to-advanced/18-multilingual-nlp) | ✅ | ~45 min |
| 19 | [Subword Tokenization — BPE, WordPiece, Unigram, SentencePiece](phases/05-nlp-foundations-to-advanced/19-subword-tokenization) | ✅ | ~60 min |
| 20 | [Structured Outputs & Constrained Decoding](phases/05-nlp-foundations-to-advanced/20-structured-outputs-constrained-decoding) | ✅ | ~60 min |
| 21 | [NLI & Textual Entailment](phases/05-nlp-foundations-to-advanced/21-nli-textual-entailment) | ✅ | ~60 min |
| 22 | [Embedding Models Deep Dive](phases/05-nlp-foundations-to-advanced/22-embedding-models-deep-dive) | ✅ | ~60 min |
| 23 | [Chunking Strategies for RAG](phases/05-nlp-foundations-to-advanced/23-chunking-strategies-rag) | ✅ | ~60 min |
| 24 | [Coreference Resolution](phases/05-nlp-foundations-to-advanced/24-coreference-resolution) | ✅ | ~60 min |
| 25 | [Entity Linking & Disambiguation](phases/05-nlp-foundations-to-advanced/25-entity-linking) | ✅ | ~60 min |
| 26 | [Relation Extraction & Knowledge Graph Construction](phases/05-nlp-foundations-to-advanced/26-relation-extraction-kg) | ✅ | ~60 min |
| 27 | [LLM Evaluation — RAGAS, DeepEval, G-Eval](phases/05-nlp-foundations-to-advanced/27-llm-evaluation-frameworks) | ✅ | ~75 min |
| 28 | [Long-Context Evaluation — NIAH, RULER, LongBench, MRCR](phases/05-nlp-foundations-to-advanced/28-long-context-evaluation) | ✅ | ~60 min |
| 29 | [Dialogue State Tracking](phases/05-nlp-foundations-to-advanced/29-dialogue-state-tracking) | ✅ | ~75 min |

## Phase 6: Speech & Audio — ✅ (~18 hours)

| # | Lesson | Status | Est. |
|---|--------|--------|------|
| 01 | [Audio Fundamentals — Waveforms, Sampling, Fourier Transform](phases/06-speech-and-audio/01-audio-fundamentals) | ✅ | ~45 min |
| 02 | [Spectrograms, Mel Scale & Audio Features](phases/06-speech-and-audio/02-spectrograms-mel-features) | ✅ | ~45 min |
| 03 | [Audio Classification](phases/06-speech-and-audio/03-audio-classification) | ✅ | ~75 min |
| 04 | [Speech Recognition (ASR)](phases/06-speech-and-audio/04-speech-recognition-asr) | ✅ | ~45 min |
| 05 | [Whisper — Architecture & Fine-Tuning](phases/06-speech-and-audio/05-whisper-architecture-finetuning) | ✅ | ~75 min |
| 06 | [Speaker Recognition & Verification](phases/06-speech-and-audio/06-speaker-recognition-verification) | ✅ | ~45 min |
| 07 | [Text-to-Speech (TTS)](phases/06-speech-and-audio/07-text-to-speech) | ✅ | ~75 min |
| 08 | [Voice Cloning & Voice Conversion](phases/06-speech-and-audio/08-voice-cloning-conversion) | ✅ | ~75 min |
| 09 | [Music Generation](phases/06-speech-and-audio/09-music-generation) | ✅ | ~75 min |
| 10 | [Audio-Language Models](phases/06-speech-and-audio/10-audio-language-models) | ✅ | ~45 min |
| 11 | [Real-Time Audio Processing](phases/06-speech-and-audio/11-real-time-audio-processing) | ✅ | ~75 min |
| 12 | [Build a Voice Assistant Pipeline](phases/06-speech-and-audio/12-voice-assistant-pipeline) | ✅ | ~120 min |
| 13 | [Neural Audio Codecs — EnCodec, SNAC, Mimi, DAC](phases/06-speech-and-audio/13-neural-audio-codecs) | ✅ | ~60 min |
| 14 | [Voice Activity Detection & Turn-Taking](phases/06-speech-and-audio/14-voice-activity-detection-turn-taking) | ✅ | ~45 min |
| 15 | [Streaming Speech-to-Speech — Moshi, Hibiki](phases/06-speech-and-audio/15-streaming-speech-to-speech-moshi-hibiki) | ✅ | ~75 min |
| 16 | [Voice Anti-Spoofing & Audio Watermarking](phases/06-speech-and-audio/16-anti-spoofing-audio-watermarking) | ✅ | ~75 min |
| 17 | [Audio Evaluation — WER, MOS, MMAU, Leaderboards](phases/06-speech-and-audio/17-audio-evaluation-metrics) | ✅ | ~60 min |

## Phase 7: Transformers Deep Dive — ✅ (~14 hours)

| # | Lesson | Status | Est. |
|---|--------|--------|------|
| 01 | [Why Transformers — The Problems with RNNs](phases/07-transformers-deep-dive/01-why-transformers) | ✅ | ~45 min |
| 02 | [Self-Attention from Scratch](phases/07-transformers-deep-dive/02-self-attention-from-scratch) | ✅ | ~75 min |
| 03 | [Multi-Head Attention](phases/07-transformers-deep-dive/03-multi-head-attention) | ✅ | ~75 min |
| 04 | [Positional Encoding — Sinusoidal, RoPE, ALiBi](phases/07-transformers-deep-dive/04-positional-encoding) | ✅ | ~45 min |
| 05 | [The Full Transformer — Encoder + Decoder](phases/07-transformers-deep-dive/05-full-transformer) | ✅ | ~75 min |
| 06 | [BERT — Masked Language Modeling](phases/07-transformers-deep-dive/06-bert-masked-language-modeling) | ✅ | ~45 min |
| 07 | [GPT — Causal Language Modeling](phases/07-transformers-deep-dive/07-gpt-causal-language-modeling) | ✅ | ~75 min |
| 08 | [T5, BART — Encoder-Decoder Models](phases/07-transformers-deep-dive/08-t5-bart-encoder-decoder) | ✅ | ~45 min |
| 09 | [Vision Transformers (ViT)](phases/07-transformers-deep-dive/09-vision-transformers) | ✅ | ~45 min |
| 10 | [Audio Transformers — Whisper Architecture](phases/07-transformers-deep-dive/10-audio-transformers-whisper) | ✅ | ~45 min |
| 11 | [Mixture of Experts (MoE)](phases/07-transformers-deep-dive/11-mixture-of-experts) | ✅ | ~45 min |
| 12 | [KV Cache, Flash Attention & Inference Optimization](phases/07-transformers-deep-dive/12-kv-cache-flash-attention) | ✅ | ~75 min |
| 13 | [Scaling Laws](phases/07-transformers-deep-dive/13-scaling-laws) | ✅ | ~45 min |
| 14 | [Build a Transformer from Scratch — The Capstone](phases/07-transformers-deep-dive/14-build-a-transformer-capstone) | ✅ | ~120 min |
| 15 | [Attention Variants — Sliding Window, Sparse, Differential](phases/07-transformers-deep-dive/15-attention-variants) | ✅ | ~60 min |
| 16 | [Speculative Decoding — Draft, Verify, Repeat](phases/07-transformers-deep-dive/16-speculative-decoding) | ✅ | ~60 min |

## Phase 8: Generative AI — ✅ (~14 hours)

| # | Lesson | Status | Est. |
|---|--------|--------|------|
| 01 | [Generative Models — Taxonomy & History](phases/08-generative-ai/01-generative-models-taxonomy-history/) | ✅ | ~45 min |
| 02 | [Autoencoders & VAE](phases/08-generative-ai/02-autoencoders-vae/) | ✅ | ~75 min |
| 03 | [GANs — Generator vs Discriminator](phases/08-generative-ai/03-gans-generator-discriminator/) | ✅ | ~75 min |
| 04 | [Conditional GANs & Pix2Pix](phases/08-generative-ai/04-conditional-gans-pix2pix/) | ✅ | ~75 min |
| 05 | [StyleGAN](phases/08-generative-ai/05-stylegan/) | ✅ | ~45 min |
| 06 | [Diffusion Models — DDPM from Scratch](phases/08-generative-ai/06-diffusion-ddpm-from-scratch/) | ✅ | ~75 min |
| 07 | [Latent Diffusion & Stable Diffusion](phases/08-generative-ai/07-latent-diffusion-stable-diffusion/) | ✅ | ~75 min |
| 08 | [ControlNet, LoRA & Image Conditioning](phases/08-generative-ai/08-controlnet-lora-conditioning/) | ✅ | ~75 min |
| 09 | [Inpainting, Outpainting & Image Editing](phases/08-generative-ai/09-inpainting-outpainting-editing/) | ✅ | ~75 min |
| 10 | [Video Generation](phases/08-generative-ai/10-video-generation/) | ✅ | ~45 min |
| 11 | [Audio Generation](phases/08-generative-ai/11-audio-generation/) | ✅ | ~45 min |
| 12 | [3D Generation](phases/08-generative-ai/12-3d-generation/) | ✅ | ~45 min |
| 13 | [Flow Matching & Rectified Flows](phases/08-generative-ai/13-flow-matching-rectified-flows/) | ✅ | ~45 min |
| 14 | [Evaluation — FID, CLIP Score, Human Preference](phases/08-generative-ai/14-evaluation-fid-clip-score/) | ✅ | ~45 min |
| 19 | [Visual Autoregressive Modeling (VAR): Next-Scale Prediction](phases/08-generative-ai/19-visual-autoregressive-var) | ✅ | ~90 min |

## Phase 9: Reinforcement Learning — ✅ (~13 hours)

| # | Lesson | Status | Est. |
|---|--------|--------|------|
| 01 | MDPs, States, Actions & Rewards | ✅ | ~45 min |
| 02 | Dynamic Programming | ✅ | ~75 min |
| 03 | Monte Carlo Methods | ✅ | ~75 min |
| 04 | Temporal Difference — Q-Learning, SARSA | ✅ | ~75 min |
| 05 | Deep Q-Networks (DQN) | ✅ | ~75 min |
| 06 | Policy Gradient Methods — REINFORCE | ✅ | ~75 min |
| 07 | Actor-Critic — A2C, A3C | ✅ | ~75 min |
| 08 | Proximal Policy Optimization (PPO) | ✅ | ~75 min |
| 09 | Reward Modeling & RLHF | ✅ | ~45 min |
| 10 | Multi-Agent RL | ✅ | ~45 min |
| 11 | Sim-to-Real Transfer | ✅ | ~45 min |
| 12 | RL for Games | ✅ | ~75 min |

## Phase 10: LLMs from Scratch — ✅ (~26 hours)

| # | Lesson | Status | Est. |
|---|--------|--------|------|
| 01 | [Tokenizers — BPE, WordPiece, SentencePiece](phases/10-llms-from-scratch/01-tokenizers) | ✅ | ~45 min |
| 02 | [Building a Tokenizer from Scratch](phases/10-llms-from-scratch/02-building-a-tokenizer) | ✅ | ~75 min |
| 03 | [Data Pipelines for Pre-Training](phases/10-llms-from-scratch/03-data-pipelines) | ✅ | ~75 min |
| 04 | [Pre-Training a Mini GPT (124M)](phases/10-llms-from-scratch/04-pre-training-mini-gpt) | ✅ | ~120 min |
| 05 | [Scaling — Distributed Training, FSDP, DeepSpeed](phases/10-llms-from-scratch/05-scaling-distributed) | ✅ | ~75 min |
| 06 | [Instruction Tuning — SFT](phases/10-llms-from-scratch/06-instruction-tuning-sft) | ✅ | ~75 min |
| 07 | [RLHF — Reward Model + PPO Training](phases/10-llms-from-scratch/07-rlhf) | ✅ | ~75 min |
| 08 | [DPO — Direct Preference Optimization](phases/10-llms-from-scratch/08-dpo) | ✅ | ~75 min |
| 09 | [Constitutional AI & Self-Improvement](phases/10-llms-from-scratch/09-constitutional-ai-self-improvement) | ✅ | ~45 min |
| 10 | [Evaluation — Benchmarks, Evals, LM Harness](phases/10-llms-from-scratch/10-evaluation) | ✅ | ~75 min |
| 11 | [Quantization — INT8, GPTQ, AWQ, GGUF](phases/10-llms-from-scratch/11-quantization) | ✅ | ~75 min |
| 12 | [Inference Optimization](phases/10-llms-from-scratch/12-inference-optimization) | ✅ | ~75 min |
| 13 | [Building a Complete LLM Pipeline](phases/10-llms-from-scratch/13-building-complete-llm-pipeline) | ✅ | ~120 min |
| 14 | [Open Models — Architecture Walkthroughs](phases/10-llms-from-scratch/14-open-models-architecture-walkthroughs) | ✅ | ~45 min |
| 15 | [Speculative Decoding and EAGLE-3](phases/10-llms-from-scratch/15-speculative-decoding-eagle3) | ✅ | ~75 min |
| 16 | [Differential Attention (V2)](phases/10-llms-from-scratch/16-differential-attention-v2) | ✅ | ~60 min |
| 17 | [Native Sparse Attention (DeepSeek NSA)](phases/10-llms-from-scratch/17-native-sparse-attention) | ✅ | ~60 min |
| 18 | [Multi-Token Prediction (MTP)](phases/10-llms-from-scratch/18-multi-token-prediction) | ✅ | ~60 min |
| 19 | [DualPipe Parallelism](phases/10-llms-from-scratch/19-dualpipe-parallelism) | ✅ | ~60 min |
| 20 | [DeepSeek-V3 Architecture Walkthrough](phases/10-llms-from-scratch/20-deepseek-v3-walkthrough) | ✅ | ~75 min |
| 21 | [Jamba — Hybrid SSM-Transformer](phases/10-llms-from-scratch/21-jamba-hybrid-ssm-transformer) | ✅ | ~60 min |
| 22 | [Async and Hogwild! Inference](phases/10-llms-from-scratch/22-async-hogwild-inference) | ✅ | ~60 min |
| 25 | [Speculative Decoding and EAGLE](phases/10-llms-from-scratch/25-speculative-decoding) | ✅ | ~75 min |
| 34 | [Gradient Checkpointing and Activation Recomputation](phases/10-llms-from-scratch/34-gradient-checkpointing) | ✅ | ~70 min |

## Phase 11: LLM Engineering — ✅ (~17 hours)

| # | Lesson | Status | Est. |
|---|--------|--------|------|
| 01 | [Prompt Engineering — Techniques & Patterns](phases/11-llm-engineering/01-prompt-engineering) | ✅ | ~45 min |
| 02 | [Few-Shot, Chain-of-Thought, Tree-of-Thought](phases/11-llm-engineering/02-few-shot-cot) | ✅ | ~45 min |
| 03 | [Structured Outputs](phases/11-llm-engineering/03-structured-outputs) | ✅ | ~75 min |
| 04 | [Embeddings & Vector Representations](phases/11-llm-engineering/04-embeddings) | ✅ | ~75 min |
| 05 | [Context Engineering](phases/11-llm-engineering/05-context-engineering) | ✅ | ~75 min |
| 06 | [RAG — Retrieval-Augmented Generation](phases/11-llm-engineering/06-rag) | ✅ | ~75 min |
| 07 | [Advanced RAG](phases/11-llm-engineering/07-advanced-rag) | ✅ | ~75 min |
| 08 | [Fine-Tuning with LoRA & QLoRA](phases/11-llm-engineering/08-fine-tuning-lora) | ✅ | ~75 min |
| 09 | [Function Calling & Tool Use](phases/11-llm-engineering/09-function-calling) | ✅ | ~75 min |
| 10 | [Evaluation & Testing LLM Applications](phases/11-llm-engineering/10-evaluation) | ✅ | ~45 min |
| 11 | [Caching, Rate Limiting & Cost Optimization](phases/11-llm-engineering/11-caching-cost) | ✅ | ~45 min |
| 12 | [Guardrails, Safety & Content Filtering](phases/11-llm-engineering/12-guardrails) | ✅ | ~45 min |
| 13 | [Building a Production LLM Application](phases/11-llm-engineering/13-production-app) | ✅ | ~120 min |
| 14 | [Model Context Protocol (MCP)](phases/11-llm-engineering/14-model-context-protocol) | ✅ | ~75 min |
| 15 | [Prompt Caching & Context Caching](phases/11-llm-engineering/15-prompt-caching) | ✅ | ~60 min |

## Phase 12: Multimodal AI — ✅ (~65 hours)

| # | Lesson | Status | Est. |
|---|--------|--------|------|
| 01 | [Vision Transformers and the Patch-Token Primitive](phases/12-multimodal-ai/01-vision-transformer-patch-tokens) | ✅ | ~120 min |
| 02 | [CLIP and Contrastive Vision-Language Pretraining](phases/12-multimodal-ai/02-clip-contrastive-pretraining) | ✅ | ~180 min |
| 03 | [BLIP-2 and Q-Former as Modality Bridge](phases/12-multimodal-ai/03-blip2-qformer-bridge) | ✅ | ~180 min |
| 04 | [Flamingo and Gated Cross-Attention](phases/12-multimodal-ai/04-flamingo-gated-cross-attention) | ✅ | ~120 min |
| 05 | [LLaVA and Visual Instruction Tuning](phases/12-multimodal-ai/05-llava-visual-instruction-tuning) | ✅ | ~180 min |
| 06 | [Any-Resolution Vision: Patch-n'-Pack and NaFlex](phases/12-multimodal-ai/06-any-resolution-patch-n-pack) | ✅ | ~120 min |
| 07 | [Open-Weight VLM Recipes: What Actually Matters](phases/12-multimodal-ai/07-open-weight-vlm-recipes) | ✅ | ~180 min |
| 08 | [LLaVA-OneVision: Single, Multi, Video](phases/12-multimodal-ai/08-llava-onevision-single-multi-video) | ✅ | ~180 min |
| 09 | [Qwen-VL Family and Dynamic-FPS Video](phases/12-multimodal-ai/09-qwen-vl-family-dynamic-fps) | ✅ | ~120 min |
| 10 | [InternVL3 Native Multimodal Pretraining](phases/12-multimodal-ai/10-internvl3-native-multimodal) | ✅ | ~120 min |
| 11 | [Chameleon and Early-Fusion Token-Only](phases/12-multimodal-ai/11-chameleon-early-fusion-tokens) | ✅ | ~180 min |
| 12 | [Emu3 Next-Token Prediction for Generation](phases/12-multimodal-ai/12-emu3-next-token-for-generation) | ✅ | ~120 min |
| 13 | [Transfusion Autoregressive + Diffusion](phases/12-multimodal-ai/13-transfusion-autoregressive-diffusion) | ✅ | ~180 min |
| 14 | [Show-o and Discrete-Diffusion Unified](phases/12-multimodal-ai/14-show-o-discrete-diffusion-unified) | ✅ | ~120 min |
| 15 | [Janus-Pro Decoupled Encoders](phases/12-multimodal-ai/15-janus-pro-decoupled-encoders) | ✅ | ~120 min |
| 16 | [MIO Any-to-Any Streaming](phases/12-multimodal-ai/16-mio-any-to-any-streaming) | ✅ | ~120 min |
| 17 | [Video-Language Temporal Grounding](phases/12-multimodal-ai/17-video-language-temporal-grounding) | ✅ | ~180 min |
| 18 | [Long-Video Understanding at Million-Token Context](phases/12-multimodal-ai/18-long-video-million-token) | ✅ | ~180 min |
| 19 | [Audio-Language Models: Whisper to AF3](phases/12-multimodal-ai/19-audio-language-whisper-to-af3) | ✅ | ~180 min |
| 20 | [Omni Models: Thinker-Talker](phases/12-multimodal-ai/20-omni-models-thinker-talker) | ✅ | ~180 min |
| 21 | [Embodied VLAs: RT-2, OpenVLA, π0, GR00T](phases/12-multimodal-ai/21-embodied-vlas-openvla-pi0-groot) | ✅ | ~180 min |
| 22 | [Document and Diagram Understanding](phases/12-multimodal-ai/22-document-diagram-understanding) | ✅ | ~180 min |
| 23 | [ColPali Vision-Native Document RAG](phases/12-multimodal-ai/23-colpali-vision-native-rag) | ✅ | ~180 min |
| 24 | [Multimodal RAG and Cross-Modal Retrieval](phases/12-multimodal-ai/24-multimodal-rag-cross-modal) | ✅ | ~180 min |
| 25 | [Multimodal Agents and Computer-Use (Capstone)](phases/12-multimodal-ai/25-multimodal-agents-computer-use) | ✅ | ~240 min |

## Phase 13: Tools & Protocols — ✅ (~24.5 hours)

| # | Lesson | Status | Est. |
|---|--------|--------|------|
| 01 | [The Tool Interface](phases/13-tools-and-protocols/01-the-tool-interface/) | ✅ | ~45 min |
| 02 | [Function Calling Deep Dive](phases/13-tools-and-protocols/02-function-calling-deep-dive/) | ✅ | ~75 min |
| 03 | [Parallel and Streaming Tool Calls](phases/13-tools-and-protocols/03-parallel-and-streaming-tool-calls/) | ✅ | ~75 min |
| 04 | [Structured Output](phases/13-tools-and-protocols/04-structured-output/) | ✅ | ~75 min |
| 05 | [Tool Schema Design](phases/13-tools-and-protocols/05-tool-schema-design/) | ✅ | ~45 min |
| 06 | [MCP Fundamentals](phases/13-tools-and-protocols/06-mcp-fundamentals/) | ✅ | ~45 min |
| 07 | [Building an MCP Server](phases/13-tools-and-protocols/07-building-an-mcp-server/) | ✅ | ~75 min |
| 08 | [Building an MCP Client](phases/13-tools-and-protocols/08-building-an-mcp-client/) | ✅ | ~75 min |
| 09 | [MCP Transports](phases/13-tools-and-protocols/09-mcp-transports/) | ✅ | ~45 min |
| 10 | [MCP Resources and Prompts](phases/13-tools-and-protocols/10-mcp-resources-and-prompts/) | ✅ | ~45 min |
| 11 | [MCP Sampling](phases/13-tools-and-protocols/11-mcp-sampling/) | ✅ | ~75 min |
| 12 | [MCP Roots and Elicitation](phases/13-tools-and-protocols/12-mcp-roots-and-elicitation/) | ✅ | ~45 min |
| 13 | [MCP Async Tasks](phases/13-tools-and-protocols/13-mcp-async-tasks/) | ✅ | ~75 min |
| 14 | [MCP Apps](phases/13-tools-and-protocols/14-mcp-apps/) | ✅ | ~75 min |
| 15 | [MCP Security I — Tool Poisoning](phases/13-tools-and-protocols/15-mcp-security-tool-poisoning/) | ✅ | ~45 min |
| 16 | [MCP Security II — OAuth 2.1](phases/13-tools-and-protocols/16-mcp-security-oauth-2-1/) | ✅ | ~75 min |
| 17 | [MCP Gateways and Registries](phases/13-tools-and-protocols/17-mcp-gateways-and-registries/) | ✅ | ~45 min |
| 18 | [MCP Auth in Production — Enrollment, JWKS Refresh, Audience Pinning](phases/13-tools-and-protocols/18-mcp-auth-production/) | ✅ | ~90 min |
| 19 | [A2A Protocol](phases/13-tools-and-protocols/19-a2a-protocol/) | ✅ | ~75 min |
| 20 | [OpenTelemetry GenAI](phases/13-tools-and-protocols/20-opentelemetry-genai/) | ✅ | ~75 min |
| 21 | [LLM Routing Layer](phases/13-tools-and-protocols/21-llm-routing-layer/) | ✅ | ~45 min |
| 22 | [Skills and Agent SDKs](phases/13-tools-and-protocols/22-skills-and-agent-sdks/) | ✅ | ~45 min |
| 23 | [Capstone — Tool Ecosystem](phases/13-tools-and-protocols/23-capstone-tool-ecosystem/) | ✅ | ~120 min |

## Phase 14: Agent Engineering — ✅ (~42 hours)

| # | Lesson | Status | Est. |
|---|--------|--------|------|
| 01 | The Agent Loop | ✅ | ~60 min |
| 02 | ReWOO and Plan-and-Execute | ✅ | ~60 min |
| 03 | Reflexion and Verbal Reinforcement Learning | ✅ | ~60 min |
| 04 | Tree of Thoughts and LATS | ✅ | ~75 min |
| 05 | Self-Refine and CRITIC | ✅ | ~60 min |
| 06 | Tool Use and Function Calling | ✅ | ~60 min |
| 07 | Memory — Virtual Context and MemGPT | ✅ | ~75 min |
| 08 | Memory Blocks and Sleep-Time Compute (Letta) | ✅ | ~75 min |
| 09 | Hybrid Memory — Vector + Graph + KV (Mem0) | ✅ | ~75 min |
| 10 | Skill Libraries and Lifelong Learning (Voyager) | ✅ | ~75 min |
| 11 | Planning with HTN and Evolutionary Search | ✅ | ~75 min |
| 12 | Anthropic's Workflow Patterns | ✅ | ~60 min |
| 13 | LangGraph — Stateful Graphs and Durable Execution | ✅ | ~75 min |
| 14 | AutoGen v0.4 — Actor Model | ✅ | ~75 min |
| 15 | CrewAI — Role-Based Crews and Flows | ✅ | ~60 min |
| 16 | OpenAI Agents SDK — Handoffs, Guardrails, Tracing | ✅ | ~75 min |
| 17 | Claude Agent SDK — Subagents and Session Store | ✅ | ~75 min |
| 18 | Agno and Mastra — Production Runtimes | ✅ | ~45 min |
| 19 | Benchmarks — SWE-bench, GAIA, AgentBench | ✅ | ~60 min |
| 20 | Benchmarks — WebArena and OSWorld | ✅ | ~60 min |
| 21 | Computer Use — Claude, OpenAI CUA, Gemini | ✅ | ~60 min |
| 22 | Voice Agents — Pipecat and LiveKit | ✅ | ~60 min |
| 23 | OpenTelemetry GenAI Semantic Conventions | ✅ | ~60 min |
| 24 | Agent Observability — Langfuse, Phoenix, Opik | ✅ | ~45 min |
| 25 | Multi-Agent Debate and Collaboration | ✅ | ~60 min |
| 26 | Failure Modes — Why Agents Break | ✅ | ~60 min |
| 27 | Prompt Injection and the PVE Defense | ✅ | ~75 min |
| 28 | Orchestration Patterns — Supervisor, Swarm, Hierarchical | ✅ | ~60 min |
| 29 | Production Runtimes — Queue, Event, Cron | ✅ | ~60 min |
| 30 | Eval-Driven Agent Development | ✅ | ~60 min |
| 31 | Agent Workbench: Why Capable Models Still Fail | ✅ | ~45 min |
| 32 | The Minimal Agent Workbench | ✅ | ~45 min |
| 33 | Agent Instructions as Executable Constraints | ✅ | ~50 min |
| 34 | Repo Memory and Durable State | ✅ | ~60 min |
| 35 | Initialization Scripts for Agents | ✅ | ~45 min |
| 36 | Scope Contracts and Task Boundaries | ✅ | ~50 min |
| 37 | Runtime Feedback Loops | ✅ | ~50 min |
| 38 | Verification Gates | ✅ | ~55 min |
| 39 | Reviewer Agent: Separate Builder from Marker | ✅ | ~55 min |
| 40 | Multi-Session Handoff | ✅ | ~50 min |
| 41 | The Workbench on a Real Repo | ✅ | ~60 min |
| 42 | Capstone: Ship a Reusable Agent Workbench Pack | ✅ | ~75 min |

## Phase 15: Autonomous Systems — ✅ (~20 hours)

| # | Lesson | Status | Est. |
|---|--------|--------|------|
| 01 | From Chatbots to Long-Horizon Agents (METR) | ✅ | ~45 min |
| 02 | STaR, V-STaR, Quiet-STaR — Self-Taught Reasoning | ✅ | ~60 min |
| 03 | AlphaEvolve — Evolutionary Coding Agents | ✅ | ~60 min |
| 04 | Darwin Gödel Machine — Self-Modifying Agents | ✅ | ~60 min |
| 05 | AI Scientist v2 — Workshop-Level Research | ✅ | ~60 min |
| 06 | Automated Alignment Research (Anthropic AAR) | ✅ | ~60 min |
| 07 | Recursive Self-Improvement — Capability vs Alignment | ✅ | ~60 min |
| 08 | Bounded Self-Improvement Designs | ✅ | ~60 min |
| 09 | Autonomous Coding Agent Landscape (SWE-bench, CodeAct) | ✅ | ~45 min |
| 10 | Claude Code Permission Modes and Auto Mode | ✅ | ~45 min |
| 11 | Browser Agents and Indirect Prompt Injection | ✅ | ~45 min |
| 12 | Durable Execution for Long-Running Agents | ✅ | ~60 min |
| 13 | Action Budgets, Iteration Caps, Cost Governors | ✅ | ~60 min |
| 14 | Kill Switches, Circuit Breakers, Canary Tokens | ✅ | ~60 min |
| 15 | HITL — Propose-Then-Commit | ✅ | ~60 min |
| 16 | Checkpoints and Rollback | ✅ | ~60 min |
| 17 | Constitutional AI and Rule Overrides | ✅ | ~60 min |
| 18 | Llama Guard and Input/Output Classification | ✅ | ~45 min |
| 19 | Anthropic Responsible Scaling Policy v3.0 | ✅ | ~45 min |
| 20 | OpenAI Preparedness Framework and DeepMind FSF | ✅ | ~45 min |
| 21 | METR Time Horizons and External Evaluation | ✅ | ~60 min |
| 22 | CAIS, CAISI, and Societal-Scale Risk | ✅ | ~45 min |

## Phase 16: Multi-Agent & Swarms — ✅ (~28 hours)

| # | Lesson | Status | Est. |
|---|--------|--------|------|
| 01 | [Why Multi-Agent](phases/16-multi-agent-and-swarms/01-why-multi-agent/) | ✅ | ~45 min |
| 02 | [FIPA-ACL Heritage and Speech Acts](phases/16-multi-agent-and-swarms/02-fipa-acl-heritage/) | ✅ | ~60 min |
| 03 | [Communication Protocols](phases/16-multi-agent-and-swarms/03-communication-protocols/) | ✅ | ~45 min |
| 04 | [The Multi-Agent Primitive Model](phases/16-multi-agent-and-swarms/04-primitive-model/) | ✅ | ~60 min |
| 05 | [Supervisor / Orchestrator-Worker Pattern](phases/16-multi-agent-and-swarms/05-supervisor-orchestrator-pattern/) | ✅ | ~75 min |
| 06 | [Hierarchical Architecture and Decomposition Drift](phases/16-multi-agent-and-swarms/06-hierarchical-architecture/) | ✅ | ~60 min |
| 07 | [Society of Mind and Multi-Agent Debate](phases/16-multi-agent-and-swarms/07-society-of-mind-debate/) | ✅ | ~75 min |
| 08 | [Role Specialization — Planner / Critic / Executor / Verifier](phases/16-multi-agent-and-swarms/08-role-specialization/) | ✅ | ~75 min |
| 09 | [Parallel Swarm and Networked Architectures](phases/16-multi-agent-and-swarms/09-parallel-swarm-networks/) | ✅ | ~60 min |
| 10 | [Group Chat and Speaker Selection](phases/16-multi-agent-and-swarms/10-group-chat-speaker-selection/) | ✅ | ~60 min |
| 11 | [Handoffs and Routines (Stateless Orchestration)](phases/16-multi-agent-and-swarms/11-handoffs-and-routines/) | ✅ | ~60 min |
| 12 | [A2A — The Agent-to-Agent Protocol](phases/16-multi-agent-and-swarms/12-a2a-protocol/) | ✅ | ~75 min |
| 13 | [Shared Memory and Blackboard Patterns](phases/16-multi-agent-and-swarms/13-shared-memory-blackboard/) | ✅ | ~75 min |
| 14 | [Consensus and Byzantine Fault Tolerance for Agents](phases/16-multi-agent-and-swarms/14-consensus-and-bft/) | ✅ | ~75 min |
| 15 | [Voting, Self-Consistency, and Debate Topology](phases/16-multi-agent-and-swarms/15-voting-debate-topology/) | ✅ | ~75 min |
| 16 | [Negotiation and Bargaining](phases/16-multi-agent-and-swarms/16-negotiation-bargaining/) | ✅ | ~75 min |
| 17 | [Generative Agents and Emergent Simulation](phases/16-multi-agent-and-swarms/17-generative-agents-simulation/) | ✅ | ~75 min |
| 18 | [Theory of Mind and Emergent Coordination](phases/16-multi-agent-and-swarms/18-theory-of-mind-coordination/) | ✅ | ~75 min |
| 19 | [Swarm Optimization for LLMs (PSO, ACO)](phases/16-multi-agent-and-swarms/19-swarm-optimization-pso-aco/) | ✅ | ~75 min |
| 20 | [MARL — MADDPG, QMIX, MAPPO](phases/16-multi-agent-and-swarms/20-marl-maddpg-qmix-mappo/) | ✅ | ~90 min |
| 21 | [Agent Economies, Token Incentives, Reputation](phases/16-multi-agent-and-swarms/21-agent-economies/) | ✅ | ~75 min |
| 22 | [Production Scaling — Queues, Checkpoints, Durability](phases/16-multi-agent-and-swarms/22-production-scaling-queues-checkpoints/) | ✅ | ~75 min |
| 23 | [Failure Modes — MAST, Groupthink, Monoculture, Cascading](phases/16-multi-agent-and-swarms/23-failure-modes-mast-groupthink/) | ✅ | ~75 min |
| 24 | [Evaluation and Coordination Benchmarks](phases/16-multi-agent-and-swarms/24-evaluation-coordination-benchmarks/) | ✅ | ~75 min |
| 25 | [Case Studies and 2026 State of the Art](phases/16-multi-agent-and-swarms/25-case-studies-2026-sota/) | ✅ | ~90 min |

## Phase 17: Infrastructure & Production — ✅ (~32 hours)

| # | Lesson | Status | Est. |
|---|--------|--------|------|
| 01 | Managed LLM Platforms — Bedrock, Azure OpenAI, Vertex AI | ✅ | ~60 min |
| 02 | Inference Platform Economics — Fireworks, Together, Baseten, Modal | ✅ | ~60 min |
| 03 | GPU Autoscaling on Kubernetes — Karpenter, KAI Scheduler | ✅ | ~75 min |
| 04 | vLLM Serving Internals — PagedAttention, Continuous Batching, Chunked Prefill | ✅ | ~75 min |
| 05 | EAGLE-3 Speculative Decoding in Production | ✅ | ~60 min |
| 06 | SGLang and RadixAttention for Prefix-Heavy Workloads | ✅ | ~60 min |
| 07 | TensorRT-LLM on Blackwell with FP8 and NVFP4 | ✅ | ~75 min |
| 08 | Inference Metrics — TTFT, TPOT, ITL, Goodput, P99 | ✅ | ~60 min |
| 09 | Production Quantization — AWQ, GPTQ, GGUF, FP8, NVFP4 | ✅ | ~75 min |
| 10 | Cold Start Mitigation for Serverless LLMs | ✅ | ~60 min |
| 11 | Multi-Region LLM Serving and KV Cache Locality | ✅ | ~60 min |
| 12 | Edge Inference — ANE, Hexagon, WebGPU, Jetson | ✅ | ~60 min |
| 13 | LLM Observability Stack Selection | ✅ | ~60 min |
| 14 | Prompt Caching and Semantic Caching Economics | ✅ | ~60 min |
| 15 | Batch APIs — the 50% Discount as Industry Standard | ✅ | ~45 min |
| 16 | Model Routing as a Cost-Reduction Primitive | ✅ | ~60 min |
| 17 | Disaggregated Prefill/Decode — NVIDIA Dynamo and llm-d | ✅ | ~75 min |
| 18 | vLLM Production Stack with LMCache KV Offloading | ✅ | ~60 min |
| 19 | AI Gateways — LiteLLM, Portkey, Kong, Bifrost | ✅ | ~60 min |
| 20 | Shadow, Canary, and Progressive Deployment | ✅ | ~60 min |
| 21 | A/B Testing LLM Features — GrowthBook and Statsig | ✅ | ~60 min |
| 22 | Load Testing LLM APIs — k6, LLMPerf, GenAI-Perf | ✅ | ~75 min |
| 23 | SRE for AI — Multi-Agent Incident Response | ✅ | ~60 min |
| 24 | Chaos Engineering for LLM Production | ✅ | ~60 min |
| 25 | Security — Secrets, PII Scrubbing, Audit Logs | ✅ | ~60 min |
| 26 | Compliance — SOC 2, HIPAA, GDPR, EU AI Act, ISO 42001 | ✅ | ~60 min |
| 27 | FinOps for LLMs — Unit Economics and Multi-Tenant Attribution | ✅ | ~60 min |
| 28 | Self-Hosted Serving Selection — llama.cpp, Ollama, TGI, vLLM, SGLang | ✅ | ~45 min |

## Phase 18: Ethics, Safety & Alignment — ✅ (~31 hours)

| # | Lesson | Status | Est. |
|---|--------|--------|------|
| 01 | [Instruction-Following as Alignment Signal](phases/18-ethics-safety-alignment/01-instruction-following-alignment-signal) | ✅ | ~45 min |
| 02 | [Reward Hacking & Goodhart's Law](phases/18-ethics-safety-alignment/02-reward-hacking-goodhart) | ✅ | ~60 min |
| 03 | [Direct Preference Optimization Family](phases/18-ethics-safety-alignment/03-direct-preference-optimization-family) | ✅ | ~60 min |
| 04 | [Sycophancy as RLHF Amplification](phases/18-ethics-safety-alignment/04-sycophancy-rlhf-amplification) | ✅ | ~45 min |
| 05 | [Constitutional AI & RLAIF](phases/18-ethics-safety-alignment/05-constitutional-ai-rlaif) | ✅ | ~60 min |
| 06 | [Mesa-Optimization & Deceptive Alignment](phases/18-ethics-safety-alignment/06-mesa-optimization-deceptive-alignment) | ✅ | ~75 min |
| 07 | [Sleeper Agents — Persistent Deception](phases/18-ethics-safety-alignment/07-sleeper-agents-persistent-deception) | ✅ | ~60 min |
| 08 | [In-Context Scheming in Frontier Models](phases/18-ethics-safety-alignment/08-in-context-scheming-frontier-models) | ✅ | ~60 min |
| 09 | [Alignment Faking](phases/18-ethics-safety-alignment/09-alignment-faking) | ✅ | ~60 min |
| 10 | [AI Control — Safety Despite Subversion](phases/18-ethics-safety-alignment/10-ai-control-subversion) | ✅ | ~75 min |
| 11 | [Scalable Oversight & Weak-to-Strong Generalization](phases/18-ethics-safety-alignment/11-scalable-oversight-weak-to-strong) | ✅ | ~60 min |
| 12 | [Red-Teaming — PAIR & Automated Attacks](phases/18-ethics-safety-alignment/12-red-teaming-pair-automated-attacks) | ✅ | ~75 min |
| 13 | [Many-Shot Jailbreaking](phases/18-ethics-safety-alignment/13-many-shot-jailbreaking) | ✅ | ~45 min |
| 14 | [ASCII Art & Visual Jailbreaks](phases/18-ethics-safety-alignment/14-ascii-art-visual-jailbreaks) | ✅ | ~60 min |
| 15 | [Indirect Prompt Injection](phases/18-ethics-safety-alignment/15-indirect-prompt-injection) | ✅ | ~75 min |
| 16 | [Red-Team Tooling — Garak, Llama Guard, PyRIT](phases/18-ethics-safety-alignment/16-red-team-tooling-garak-llamaguard-pyrit) | ✅ | ~75 min |
| 17 | [WMDP & Dual-Use Capability Evaluation](phases/18-ethics-safety-alignment/17-wmdp-dual-use-evaluation) | ✅ | ~60 min |
| 18 | [Frontier Safety Frameworks — RSP, PF, FSF](phases/18-ethics-safety-alignment/18-frontier-safety-frameworks-rsp-pf-fsf) | ✅ | ~75 min |
| 19 | [Model Welfare Research](phases/18-ethics-safety-alignment/19-model-welfare-research) | ✅ | ~45 min |
| 20 | [Bias & Representational Harm](phases/18-ethics-safety-alignment/20-bias-representational-harm) | ✅ | ~60 min |
| 21 | [Fairness Criteria — Group, Individual, Counterfactual](phases/18-ethics-safety-alignment/21-fairness-criteria-group-individual-counterfactual) | ✅ | ~60 min |
| 22 | [Differential Privacy for LLMs](phases/18-ethics-safety-alignment/22-differential-privacy-for-llms) | ✅ | ~60 min |
| 23 | [Watermarking — SynthID, Stable Signature, C2PA](phases/18-ethics-safety-alignment/23-watermarking-synthid-stable-signature-c2pa) | ✅ | ~75 min |
| 24 | [Regulatory Frameworks — EU, US, UK, Korea](phases/18-ethics-safety-alignment/24-regulatory-frameworks-eu-us-uk-korea) | ✅ | ~75 min |
| 25 | [EchoLeak & CVEs for AI](phases/18-ethics-safety-alignment/25-echoleak-cves-for-ai) | ✅ | ~45 min |
| 26 | [Model, System & Dataset Cards](phases/18-ethics-safety-alignment/26-model-system-dataset-cards) | ✅ | ~60 min |
| 27 | [Data Provenance & Training-Data Governance](phases/18-ethics-safety-alignment/27-data-provenance-training-governance) | ✅ | ~60 min |
| 28 | [Alignment Research Ecosystem — MATS, Redwood, Apollo, METR](phases/18-ethics-safety-alignment/28-alignment-research-ecosystem) | ✅ | ~45 min |
| 29 | [Moderation Systems — OpenAI, Perspective, Llama Guard](phases/18-ethics-safety-alignment/29-moderation-systems-openai-perspective-llamaguard) | ✅ | ~60 min |
| 30 | [Dual-Use Risk — Cyber, Bio, Chem, Nuclear](phases/18-ethics-safety-alignment/30-dual-use-risk-cyber-bio-chem-nuclear) | ✅ | ~75 min |

## Phase 19: Capstone Projects — ✅ (~620 hours)

| # | Project | Status | Est. |
|---|---------|--------|------|
| 01 | [Terminal-Native Coding Agent](phases/19-capstone-projects/01-terminal-native-coding-agent) | ✅ | ~35 hr |
| 02 | [RAG over Codebase (Cross-Repo Semantic Search)](phases/19-capstone-projects/02-rag-over-codebase) | ✅ | ~30 hr |
| 03 | [Real-Time Voice Assistant (ASR to LLM to TTS)](phases/19-capstone-projects/03-realtime-voice-assistant) | ✅ | ~30 hr |
| 04 | [Multimodal Document QA (Vision-First)](phases/19-capstone-projects/04-multimodal-document-qa) | ✅ | ~30 hr |
| 05 | [Autonomous Research Agent (AI-Scientist Class)](phases/19-capstone-projects/05-autonomous-research-agent) | ✅ | ~40 hr |
| 06 | [DevOps Troubleshooting Agent for Kubernetes](phases/19-capstone-projects/06-devops-troubleshooting-agent) | ✅ | ~30 hr |
| 07 | [End-to-End Fine-Tuning Pipeline](phases/19-capstone-projects/07-end-to-end-fine-tuning-pipeline) | ✅ | ~35 hr |
| 08 | [Production RAG Chatbot (Regulated Vertical)](phases/19-capstone-projects/08-production-rag-chatbot) | ✅ | ~30 hr |
| 09 | [Code Migration Agent (Repo-Level Upgrade)](phases/19-capstone-projects/09-code-migration-agent) | ✅ | ~30 hr |
| 10 | [Multi-Agent Software Engineering Team](phases/19-capstone-projects/10-multi-agent-software-team) | ✅ | ~40 hr |
| 11 | [LLM Observability & Eval Dashboard](phases/19-capstone-projects/11-llm-observability-dashboard) | ✅ | ~25 hr |
| 12 | [Video Understanding Pipeline (Scene to QA)](phases/19-capstone-projects/12-video-understanding-pipeline) | ✅ | ~30 hr |
| 13 | [MCP Server with Registry and Governance](phases/19-capstone-projects/13-mcp-server-with-registry) | ✅ | ~25 hr |
| 14 | [Speculative-Decoding Inference Server](phases/19-capstone-projects/14-speculative-decoding-server) | ✅ | ~30 hr |
| 15 | [Constitutional Safety Harness + Red-Team Range](phases/19-capstone-projects/15-constitutional-safety-harness) | ✅ | ~25 hr |
| 16 | [GitHub Issue-to-PR Autonomous Agent](phases/19-capstone-projects/16-github-issue-to-pr-agent) | ✅ | ~30 hr |
| 17 | [Personal AI Tutor (Adaptive, Multimodal)](phases/19-capstone-projects/17-personal-ai-tutor) | ✅ | ~30 hr |
| 20 | [Agent Harness Loop Contract](phases/19-capstone-projects/20-agent-harness-loop-contract) | ✅ | ~90 min |
| 21 | [Tool Registry with Schema Validation](phases/19-capstone-projects/21-tool-registry-schema-validation) | ✅ | ~90 min |
| 22 | [JSON-RPC 2.0 Over Newline-Delimited Stdio](phases/19-capstone-projects/22-jsonrpc-stdio-transport) | ✅ | ~90 min |
| 23 | [Function Call Dispatcher](phases/19-capstone-projects/23-function-call-dispatcher) | ✅ | ~90 min |
| 24 | [Plan-Execute Control Flow](phases/19-capstone-projects/24-plan-execute-control-flow) | ✅ | ~90 min |
| 25 | [Verification Gates and the Observation Budget](phases/19-capstone-projects/25-verification-gates-observation-budget) | ✅ | ~90 min |
| 26 | [Sandbox Runner with Denylist and Path Jail](phases/19-capstone-projects/26-sandbox-runner-denylist) | ✅ | ~90 min |
| 27 | [Eval Harness with Fixture Tasks](phases/19-capstone-projects/27-eval-harness-fixture-tasks) | ✅ | ~90 min |
| 28 | [Observability with OTel GenAI Spans and Prometheus Metrics](phases/19-capstone-projects/28-observability-otel-traces) | ✅ | ~90 min |
| 29 | [End-to-End Coding Agent on the Harness](phases/19-capstone-projects/29-end-to-end-coding-task-demo) | ✅ | ~90 min |
| 30 | [BPE Tokenizer From Scratch](phases/19-capstone-projects/30-bpe-tokenizer-from-scratch) | ✅ | ~90 min |
| 31 | [Tokenized Dataset with Sliding Window](phases/19-capstone-projects/31-tokenized-dataset-sliding-window) | ✅ | ~90 min |
| 32 | [Token and Positional Embeddings](phases/19-capstone-projects/32-token-positional-embeddings) | ✅ | ~90 min |
| 33 | [Multi-Head Self-Attention](phases/19-capstone-projects/33-multihead-self-attention) | ✅ | ~90 min |
| 34 | [Transformer Block from Scratch](phases/19-capstone-projects/34-transformer-block) | ✅ | ~90 min |
| 35 | [GPT Model Assembly](phases/19-capstone-projects/35-gpt-model-assembly) | ✅ | ~90 min |
| 36 | [Training Loop and Evaluation](phases/19-capstone-projects/36-training-loop-eval) | ✅ | ~90 min |
| 37 | [Loading Pretrained Weights](phases/19-capstone-projects/37-loading-pretrained-weights) | ✅ | ~90 min |
| 38 | [Classifier Fine-Tuning by Head Swap](phases/19-capstone-projects/38-classifier-finetuning) | ✅ | ~90 min |
| 39 | [Instruction Tuning by Supervised Fine-Tuning](phases/19-capstone-projects/39-instruction-tuning-sft) | ✅ | ~90 min |
| 40 | [Direct Preference Optimization from Scratch](phases/19-capstone-projects/40-dpo-from-scratch) | ✅ | ~90 min |
| 41 | [Full Evaluation Pipeline](phases/19-capstone-projects/41-eval-pipeline) | ✅ | ~90 min |
| 42 | [Large Corpus Downloader](phases/19-capstone-projects/42-large-corpus-downloader) | ✅ | ~90 min |
| 43 | [HDF5 Tokenized Corpus](phases/19-capstone-projects/43-hdf5-tokenized-corpus) | ✅ | ~90 min |
| 44 | [Cosine LR with Linear Warmup](phases/19-capstone-projects/44-cosine-lr-warmup) | ✅ | ~90 min |
| 45 | [Gradient Clipping and Mixed Precision](phases/19-capstone-projects/45-gradient-clipping-amp) | ✅ | ~90 min |
| 46 | [Gradient Accumulation](phases/19-capstone-projects/46-gradient-accumulation) | ✅ | ~90 min |
| 47 | [Checkpoint Save and Resume](phases/19-capstone-projects/47-checkpoint-save-resume) | ✅ | ~90 min |
| 48 | [Distributed Data Parallel and FSDP from Scratch](phases/19-capstone-projects/48-distributed-fsdp-ddp) | ✅ | ~90 min |
| 49 | [Language Model Evaluation Harness](phases/19-capstone-projects/49-lm-eval-harness) | ✅ | ~90 min |
| 50 | [Hypothesis Generator](phases/19-capstone-projects/50-hypothesis-generator) | ✅ | ~90 min |
| 51 | [Literature Retrieval](phases/19-capstone-projects/51-literature-retrieval) | ✅ | ~90 min |
| 52 | [Experiment Runner](phases/19-capstone-projects/52-experiment-runner) | ✅ | ~90 min |
| 53 | [Result Evaluator](phases/19-capstone-projects/53-result-evaluator) | ✅ | ~90 min |
| 54 | [Paper Writer](phases/19-capstone-projects/54-paper-writer) | ✅ | ~90 min |
| 55 | [Critic Loop](phases/19-capstone-projects/55-critic-loop) | ✅ | ~90 min |
| 56 | [Iteration Scheduler](phases/19-capstone-projects/56-iteration-scheduler) | ✅ | ~90 min |
| 57 | [End-to-End Research Demo](phases/19-capstone-projects/57-end-to-end-research-demo) | ✅ | ~90 min |
| 58 | [Vision Encoder Patches](phases/19-capstone-projects/58-vision-encoder-patches) | ✅ | ~90 min |
| 59 | [Vision Transformer Encoder](phases/19-capstone-projects/59-vit-transformer) | ✅ | ~90 min |
| 60 | [Projection Layer for Modality Alignment](phases/19-capstone-projects/60-projection-layer-modality-align) | ✅ | ~90 min |
| 61 | [Cross-Attention Fusion](phases/19-capstone-projects/61-cross-attention-fusion) | ✅ | ~90 min |
| 62 | [Vision-Language Pretraining](phases/19-capstone-projects/62-vision-language-pretraining) | ✅ | ~90 min |
| 63 | [Multimodal Evaluation](phases/19-capstone-projects/63-multimodal-eval) | ✅ | ~90 min |
| 64 | [Chunking Strategies, Compared](phases/19-capstone-projects/64-chunking-strategies-advanced) | ✅ | ~90 min |
| 65 | [Hybrid Retrieval with BM25 and Dense Embeddings](phases/19-capstone-projects/65-hybrid-retrieval-bm25-dense) | ✅ | ~90 min |
| 66 | [Cross-Encoder Reranker](phases/19-capstone-projects/66-reranker-cross-encoder) | ✅ | ~90 min |
| 67 | [Query Rewriting: HyDE, Multi-Query, and Decomposition](phases/19-capstone-projects/67-query-rewriting-hyde) | ✅ | ~90 min |
| 68 | [RAG Evaluation: Precision, Recall, MRR, nDCG, Faithfulness, Answer Relevance](phases/19-capstone-projects/68-rag-eval-precision-recall) | ✅ | ~90 min |
| 69 | [End-to-End RAG System](phases/19-capstone-projects/69-end-to-end-rag-system) | ✅ | ~90 min |
| 70 | [Task Spec Format](phases/19-capstone-projects/70-task-spec-format) | ✅ | ~90 min |
| 71 | [Classical Metrics](phases/19-capstone-projects/71-classical-metrics) | ✅ | ~90 min |
| 72 | [Code Exec Metric](phases/19-capstone-projects/72-code-exec-metric) | ✅ | ~90 min |
| 73 | [Perplexity and Calibration](phases/19-capstone-projects/73-perplexity-calibration) | ✅ | ~90 min |
| 74 | [Leaderboard Aggregation](phases/19-capstone-projects/74-leaderboard-aggregation) | ✅ | ~90 min |
| 75 | [End-to-End Eval Runner](phases/19-capstone-projects/75-end-to-end-eval-runner) | ✅ | ~90 min |
| 76 | [Collective Ops From Scratch](phases/19-capstone-projects/76-collective-ops-from-scratch) | ✅ | ~90 min |
| 77 | [Data Parallel DDP From Scratch](phases/19-capstone-projects/77-data-parallel-ddp) | ✅ | ~90 min |
| 78 | [ZeRO Optimizer State Sharding](phases/19-capstone-projects/78-zero-parameter-sharding) | ✅ | ~90 min |
| 79 | [Pipeline Parallel and Bubble Analysis](phases/19-capstone-projects/79-pipeline-parallel) | ✅ | ~90 min |
| 80 | [Sharded Checkpoint and Atomic Resume](phases/19-capstone-projects/80-checkpoint-sharded-resume) | ✅ | ~90 min |
| 81 | [End-to-End Distributed Training](phases/19-capstone-projects/81-end-to-end-distributed-train) | ✅ | ~90 min |
| 82 | [Jailbreak Taxonomy](phases/19-capstone-projects/82-jailbreak-taxonomy) | ✅ | ~90 min |
| 83 | [Prompt Injection Detector](phases/19-capstone-projects/83-prompt-injection-detector) | ✅ | ~90 min |
| 84 | [Refusal Evaluation](phases/19-capstone-projects/84-refusal-evaluation) | ✅ | ~90 min |
| 85 | [Content Classifier Integration](phases/19-capstone-projects/85-content-classifier-integration) | ✅ | ~90 min |
| 86 | [Constitutional Rules Engine](phases/19-capstone-projects/86-constitutional-rules-engine) | ✅ | ~90 min |
| 87 | [End-to-End Safety Gate](phases/19-capstone-projects/87-end-to-end-safety-gate) | ✅ | ~90 min |

---

**Total: 20 phases, 503 lessons | 503 complete | ~1,050 hours estimated**

Want to help? Pick any ⬚ lesson and submit a PR. See [CONTRIBUTING.md](CONTRIBUTING.md).