Course01 · 42/42 written
Computing Foundations
How computers, operating systems, the command line, networks, and developer tooling actually work — the bedrock every AI practitioner builds on.
One year. Nine courses. Every day.
A complete, self-paced path from how a computer actually works to shipping production AI systems — one substantial lesson and one hands-on lab every single day. No prerequisites beyond curiosity, and every lab runs on free and open-source tools.
365days
52weeks
9courses
210lessons written
210labs released
The whole year, end to end
where this takes you
The nine courses
foundations → production
Course02 · 56/56 written
Programming with Python
From first program to tested, packaged, database-backed applications — the working programming skill AI work demands.
Course03 · 42/42 written
Math, Statistics, and Data
The linear algebra, calculus, probability, and data-analysis skills that make machine learning understandable rather than magical.
Course04 · 56/56 written
Machine Learning
Classical machine learning done properly: models, evaluation, feature work, and the discipline that separates working systems from leaderboard tricks.
Course05 · 14/42 written
Deep Learning
Neural networks from first principles to transformers: build them, train them, debug them, and understand the hardware they run on.
Course06 · 0/49 written
LLMs and Generative AI
Large language models as a working material: how they are made, how to prompt and call them, how to ground them with retrieval, customize them, and go multimodal.
Course07 · 0/42 written
AI Engineering: Agents and Applications
Agents, MCP, AI coding tools, evaluation, and full-stack AI applications — engineering AI systems that hold up in production.
Course08 · 0/21 written
Deployment, MLOps, and Security
Containers, cloud, CI/CD, monitoring, and the security discipline AI systems demand in the real world.
Course09 · 0/15 written
Capstone
Two weeks to design, build, evaluate, secure, deploy, and present a complete AI application of your own.
How this works
what you get each day
A lesson you can read in one sitting
Written prose, not slides — with worked examples, a quiz to check yourself, and a glossary of every term it introduces.
A lab you actually run
Starter files with numbered exercises, a reference implementation, automated tests that exit zero when you are done, and genuinely captured expected output.
Honest progress
Days that are titled but not yet written are marked planned, never dressed up as finished. The counters above are computed from what is actually on disk.
The full curriculum
every day, in order
Computing Foundations 42/42
How Computers Work
1 How a Computer Works: From Transistors to Programs 2 The CPU: Fetch, Decode, Execute 3 Memory Hierarchy: Registers, RAM, and Storage 4 Binary and Data Representation: Bits, Bytes, and Numbers 5 Text, Images, and Sound as Data 6 Operating Systems: What They Do and Why 7 Processes, Threads, and Scheduling 8 Meet the Terminal: Shells, Prompts, and Commands 9 Navigating the Filesystem: Paths, Files, and Permissions 10 Working with Text: cat, grep, sed, and Pipes 11 Environment Variables and Shell Configuration 12 Shell Scripting: Variables, Loops, and Conditionals 13 Package Managers: Homebrew, apt, and winget 14 Automating Tasks with Shell Scripts and cron
Networks and the Internet
15 What Happens When You Load a Web Page 16 IP Addresses, DNS, and Routing 17 TCP, UDP, and Ports 18 HTTP: Requests, Responses, and Methods 19 HTTPS and TLS: Encryption on the Wire 20 How Browsers Render: HTML, CSS, and JavaScript 21 Inspecting Traffic with curl and Developer Tools 22 What an API Is and Why Everything Has One 23 REST Fundamentals: Resources and Verbs 24 JSON and Data Serialization 25 API Authentication: Keys, Tokens, and OAuth 26 Webhooks and Event-Driven APIs 27 Rate Limits, Pagination, and Error Handling 28 Consuming a Public API from the Command Line
Developer Workflow
29 Why Version Control Exists 30 Git Fundamentals: Repositories, Staging, and Commits 31 Branching and Merging 32 Remotes and GitHub 33 Pull Requests and Code Review 34 Undoing Things: Reset, Revert, and Reflog 35 Git Workflows for Real Projects 36 Choosing and Configuring a Code Editor 37 Debuggers, Linters, and Formatters 38 Regular Expressions 39 Data Storage: Files, Databases, Object Storage, and Caches 40 Observability: Logs, Metrics, Traces, and Dashboards 41 Thinking in Automation: Scripts, Hooks, and Pipelines 42 Section Review: Your Computing Foundations Toolkit
Programming with Python 56/56
Python Basics
43 Installing Python and Virtual Environments 44 Variables and Types 45 Strings and Text Processing 46 Numbers, Math, and Precision 47 Input, Output, and f-strings 48 Reading Error Messages and Debugging 49 Your First Real Program 50 Conditionals and Boolean Logic 51 Loops: for, while, and Iteration Patterns 52 Lists in Depth 53 Dictionaries in Depth 54 Tuples, Sets, and Choosing a Collection 55 Comprehensions and Iterator Thinking 56 Building a Data-Driven CLI 57 Functions: Definition, Arguments, and Return Values 58 Scope, Closures, and *args/**kwargs 59 Modules, Imports, and Project Layout 60 A Tour of the Standard Library 61 Writing Readable Code 62 Recursion 63 Designing a Small Program Well
Python in Practice
64 Reading and Writing Files 65 CSV and JSON in the Real World 66 Exceptions and Error Handling Strategy 67 Classes and Objects 68 Inheritance, Composition, and Dunder Methods 69 Dataclasses and Type Hints 70 Modeling a Domain with Objects 71 Why Test, and pytest Basics 72 Fixtures, Parametrization, and Test Design 73 Test-Driven Development 74 Mocking and Testing Boundaries 75 Static Typing with mypy 76 Linting and Formatting with Ruff 77 Quality Gates for a Python Project 78 HTTP in Python with requests 79 Web Scraping Responsibly 80 Building CLIs with argparse 81 Scheduling and Background Jobs 82 A First Web API with FastAPI 83 Packaging and Distributing Python Code 84 Shipping an Automation Toolkit
Data and Databases
85 Relational Databases and SQLite 86 SELECT: Filtering, Sorting, and Aggregating 87 Joins and Relationships 88 Inserting, Updating, and Schema Design 89 Indexes and Query Performance 90 SQLite from Python 91 Designing and Querying a Real Schema 92 Beyond Tables: NoSQL and Key-Value Stores 93 ORMs and SQLAlchemy 94 Data Validation with pydantic 95 Dates, Times, and Time Zones 96 Concurrency and async Basics 97 Logging and Configuration 98 Section Project: A Complete Data Pipeline
Math, Statistics, and Data 42/42
Mathematics for AI
99 Vectors: Direction, Magnitude, and Meaning 100 Matrices and What They Represent 101 Matrix Multiplication 102 Linear Transformations 103 Dot Products and Similarity 104 NumPy: Arrays and Vectorized Thinking 105 Transforming Images with Matrices 106 Eigenvalues and Eigenvectors, Intuitively 107 Norms, Distances, and Similarity Measures 108 Derivatives: Rates of Change 109 Partial Derivatives and Gradients 110 The Chain Rule 111 Gradient Descent from Scratch 112 Visualizing Optimization 113 Probability: Events, Rules, and Intuition 114 Random Variables and Distributions 115 Bayes’ Theorem 116 Descriptive Statistics That Don’t Lie 117 Sampling and the Central Limit Theorem 118 Hypothesis Tests and Confidence Intervals 119 Analyzing an Experiment End to End
Data Analysis
120 pandas: Series and DataFrames 121 Loading and Inspecting Data 122 Selecting and Filtering 123 Groupby and Aggregation 124 Merging and Reshaping 125 Cleaning Messy Data 126 A Reproducible Cleaning Pipeline 127 Why We Visualize, and Choosing the Right Chart 128 Matplotlib Fundamentals 129 Statistical Plots with seaborn 130 Distributions and Relationships 131 Time Series Visualization 132 Visual Storytelling and Chart Honesty 133 Building an EDA Report 134 Finding Data: Open Datasets and APIs 135 From API to DataFrame 136 The Exploratory Data Analysis Process 137 Thinking in Features 138 Data Ethics, Bias, and Provenance 139 Reproducible Notebooks 140 Section Project: An Exploratory Study
Machine Learning 56/56
Core Concepts
141 What Machine Learning Is and Is Not 142 Supervised, Unsupervised, and Reinforcement Learning 143 The Machine Learning Workflow 144 Train, Validation, and Test Splits 145 Overfitting and Underfitting 146 Your First Model with scikit-learn 147 An End-to-End Classification Exercise 148 Linear Regression 149 Loss Functions and Least Squares 150 Multiple and Polynomial Regression 151 Regularization: Ridge and Lasso 152 Regression Metrics 153 Linear Regression from Scratch 154 A Complete Regression Project 155 Logistic Regression 156 Decision Boundaries 157 k-Nearest Neighbors 158 Naive Bayes and Text Classification 159 Precision, Recall, ROC, and Choosing Thresholds 160 Class Imbalance 161 A Complete Classification Project
Supervised Learning in Depth
162 Decision Trees 163 Random Forests 164 Gradient Boosting 165 XGBoost and LightGBM in Practice 166 Hyperparameter Tuning 167 Cross-Validation Done Right 168 Winning on Tabular Data 169 Support Vector Machines 170 Feature Scaling and Encoding 171 Feature Engineering 172 Feature Selection 173 scikit-learn Pipelines 174 Handling Missing Data 175 Features Beat Algorithms 176 Choosing the Right Metric 177 Learning Curves and Diagnostics 178 Interpreting Models: Importances and SHAP 179 Fairness and Bias in Models 180 Data Leakage 181 Baselines and Error Analysis 182 Writing a Model Report
Beyond Supervised Learning
183 Clustering with k-means 184 Hierarchical Clustering and DBSCAN 185 Principal Component Analysis 186 t-SNE and UMAP 187 Anomaly Detection 188 Recommender Systems 189 A Segmentation Study 190 The ML Project Lifecycle 191 Building Datasets and Labeling 192 Time Series Forecasting Basics 193 Saving and Versioning Models 194 Serving a Model over an API 195 Monitoring Models in Production 196 Section Project: An ML Service
Deep Learning 14/42
Neural Networks
197 The Perceptron 198 Activation Functions 199 Forward Propagation 200 Backpropagation 201 A Neural Network in Pure NumPy 202 PyTorch Tensors 203 Training MNIST from Scratch 204 PyTorch: autograd and nn.Module 205 Datasets and DataLoaders 206 Optimizers: SGD to Adam 207 Learning Rate Schedules 208 Dropout, Batch Norm, and Regularization 209 Debugging Training Runs 210 A Disciplined Training Project 211 Convolutions 212 CNN Architectures 213 Transfer Learning 214 Data Augmentation 215 Training a Vision Model End to End 216 Beyond Classification: Detection and Segmentation 217 Your Own Image Classifier
Sequence Models and Transformers
218 Text Preprocessing and Tokenization 219 Word Embeddings 220 Recurrent Neural Networks 221 LSTMs and GRUs 222 Sequence-to-Sequence and Early Attention 223 Text Classification with Embeddings 224 A Sentiment Analysis Project 225 “Attention Is All You Need” 226 Self-Attention, Step by Step 227 The Transformer Architecture 228 Encoder Models: BERT and Friends 229 Decoder Models: The GPT Family 230 Hugging Face Transformers in Practice 231 Fine-Tuning a Small Transformer 232 GPUs and AI Hardware 233 Mixed Precision and Performance 234 Distributed Training Concepts 235 Experiment Tracking 236 Quantization and Distillation 237 Scaling Laws and What They Bought Us 238 Section Project: Reproducing a Paper
LLMs and Generative AI 0/49
Working with LLMs
239 How Large Language Models Are Trained 240 Pretraining, Fine-Tuning, and RLHF 241 The Model Landscape: Claude, GPT, Gemini, Llama 242 Open Weights versus Closed APIs 243 Tokens, Context Windows, and Sampling 244 Capabilities, Limits, and Hallucination 245 Benchmarking Models Yourself 246 Prompting Fundamentals 247 System Prompts and Role Design 248 Few-Shot Examples and Chain of Thought 249 Structured Output: Getting Reliable JSON 250 Prompt Patterns and Templates 251 Prompt Injection and Safe Prompting 252 A Tested Prompt Library 253 First Calls to the Claude API 254 The OpenAI-Compatible Ecosystem 255 Streaming Responses 256 Tool Use and Function Calling 257 Working with Images and Documents 258 Cost, Caching, and Rate Limits 259 Building a CLI Assistant
Retrieval and Customization
260 What Embeddings Are 261 Semantic Similarity Search 262 Vector Databases 263 Chunking Strategies 264 Hybrid Search and Rerankers 265 Evaluating Retrieval Quality 266 Semantic Search over Your Own Notes 267 The RAG Architecture 268 A Minimal RAG System from Scratch 269 RAG over PDFs and Messy Documents 270 Citations and Grounded Answers 271 Advanced RAG Patterns 272 Evaluating RAG Systems 273 A Documentation Assistant 274 Prompting versus RAG versus Fine-Tuning 275 Fine-Tuning with LoRA 276 Building Fine-Tuning Datasets 277 Running Local Models with Ollama 278 Quantized Inference and llama.cpp 279 Serving Open Models 280 Fine-Tune and Serve Your Own Model
Multimodal and Frontier
281 How Diffusion Models Generate Images 282 Image Generation in Practice 283 Speech: Recognition and Synthesis 284 Video and Music Generation 285 Multimodal Models 286 Generative AI Ethics and Copyright 287 Section Project: A Multimodal Application
AI Engineering: Agents and Applications 0/42
Agents and Tools
288 What an AI Agent Is 289 The Agent Loop: Reason, Act, Observe 290 Designing Tools for Agents 291 An Agent from Scratch 292 Agent Frameworks and When to Use Them 293 Multi-Agent Systems 294 Building a Research Agent 295 What MCP Is and Why It Exists 296 Using MCP Servers 297 Building an MCP Server 298 MCP Resources and Prompts 299 Building an MCP Client 300 MCP Security 301 Your Personal MCP Server 302 The AI Coding Landscape 303 Working with a Coding Agent 304 Effective Agentic Coding Workflows 305 Configuring Agents: Memory, Skills, and Rules 306 Reviewing and Trusting AI-Written Code 307 Coding Agents in CI and Automation 308 Shipping a Feature with an Agent
Production AI Systems
309 Why Evals Are the Real Moat 310 Building Evaluation Datasets 311 LLM-as-Judge 312 Regression Testing for Prompts and Models 313 Guardrails and Content Moderation 314 Observability and Tracing for AI 315 An Evaluation Harness 316 Architecture of an AI Product 317 Backend Patterns for LLM Apps 318 Chat UX and Streaming Frontends 319 Auth, Quotas, and Billing 320 Latency and Caching 321 Vendor Abstraction and Fallbacks 322 A Full-Stack AI Application 323 Data Ingestion Pipelines 324 Document Processing at Scale 325 Keeping Indexes Fresh 326 Scaling Retrieval 327 Cost Engineering for AI Systems 328 Privacy in AI Systems 329 Section Project: A Production Assistant
Deployment, MLOps, and Security 0/21
Deploying AI Systems
330 Docker Fundamentals 331 Dockerizing an AI Application 332 Docker Compose for Multi-Service Apps 333 Kubernetes Concepts 334 Cloud Options and Free Tiers 335 CI/CD with GitHub Actions 336 A Containerized AI Deployment 337 Deploying to a Cloud Service 338 GPU Serving and Inference Infrastructure 339 Monitoring and Alerting 340 Logging and Analytics for AI Features 341 Rollouts, A/B Tests, and Feature Flags 342 Incidents and Rollbacks 343 A Monitored Production Deployment
Securing AI Systems
344 Threat Modeling AI Systems 345 Defending Against Prompt Injection 346 Data Privacy and PII Handling 347 Model and Supply Chain Security 348 AI Governance and Regulation 349 Red Teaming Your Own Systems 350 Section Project: A Security Review
Capstone 0/15
Capstone Project
351 Choosing and Scoping Your Capstone 352 Architecture and Design Document 353 Data and Retrieval Layer 354 Core AI Features 355 Agent and Tool Integration 356 Tests and Evals for Your Capstone 357 Milestone Review and Course Correction 358 Frontend and User Experience 359 Deploying Your Capstone 360 Monitoring and Cost Controls 361 Security Review of Your Capstone 362 Documentation and Demo 363 Portfolio, Resume, and Sharing Your Work 364 Capstone Retrospective 365 Graduation: Your AI Roadmap Going Forward