Follow a practical sequence from fundamentals to modern AI systems. Understand the concepts, build real things, and know what you should be able to prove next.
The learning path
Use the sequence when you're starting from scratch. Jump into a topic directly when you already have the foundations.
Build the core ideas: data, regression, classification, evaluation, features, and generalization.
Algorithms · Data · EvaluationMove into neural networks, training, PyTorch, CNNs, transformers, and representation learning.
Neural Networks · PyTorch · TransformersLearn how modern generative systems work and how to build useful applications around them.
Generation · RAG · AgentsUnderstand tokens, attention, embeddings, inference, evaluation, fine-tuning, and production use.
LLMs · RAG · EvaluationTurn models into reliable software with APIs, deployment, observability, security, and MLOps.
Systems · Deployment · MLOpsStart here
MCP explained for AI engineers: architecture, clients, servers, tools, resources, prompts, transports, authorization, security, real-world use cases, and how to build your first MCP integration.
Explore by topic
Each topic connects explanations with the next thing you should learn or build.
Build the core ideas: data, regression, classification, evaluation, features, and generalization.
Explore topicMove into neural networks, training, PyTorch, CNNs, transformers, and representation learning.
Explore topicLearn how modern generative systems work and how to build useful applications around them.
Explore topicUnderstand tokens, attention, embeddings, inference, evaluation, fine-tuning, and production use.
Explore topicTurn models into reliable software with APIs, deployment, observability, security, and MLOps.
Explore topicDon't stop at reading
When you understand something, build it. When you build it, evaluate it. When you can explain the result, you have evidence.
Continue learning
AI agents explained from the ground up: how agents plan, use tools, manage context, take actions, handle failures, and how developers can build reliable agentic AI systems.
Machine Learning Engineer vs AI Engineer explained clearly: responsibilities, skills, tools, projects, career paths, and how to choose the right role.
A practical AI engineer skills guide covering software engineering, ML, LLMs, RAG, evaluation, deployment, systems, and problem solving.
Learn what AI engineers do, the skills they need, what they build, and how to start a practical AI engineering career.
