TECHBYTEBYBYTE

Learn AI. Byte by Byte.

Understand the concepts behind AI. Build with it. Learn it, byte by byte.

Start Learning →AI Vocabulary

Your AI Learning Path

From fundamentals to production AI

📘

1. AI Foundations

🧭Introduction to AI 🧮Mathematics for AI 🐍Python for AI 🤖Machine Learning 🧠Neural Networks & Deep Learning 📝Natural Language Processing

🔄

2. LLMs & Transformers

🔄Transformers 🧠Large Language Models ✍️Prompt Engineering

📚

3. RAG & Agents

🧩Embeddings & Vectors 📚RAG 🤖AI Agents

🚀

4. Agentic AI

🚀Agentic AI 👥Multi-Agent Systems 🧩Agent Design Patterns 🔗LangGraph 🔌MCP 🛡️Production Agentic AI

Learn step by step. Build as you go.

View full roadmap →

LEARNING PATHS

Explore AI. Build your foundation. Go deeper.

Start with the fundamentals, understand how the pieces connect, and gradually explore modern AI, LLMs, RAG and agentic AI.

AI fundamentals

Introduction to AI

Understand AI, ML, deep learning, LLMs and how the major pieces of modern AI fit together.

Mathematics for AI

Learn the algebra, vectors, probability, statistics and optimization concepts needed for AI.

Python for AI

Learn Python, NumPy, Pandas and the programming skills you need to build AI systems.

Machine Learning

Understand supervised learning, unsupervised learning, algorithms, training and evaluation.

Neural Networks

Understand neurons, weights, activation functions, forward propagation and backpropagation.

Deep Learning

Explore CNNs, RNNs, LSTMs and the architectures behind modern deep learning.

Natural Language Processing

Learn how machines represent, process and understand human language.

Transformer tutorials

Transformers

Understand attention, self-attention, multi-head attention and the Transformer architecture.

Large Language Models

Understand tokens, embeddings, logits, next-token prediction, training and inference.

Prompt Engineering

Learn how to communicate effectively with LLMs using structured and advanced prompting techniques.

Generative AI

Understand the concepts, architectures and applications behind modern generative AI.

Spring AI

Build AI applications with Spring Boot using ChatClient, RAG, tools, MCP and production patterns.

RAG

Learn how retrieval, embeddings, vector databases and LLMs work together to build RAG systems.

Agent tutorials

AI Agents

Understand agents, tools, memory, reasoning, planning and agent execution loops.

AI Engineering

Learn the engineering practices needed to build reliable, observable and production-ready AI systems.

Agentic AI

Understand agentic systems, planning, reasoning, memory, orchestration and autonomous workflows.

Multi-Agent Systems

Learn how multiple specialized agents communicate, collaborate and solve complex problems.

Design Patterns

Agent Design Patterns

Learn reusable patterns for designing reliable agentic AI systems.

LangChain

Build LLM and agent applications using LangChain and its ecosystem.

LangGraph

Build stateful, controllable and production-oriented agent workflows with LangGraph.

MCP

Understand Model Context Protocol and how AI systems connect to external tools and data.

QA Coding Questions

Practice frequently asked QA coding interview questions with clear, worked Java answers.

Playwright: Zero to Expert

Learn modern browser automation, API testing, debugging, CI/CD and production test architecture.

Ideas behind the technology

From the Blog

Engineering stories and practical explanations for readers who want to understand how modern AI really works.

View all articles →

How AI Works

Attention: How an LLM Decides Which Words Matter Right Now

A slow, number-by-number explanation of attention—from context and Query, Key and Value vectors to dot products, masking, softmax, multi-head attention and KV cache.

21 min readSeptember 11, 2026

How AI Works

Where Does an LLM Store ‘Paris Is the Capital of France’?

Follow one page from training data into tokens, gradients and model weights—and then watch those learned parameters answer a simple question.

18 min readSeptember 11, 2026

Three curves illustrating underfitting, a balanced fit, and overfitting to sample data

How AI Works

The Model Scored 99% in Practice—and Failed the Real Test

A slow, beginner-first explanation of underfitting, overfitting and generalization, with training curves, examples, diagnosis, fixes and modern AI connections.

20 min readSeptember 8, 2026