See before you buy
Every note opens with a free five-page preview
Flip through the first pages right in your browser — zoom in, step through pages, and judge the quality before you order.
Learning categories
Pick your battlefield
From Python foundations to AI system design — each category is a focused library of handwritten notes.
Python for AI Engineering
Python foundations, tooling and the AI engineering stack.
Machine Learning Fundamentals
Core ML concepts, algorithms and evaluation, explained from a developer's lens.
Deep Learning
Backpropagation, optimisation and training deep models by hand.
Mathematics for AI
Linear algebra, calculus and probability you actually need for AI.
Neural Networks
Architectures, activations and training dynamics, sketched clearly.
Transformers and Attention
Self-attention, multi-head attention and the transformer block, drawn step by step.
Large Language Models
Tokenisation, pretraining, fine-tuning and alignment of modern LLMs.
Prompt Engineering
Practical prompting patterns, evaluation and structured outputs.
RAG and Vector Databases
Retrieval-augmented generation pipelines, embeddings and vector stores.
LangChain and LangGraph
Building LLM applications with chains, graphs and tooling.
AI Agents and Agentic AI
Agentic workflows, planning, tools and multi-agent systems.
Model Context Protocol (MCP)
The MCP standard: servers, clients, tools and resources.
LLM Deployment and Optimization
Serving, scaling and productionising LLM applications.
LLM Quantization and Inference
Quantisation techniques and efficient local inference.
AI System Design
Designing AI systems end to end: latency, cost, reliability and safety.
GenAI Interview Preparation
Handwritten solutions to the questions interviewers actually ask.
Learning paths
Structured roadmaps, not random tutorials
Follow a curated sequence of notes from your current stack to your target AI role.
Developer to AI Engineer
The complete roadmap for software developers transitioning into AI engineering roles.
View path →
Developer to GenAI Engineer
Everything a developer needs to build with generative AI: LLMs, prompting, RAG and agents.
View path →
LLM Engineering Roadmap
From tokenisation to fine-tuning, deployment and inference optimisation.
View path →
RAG Engineer Roadmap
Embeddings, vector databases, retrieval pipelines and RAG evaluation.
View path →
AI Agent Engineer Roadmap
Tool use, planning, orchestration and production agent systems.
View path →
GenAI Interview Preparation
Handwritten answers, diagrams and code for GenAI technical interviews.
View path →
Featured notes
Latest and most popular
Fresh uploads and the notes developers keep buying.
Popular right now
GenAI Interview Preparation
GenAI Interview Guide: 120 Questions Solved
The questions GenAI interviewers actually ask — with handwritten explanations, diagrams and code for every answer.
RAG and Vector Databases
RAG Systems: The Retrieval Blueprint
End-to-end retrieval-augmented generation: chunking strategies, embeddings, hybrid search, reranking and evaluation — with full pipeline diagrams.
Large Language Models
LLM Fundamentals: Tokens to Alignment
How large language models really work: tokenisation, pretraining objectives, instruction tuning, RLHF and decoding strategies, explained visually.
Latest uploads
Python for AI Engineering
Python Foundations for AI Engineering
Everything a working developer needs in Python for AI: environments, NumPy, data pipelines, notebook workflows and the libraries the AI stack actually uses.
RAG and Vector Databases
RAG Systems: The Retrieval Blueprint
End-to-end retrieval-augmented generation: chunking strategies, embeddings, hybrid search, reranking and evaluation — with full pipeline diagrams.
Large Language Models
LLM Fundamentals: Tokens to Alignment
How large language models really work: tokenisation, pretraining objectives, instruction tuning, RLHF and decoding strategies, explained visually.
Bundles
Get several notes together for less
Curated sets of notes in one order, at a bundle price.
Why AiNotes
Built for the transition
Developer-focused content
Written for working software developers — Java, Python, JavaScript, backend, Appium, Salesforce and low-code backgrounds — not for academics.
Handwritten explanations
Every concept is drawn and annotated by hand, which builds intuition faster than slides or dense textbooks.
Technical architecture diagrams
Transformers, RAG pipelines, agent loops and system designs sketched as clean, interview-ready diagrams.
Interview-oriented learning
Notes emphasise the explanations, trade-offs and questions GenAI interviewers actually ask.
Affordable resources
Premium notes at prices a working developer can justify — buy exactly the topic you need.