Learn AI
Next LLM
One index for every study guide and interview-answer doc in this repo, ordered topic by topic: Python → SQL → GitHub, then math → ML → embeddings → attention → LLM → AI frameworks → chatbot → RAG → AI platform → system design → MCP → API design.
1
Python
The language fundamentals every other topic here assumes.
2
SQL
Query fundamentals for the data layer beneath ML pipelines and RAG systems.
3
GitHub
Git internals, branching strategy, and GitHub-specific workflow tooling.
4
Math
Linear algebra, calculus, probability, and statistics behind ML models.
math/aiml-maths-plan.html
AIML Maths — Topic Coverage
What to learn, why it matters, and where it shows up in interviews.
math/linear-algebra-deep.html
Linear Algebra — Deep Study Guide
The language of data, weights, and transformations.
math/calculus-deep.html
Calculus — Deep Study Guide
How models learn: backprop and optimization from first principles.
math/probability-deep.html
Probability — Deep Study Guide
Uncertainty & inference — how models reason about what they don't know.
math/statistics-deep.html
Statistics — Deep Study Guide
Data & model evaluation — describing data and judging quality from evidence.
5
Machine Learning
Classical ML — the layer beneath deep learning and LLMs.
6
Embeddings
From sparse NLP features to dense vectors — what an embedding is and how it's trained.
7
Attention
Why RNNs struggled with long text, and how self-attention and transformers replaced them.
8
LLM
Core mechanics, inference, tuning, and production monitoring.
llms/llm-internals.html
LLM Internals — Deep Study Guide
Context windows, attention, and why LLMs behave the way they do.
llms/llm-production.html
LLM Internals & Production GenAI — Interview Answers
Tokenization through production monitoring, interview-ready.
llms/llm-evaluations.html
LLM / Agent Evaluation & Observability
Production logging, agent monitoring, and LLM-as-a-judge risks.
9
AI Frameworks
The orchestration layer on top of raw LLM calls.
10
Chatbot
The conversational-interface layer between raw LLM calls and full agents.
11
RAG
Retrieval-augmented generation: faithfulness, failure modes, and evaluation.
12
AI Platform
Enterprise platform architecture for agentic GenAI systems.
13
System Design
Open-ended design questions that synthesize RAG, agents, and production into one answer.
14
MCP
Model Context Protocol, from first principles.
15
API Design
How FastAPI works under the hood, core concepts, and a runnable example.