✨Artificial Intelligence

Generative AI: full course guide

From how transformers generate text to prompting, embeddings, retrieval augmented generation, fine tuning and evaluation, with runnable examples throughout.

100 pages15 modules75 topics

Beginner to Advanced · read it in your browser with Skiiling Pro.

📝 Evaluation25 Q🎙️ Mock Interview
Beta

Loading the reader…

What is inside this guide

01AI & ML Foundations

  • What is Artificial Intelligence?
  • ML vs Deep Learning vs GenAI
  • Neural Networks Simplified
  • Training vs Inference
  • AI Use Cases Today

02Large Language Models

  • What is a LLM?
  • Tokens & Embeddings
  • Transformer Architecture (Simplified)
  • GPT, BERT & Variants
  • Capabilities & Limitations

03Prompt Engineering

  • What is Prompting?
  • Zero-Shot & Few-Shot Prompting
  • Chain-of-Thought Prompting
  • System vs User Prompts
  • Common Prompting Mistakes

04Using AI Tools

  • ChatGPT & Claude APIs
  • Hugging Face Hub
  • Using Ollama Locally
  • Image Generation (DALL-E / Stable Diffusion)
  • AI-Powered Coding (Copilot)

05Building with GenAI

  • Calling the OpenAI API
  • Building a Simple Chatbot
  • Summarisation App
  • Q&A over Documents
  • Deploying an AI App

06Advanced Prompting

  • ReAct Prompting
  • Structured Output & JSON Mode
  • Function Calling
  • Prompt Chaining
  • Prompt Evaluation & Testing

07RAG (Retrieval Augmented Generation)

  • Why RAG?
  • Vector Databases (Chroma, Pinecone)
  • Embedding Models
  • Chunking Strategies
  • Retrieval Pipeline Design

08LangChain Framework

  • LangChain Architecture
  • Chains & Runnables
  • Document Loaders & Splitters
  • Memory in LangChain
  • LangChain Tools & Agents

09Fine-Tuning Basics

  • When to Fine-Tune?
  • Dataset Preparation
  • LoRA & QLoRA
  • Using Hugging Face Trainer
  • Evaluating Fine-Tuned Models

10Production AI Apps

  • Streaming Responses
  • Caching & Cost Reduction
  • Observability & Tracing (LangSmith)
  • Rate Limiting & Error Handling
  • Deploying to Cloud

11LLM Architecture Deep Dive

  • Attention Mechanism in Depth
  • Positional Encoding
  • KV Cache
  • Quantisation (INT8, INT4)
  • Speculative Decoding

12Advanced RAG

  • Hybrid Search (BM25 + Dense)
  • HyDE & Multi-Query Retrieval
  • Re-ranking with Cross-Encoders
  • GraphRAG
  • Evaluation with RAGAS

13Agentic Systems

  • Agent Architectures
  • Tool Use & Planning
  • Memory Systems (Short & Long Term)
  • Multi-Agent Orchestration
  • Self-Reflection & Critique

14Custom Model Training

  • Pretraining from Scratch
  • Instruction Tuning (SFT)
  • RLHF & DPO
  • PEFT Methods
  • Model Merging

15Deployment & MLOps

  • Model Serving (vLLM, TGI)
  • Batching & Throughput Optimisation
  • A/B Testing LLMs
  • Red Teaming & Safety
  • LLMOps Pipelines

How to read it

The reader above opens the complete guide in your browser. The contents panel on the left is built from the guide's own bookmarks, so every module and topic is one click away. You can search the full text, zoom, and highlight passages in four colours; highlights and your reading position are remembered on this device.

Reading the guides is part of Skiiling Pro, the one web subscription that also unlocks Role Prep and Practical Labs and Skill Plans. The syllabus above is free to browse. See pricing.