1 * Foundations
Start here. Understand what GenAI is, how LLMs work, and the key concepts like tokens and embeddings -- explained simply.
What is GenAI
LLM Basics
Tokens
Embeddings
Start here →
2 * Core Concepts
Understand transformers intuitively, how attention mechanisms work, and how to use AI APIs effectively in your applications.
Transformers
Attention
OpenAI API
Anthropic
Explore →
⭐ Most Popular
3 * Build Your First App
Jump straight into building. Create a working chatbot, master prompt basics, and implement streaming responses. Hands-on from minute one.
Chatbot
Prompts
Streaming
Build now →
🏆 Flagship Track
4 * RAG Systems
The most in-demand GenAI skill right now. Learn Retrieval-Augmented Generation end-to-end -- from chunking strategies to vector databases to a complete PDF Q&A project.
What is RAG
Chunking
Vector DB
PDF Q&A Project
Master RAG →
5 * Advanced Topics
Deep dive into prompt engineering, fine-tuning your own models with LoRA, and building autonomous agents with LangChain.
Prompt Deep Dive
Fine-Tuning
Agents
LangChain
Go deeper →
6 * Production & Scaling
Take your GenAI app from prototype to production. Evaluation frameworks, guardrails, cost optimisation, and FastAPI deployment.
Evaluation
Guardrails
Cost Opt.
FastAPI
Ship it →
Section 1
Foundations
Start here -- understand what GenAI is, how LLMs work, and the vocabulary every AI engineer needs.
What is GenAI?
A clear, jargon-free explanation of generative AI and why it matters for engineers right now.
Learn →
LLM Basics
How large language models are trained, what they predict, and why they're so powerful.
Learn →
Tokens & Embeddings
The fundamental units of LLMs -- explained with simple analogies and why they matter for your costs.
Learn →
Section 2
Core Concepts
Transformers, attention mechanisms, and how to use AI APIs effectively in your applications.
Transformers
The architecture behind every modern LLM. Understand the intuition and key steps without the maths overwhelm.
Learn →
Attention Mechanism
Why "attention is all you need" -- the concept that changed everything in NLP.
Learn →
Using AI APIs
OpenAI, Anthropic, and open-source APIs. How to call them, structure messages, and handle responses.
Learn →
⭐
Most Popular Section
This is where most engineers get their first real win. Start here if you want to build something working today.
Build a Chatbot
Build a fully working chatbot with conversation memory in under 50 lines of Python.
Build →
Prompt Basics
The fundamentals of writing effective prompts -- system prompts, few-shot examples, and formatting.
Learn →
Streaming Responses
Make your app feel instant with streaming -- stream tokens as they're generated instead of waiting.
Learn →
🏆
Flagship Track -- Most In-Demand Skill
RAG is what every GenAI engineer needs right now. Master this and you'll stand out in any interview.
What is RAG?
Why LLMs hallucinate and how RAG solves it. The architecture explained clearly with a real example.
Start here →
Chunking Strategies
Fixed-size, semantic, and recursive chunking -- when to use each and how it affects retrieval quality.
Learn →
Vector Databases
Pinecone, Chroma, Weaviate -- how they work and how to choose the right one for your project.
Learn →
⭐ Project
PDF Q&A Project
Build a complete RAG system that can answer questions about any PDF document. End-to-end project with full code.
Build it →
Prompt Engineering
Chain-of-thought, tree-of-thought, ReAct, and advanced prompting patterns used in production.
Learn →
Fine-Tuning with LoRA
When to fine-tune vs prompt engineer. LoRA and PEFT explained -- fine-tune Llama on your own data.
Learn →
Agents with LangChain
Build autonomous agents that can use tools, search the web, and complete multi-step tasks.
Learn →
Evaluation & Guardrails
How to measure LLM quality, detect hallucinations, and implement content safety in production.
Learn →
Cost Optimization
Caching, model selection, prompt compression, and batching -- reduce your API costs by 70%+.
Learn →
Deploy with FastAPI
Wrap your LLM app in a production FastAPI server with async streaming, auth, and rate limiting.
Learn →
Monitoring & Logging
LangSmith, Helicone, and custom logging -- observability for your GenAI applications.
Learn →
Projects -- Beginner to Advanced
Build real things. Each project includes full code, step-by-step instructions, and a stretch goal.
Beginner
💬 Simple Chatbot
A chatbot with memory using the OpenAI API. Under 50 lines of Python.
PythonOpenAI
Intermediate
📄 PDF Q&A System
Upload any PDF and ask questions about it using RAG. Full end-to-end project.
PythonLangChainChroma
Beginner
⚡ Streaming Chat UI
Real-time streaming responses with a clean web interface. Feels like ChatGPT.
PythonFastAPIJS
Advanced
🤝 Research Agent
An autonomous agent that can search the web, summarise papers, and write reports.
LangChainToolsMemory
Advanced
🔧 Fine-Tuned Model
Fine-tune Llama 2 on your own dataset using LoRA. Full training pipeline included.
LoRAPEFTHuggingFace
Intermediate
🏭 Production LLM API
Deploy your LLM app as a production API with auth, rate limiting, and monitoring.
FastAPIDockerRedis
Loading...
Loading topic...
Claude is generating this lesson...