🎓 Free, always — no sign-up walls
Everything here starts from zero and stays in plain English. You do not need a degree, a GPU, or maths beyond school level to begin.
No background assumed. Begin at the top and work down.
The three words get used interchangeably and they are not the same thing. Start here if you are starting from zero.
Read the guide →
What a model is really doing when it answers you — tokens, prediction, context windows — without the maths.
Read the guide →
You do not need to master all of Python first. Here is the slice that matters, and what you can skip for now.
Read the guide →
An honest answer, split by role. Applied engineering and research have very different bars.
Read the guide →
The ideas behind most AI products being built right now.
Beyond tricks: how to write prompts that hold up in production, and why most 'prompt hacks' do not.
Read the guide →
How to make a model answer from your own documents. Chunking, embeddings, vector search, and where it goes wrong.
Read the guide →
The open standard for connecting models to tools and data. What it is, why it exists, and how to build a server.
Read the guide →
What separates an agent from a chatbot, the loop at the centre of it, and why agents fail in the real world.
Read the guide →
What separates a demo from something that survives production.
The decision people get wrong most often. Usually you do not need to fine-tune — here is how to tell.
Read the guide →
How to know if your AI feature is any good. The skill that separates hobby projects from shipped products.
Read the guide →
Deployment, monitoring, drift, retraining, cost. The unglamorous work that keeps AI systems alive.
Read the guide →
GPUs, inference, serving, and why your cloud bill explodes. Backend and DevOps skills, seen through the AI lens.
Read the guide →
