The complete map. Six layers from hardware to application.
Chatbots, code assistants, search, agents. What gets built on top of AI and delivered to end users.
The API, the web UI, the prompt. How the outside world communicates with the model — and how the model responds.
Running a live query. The prompt arrives, gets processed, tokens are generated one by one, a response is assembled and returned.
The trained model itself. Transformer architecture, tokenization, neural network weights — the frozen knowledge from training.
How the model learned. Data ingestion, supervised and reinforcement learning, RLHF — the process that produced the model.
GPU and TPU clusters, high-speed interconnects, massive storage. The physical infrastructure everything else runs on.
The stack splits cleanly into two phases:
Build time (layers 1–2): Happens once, takes weeks or months, costs millions of dollars in compute. Hardware runs training. Data shapes the model. The result is a set of weights — billions of numbers that encode what the model knows.
Run time (layers 3–6): Happens continuously, milliseconds per query. The frozen model receives a prompt, generates a response, delivers it through the interface to the application. No learning happens here — inference is pure execution.
This distinction matters: when you use Claude or ChatGPT, you are talking to a frozen model. It is not learning from your conversation in real time. The learning happened months ago, on hardware you'll never see, with data you'll never read.
The remaining six parts of this series take each layer in turn — starting at the bottom of the stack and working up to the application. By the end you will have a complete mental model of how AI works, end to end, with no black boxes.