Glossary
Large Language Model (LLM)
A neural network trained on vast text to predict the next token.
What it is
A large language model is a transformer-based neural network trained on huge text corpora to predict the next token. In AI engineering you use LLMs as components behind an API rather than training them yourself.
Why it matters in production
Almost everything you build — RAG, agents, evals — is an LLM wrapped in engineering. Knowing what the model is good at (language, reasoning over context) and bad at (facts it hasn't seen, exact computation) tells you which parts need systems around them.
In practice
Calling an OpenAI-compatible chat completions endpoint with a system prompt and a user question — the model is the engine; your code is everything around it.
Go deeper
Related terms
Production AI Notes
One practical AI engineering email each week
One concept, one architecture, one project idea, and one interview question — written for developers who want to build and ship real AI systems.