When OpenAI released ChatGPT in November 2022, it instantly captured the public's imagination with its ability to answer questions, write poetry and riff on almost any topic. ChatGPT is driven by what A.I. researchers call a neural network. A neural network learns skills by analyzing data and pinpointing patterns in order to perform some task. Researchers at labs like OpenAI have designed neural networks that analyze vast amounts of digital text from many varied sources on a variety of topics. ChatGPT is just one example of a technology class referred to as Large Language Models. ChatGPT technology can appear amazing but can also blend fact with fiction and even make up information, a phenomenon that technologists refer to (by analogy) as "hallucination", while not informing you of those fictive limitations when they occur and are presented in ChatGPT's output or "completion".
Prompt engineering is the process of formulating a prompt for an AI system so that it produces a completion that closely matches your needs and expectations.