Prompt engineering is half writing, half experimental method. The model is a function from text to text; the prompt is the lever. The discipline lies in noticing which phrasings reliably move which behaviors.
In plain language
An LLM is a function from text to text. The prompt is the lever you have. Better prompts come from noticing which phrasings, examples, and constraints reliably steer the model — often more than people expect. It is part writing, part experimental method: change one thing, observe, keep the change if it helps.
An everyday picture
Think of Prompt Engineering less like a thinking person and more like someone who has read an enormous amount and now finishes other people's sentences for a living. They have absorbed the shape of the work; they have not memorised any one page.
Where it shows up
Prompt Engineering tends to sit inside products that need to read, write, or recognise without a hard-coded rule — assistants, search, document tools, voice apps. It is rarely the only moving part, but it is often the part the user feels.
A small example
Asking 'summarise this' often returns generic text. Asking 'summarise this for a busy product manager in three bullet points, each under 15 words' usually returns something genuinely useful.
Common misunderstanding
One line to take with you
Prompt Engineering is statistics worn well. Useful for patterns; double-check it for facts.