Learn

Prompt: the input you give a model

A prompt is the input text you give a large language model to produce a response. It can be a single question or a long block carrying instructions, examples, and background. The model continues from what the prompt sets up, so the wording and the context you include shape the answer you get back.

At a glance

What it is
The input text you send a model to get a response
What it carries
A question, instructions, examples, and background
Why it matters
Wording and context shape the answer the model returns
Its cost
Longer prompts use more of the context window

What counts as a prompt?

A prompt is whatever text you hand the model to respond to. At its smallest it is a single question. In practice it is usually more: instructions about the task, a few examples, and some background the model needs. A language model works by continuing from what it is given, so the prompt is not a formality wrapped around the real request. It is the request. Change the wording and you change the output.

That is also why the same model can seem sharp or useless depending on who is driving it. A vague prompt leaves the model guessing at context you never supplied, and it will fill the gap with something plausible whether or not it is right.

What makes a prompt work better?

The reliable moves are unglamorous. State the task plainly and say what format you want the answer in. Give the context the model cannot know on its own. When the output shape is specific, show one example rather than describing it. And prefer saying what to do over a list of things to avoid, since a positive instruction is easier to follow than a wall of prohibitions.

There is a cost to remember: every prompt is made of tokens, the chunks of text a model reads, and a longer prompt eats more of the context window, the fixed budget of tokens the model can hold at once. Padding a prompt with detail it does not need can crowd out the part that matters. Clear and complete beats long.

A clearer prompt

  • States the task and the format you want back
  • Gives the context the model needs to answer
  • Shows an example when the format is specific
  • Says what to do, not only what to avoid

A weaker prompt

  • Assumes the model knows context you never gave it
  • Bundles several unrelated asks into one
  • Leaves the output format to chance
  • Is so long it crowds out the real question

Related terms

← All terms Reviewed: June 2026