Core concepts
Prompt
Definition
A prompt is the input you give an AI model to produce an output. Effective prompts specify five things: the role the model should adopt, relevant context, the specific task, the output format, and any constraints.
Everything a model knows about your intent comes from the prompt. It has no access to your screen, your goals, or the conversation you had yesterday unless you put that information in.
The most reliable structure covers five elements. Role: who the model should act as ("a senior copy editor"). Context: the background it needs ("the audience is non-technical"). Task: the specific request ("rewrite this for clarity"). Format: how the output should be shaped ("plain paragraphs, under 200 words"). Constraints: hard limits and prohibitions ("no jargon, keep all factual details").
Missing elements are the single most common cause of vague output. When an answer feels generic, the fix is almost always adding context or constraints — not writing a longer prompt.
Related terms
System prompt
A system prompt is a standing instruction that shapes a model's behaviour across an entire conversation, separate from individual user messages. It typically defines persona, rules, tone and output format.
Few-shot prompting
Few-shot prompting means including two to five worked examples of the input-output pattern you want before making your real request. It is the fastest way to lock in a consistent format, tone or edge-case behaviour.
Prompt engineering
Prompt engineering is the practice of designing model inputs that reliably produce the output you want. It combines clear instruction-writing, structured formatting, worked examples, and systematic testing.
Zero-shot prompting
Zero-shot prompting means asking a model to do a task with no worked examples — just an instruction. It works well for common tasks the model has seen extensively in training.
Token
A token is the unit of text an AI model reads and writes — roughly four characters or three-quarters of a word in English. Models price by the token and cap context by the token, so token count determines both what you pay and what fits.
Tokenizer
A tokenizer is the component that splits text into tokens before a model processes it. Different model families use different tokenizers, which is why the same text can have different token counts on GPT versus Claude.
Put this into practice
Understanding the term is step one. Our free courses and tools let you actually use it.