Core concepts
Prompt engineering
Definition
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.
Prompt engineering emerged because model behaviour is highly sensitive to how a request is phrased. The same underlying capability can produce a useless answer or an excellent one depending on framing, and the difference is learnable.
The discipline has a few durable principles. Be specific rather than long. Show examples when you need consistent formatting or tone. Ask for reasoning before conclusions on hard problems. Request explicit output schemas when a program will consume the result. And test prompts against real cases rather than trusting a single lucky output.
As models improve, some early tricks become unnecessary — but the core skill of specifying a task precisely does not go away. It's the same skill as writing a good brief for a capable contractor.
Related terms
Prompt
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.
Chain-of-thought prompting
Chain-of-thought prompting asks a model to work through its reasoning step by step before answering. It measurably improves accuracy on maths, logic, and multi-step problems by forcing intermediate steps instead of an immediate guess.
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.
Meta-prompting
Meta-prompting is using a model to write, critique or improve prompts. You describe the task and the failure modes you want to avoid, and the model drafts the prompt.
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.