Skip to main content
ModelTerms

Prompting · beginner

Prompt

A prompt is the text you send to an LLM to elicit a response. It typically includes a system message, optional examples, and the user's query.

Explanation

Prompts are the LLM's only input besides the model's baked-in weights. They control persona ("you are a helpful assistant"), task ("translate this to French"), format ("respond in JSON"), and context (the actual content to operate on).

In modern chat APIs the prompt is structured as a list of messages, each tagged with a role (system, user, assistant) and content. The model sees the whole list and produces the next assistant message.

A well-crafted prompt can mean the difference between a model that refuses, hallucinates, or formats wrong and one that gets the job done first try.

Examples

  • A system prompt + user message + a few-shot examples = a typical prompt.
  • Code completion: prompt = the file before the cursor.

Frequently asked

What is Prompt?

A prompt is the text you send to an LLM to elicit a response. It typically includes a system message, optional examples, and the user's query.

What is an example of prompt?

A system prompt + user message + a few-shot examples = a typical prompt.

How is Prompt related to System Prompt?

Prompt and System Prompt are both prompting concepts. The system prompt is the first message in a chat that sets the model's persona, rules, and overall behavior. It is treated by most providers as higher-trust than user input.

Is Prompt considered beginner?

Prompt is generally considered beginner-level material in the AI and LLM space.

System PromptPrompting

The system prompt is the first message in a chat that sets the model's persona, rules, and overall behavior. It is treated by most providers as higher-trust than user input.

Few-ShotPrompting

Few-shot prompting includes a small number of input-output examples directly in the prompt so the model can pattern-match without any fine-tuning.

Zero-ShotPrompting

Zero-shot prompting asks the model to perform a task without showing any examples — only the instruction and the input. Modern instruction-tuned models do this well.

Chain-of-ThoughtPrompting

Chain-of-thought prompting asks the model to show its reasoning step by step before giving a final answer. It dramatically improves performance on multi-step problems.

Prompt EngineeringPrompting

Prompt engineering is the craft of writing prompts that reliably produce the behavior you want from an LLM. It blends formatting, examples, tone, and constraints.

Side-by-side comparisons

Sources