Basics for Prompt Engineerings
Basics explains how a language model works well enough to prompt it. The model reads tokens and predicts the next one, so wording, order and examples steer the output. A prompt usually combines a role or system message, the task, context, and an output format, and parameters like temperature change randomness.
Stage: Foundations · Part of the Prompt Engineering roadmap · Last reviewed 19 November 2026
What to learn in Basics
- Explain tokens, context windows and next-token prediction in plain words
- Separate system, user and assistant messages in a chat request
- Structure a prompt with task, context, constraints and format
- Change temperature and see how it affects variety and consistency
- Estimate token counts to stay inside a context window
Basics interview questions
What does temperature do in a language model request?
Temperature scales how random token choice is. Low values make the model pick the most likely tokens, which suits extraction and code, while higher values give more varied wording, which suits brainstorming. It does not make the model more truthful.
What is the difference between a system prompt and a user prompt?
The system prompt sets standing behaviour such as role, tone, rules and format, and is usually written by the developer. The user prompt carries the specific request for that turn. Models weight system instructions more, though they are not a hard security boundary.
Where Basics fits in the Prompt Engineering roadmap
Basics belongs to the Foundations stage (beginner level), which takes about 12 hours. How LLMs respond.
Other units in this stage
Back to the full Prompt Engineering roadmap