AI / A CONCEPT NOTE

User Prompt

the question or task from the end user

~60 sec read

Overview · mechanism
pitfall · examples

01 / THE SHORT VERSION

The idea in a few sentences.

The specific query, command, or context block typed by the user. Prompt engineering optimizes this input text to extract accurate, structured answers from the model.

02 / FOLLOW THE MECHANISM

How user prompt flows

  1. Prompt write

    user writes request: 'Format this data as a table.'

  2. Parsing

    client app clean text, attaching context metadata.

  3. Generation

    LLM processes prompt input, producing target output.

04 / COMMAND NOTES

Read the command, then the result.

Inspect the flags and arguments before trying an example. Snippets can need local setup, replacement values, or resources in your own environment.

EXAMPLE 01 · REFERENCE

open local prompt engineering testing dashboard

promptfoo view

Explore command anatomy in the CLI lab