Empromptu Docs
  • Welcome
  • Getting Started
    • Take a Tour of Empromptu
    • How do you define Accuracy?
    • Quickstart
      • Quickstart - Archive
  • Advanced Configuration
  • No App, Use Prompt Optimizer
  • Examples
  • Basics
    • Projects and Tasks
    • Prompts Overview
      • Manual Optimization
      • Automatic Optimization
    • Input Optimization
    • Edge Case Optimizer
    • Evaluations
    • Models
    • Data Generator
    • Core Concepts
    • Usage Guide
      • Data Viewer
      • Performance Over Time
      • Prompt Explorer
      • Show Input Space
      • Prompt Performance
      • Prompt Playground
    • Best Practices
    • FAQ
    • Troubleshooting
Powered by GitBook
On this page
  1. Basics

Core Concepts

Lingo you need to know when working with Empromptu

Terms

  • Prompt: The set of variables (e.g., prompt text, model temperature, model name) used to interact with an LLM. These variables are optional and can be customized for your specific needs.

  • Input Data: Dynamic content provided with each LLM call. This could include scraped data, user inputs, or other variable information that is not part of the fixed prompt.

  • Prompt Family: A group of prompts designed to accomplish the same task. Each prompt in the family can have variations and is identified by a user-defined prompt_key.

  • LLM Input/Output: The full JSON structures sent to and returned from an LLM call. This provides a complete picture of the data exchange.

PreviousData GeneratorNextUsage Guide

Last updated 4 months ago