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
  • What is Empromptu?
  • Wait... Isn't that just AI observability?
  • So what is it exactly?
  • How does it work?
  • But that sounds too good to be true?
  1. Getting Started

Take a Tour of Empromptu

PreviousWelcomeNextHow do you define Accuracy?

Last updated 2 months ago

What is Empromptu?

Empromptu is an easy to use, AI library that you can connect to your application in code or use our UI that makes it almost effortless to visualize, build and optimize reliable, consistent, accurate AI applications, bots or agents.

Wait... Isn't that just AI observability?

Unlike other observability tools on the market that allow developers to only see their data, Empromptu corrects your data using AI.

So what is it exactly?

Empromptu's Library optimizes 6 parts of your application. When you use 1 or more of the parts, either manually or automatically, you can create an accurate and reliable multi-modal AI application. The more parts you use, the more accurate your application becomes.

The 6 parts are:

How does it work?

Empromptu supports both programmatic and UI-based interaction. Use either independently or in tandem.

  1. Using our UI you can create inputs, prompts, and evaluations and we will recommend the best inputs, prompts, models that provide you the best most accurate results. You can test your entire system against different prompts, models, evals and we will ensure that your application delivers the desired results consistently.

  2. Using our real-time embeddable library, instead of writing your prompts in a static code file, you embed our prompt library and in real-time, with low latency, we will send you back the most optimized prompt for the input.

But that sounds too good to be true?

Awesome, you should give it a try.

Prompt optimizer
Input optimizer
Evaluations
Edge case optimizer
Model evaluator
Data Generator
Go to our quickstart guide to try it in 5 easy steps.