Prompts Royale

Prompts Royale

Prompts Royale is an open-source, browser-based prompt engineering application that automatically generates prompt candidates, pits them against each other in Monte Carlo matchmaking and ELO rating battles, and ranks them to reveal the best prompt for your task.

What is Prompts Royale?

Prompts Royale is a prompt engineering tool that turns a task description and example test cases into ranked prompt candidates. It takes a natural language description of what you want a prompt to accomplish, plus a few scenario/expected-output pairs, and generates N candidate prompts that are then battle-tested against each other. The application runs in the browser—the repository is built with Nuxt—and all data stays local; requests go directly from your browser to the LLM API of your choice. The project is maintained by meistrari and is available both as a hosted site (promptsroyale.com) and as a self-hosted Node/Bun application.

Key Features

• Automatic prompt generation: Creates prompt candidates from your description and test case scenarios; you can also write and add your own prompts.
• Automatic test case generation: Generates test cases from the description to help you get started without manual work.
• Monte Carlo Matchmaking + ELO Rating: Uses the Monte Carlo method to select duels that maximize information gained, and ELO ratings to rank candidates based on wins and the strength of opponents beaten.
• Everything is customizable: A settings page lets you adjust every parameter, including the learning rate (recommended 0.96), K points per battle, and more.
• Local & Secure: All data is stored locally and requests are made from your browser to the LLM API, so your prompts and test cases don't leave your machine.
• Hosted or self-hosted: Use the live site at promptsroyale.com or clone the repository and run it locally with Node 16+ and Bun.

Who is it for?

• Prompt engineers who need an objective, repeatable way to compare prompt variations rather than relying on gut feeling.
• AI product developers who want to select the best system prompt for their LLM-powered features by testing against real scenarios.
• Teams building LLM applications that need to A/B test system prompts before deployment.

What can you do with Prompts Royale?

• Generate and battle prompts: Provide a description like Write a prompt that creates a headline for a website, add 2-3 test cases with expected outputs, then let the system generate candidates that fight each other for the #1 spot.
• Write your own candidates: If you have a specific prompt in mind, add it manually and let it compete against the generated ones.
• Run a local instance: Clone the repository, run bun i to install dependencies, and bun run dev to launch your own private instance.

How does Prompts Royale work?

Each prompt is modeled as a normal distribution with an initial mean of 1000 and standard deviation of 350, representing its ELO score. A Monte Carlo sampler picks pairs of prompts to duel; the probability of being drawn is proportional to the chance that the prompt is the best. In each duel, both prompts answer every test case, and a separate judge prompt decides which answer is best. ELO scores are updated with formulas that include a learning rate, K points per battle, and the number of test cases; the standard deviation also shrinks after each match as confidence in the estimate grows.

Alternatives

• gpt-prompt-engineer (GitHub) — an earlier project that inspired Prompts Royale's automatic prompt generation approach.

FAQ

Is Prompts Royale free?

The source code is publicly available on GitHub under the meistrari account, and you can run it locally for free with Node 16+ and Bun. The hosted version at promptsroyale.com is provided by the developer, but pricing or usage limits are not stated on this page.

What does Prompts Royale do?

It generates multiple prompt candidates from a task description and example test cases, then runs them in automated battles using Monte Carlo matchmaking and ELO ratings. The result is a ranked list of prompts based on how well they perform on your scenarios.

Do I need an API key?

Because requests are made directly from your browser to the LLM API, you need access to an LLM API endpoint. The page doesn't specify which providers are supported, but you'll need to configure your own API access for battles to run.

Can I write my own prompts?

Yes. In addition to the automatically generated candidates, you can input your own prompt candidates and let them compete against the generated ones.

What are the system requirements?

Node.js version 16 or higher is required to run the project locally. The project uses Bun for dependency management and to run the development server.