Getting started in 30 seconds

Scorable

Scorable is the automated LLM Evaluation Engineer agent for co-managing Scorable platform with you.

From the App

To get started, sign up and login to Scorable app. Select an evaluator under Evaluators tab and Execute. You will get a score between 0 and 1 and the justification for the score.

Programmatically

Create your Scorable API key under Settings > Developer.

In Python

pip install scorable

Quick test

For the best experience, we encourage you to create an account. However, if you prefer to run quick tests at this point, please create a temporary API key here.

Scorable provides over 30 evaluators or judges, which you can use to score any text based on a wealth of metrics. You can attach evaluators to an existing application with just a few lines of code.

from root import Scorable

# Just a quick test?
# You can get a temporary API key from https://scorable.ai/demo-user 
client = Scorable(api_key="my-developer-key")
client.evaluators.Politeness(
    response="You can find the instructions from our Careers page."
)
# {score=0.7, justification='The response is st...', execution_log_id=...}

• Python SDK Docs

• Python SDK GitHub Repo

In Typescript

npm install @root-signals/scorable
# or
yarn add @root-signals/scorable
# or  
pnpm add @root-signals/scorable

and execute:

import { Scorable } from '@root-signals/scorable';

// Connect to Scorable API
const client = new Scorable({
  apiKey: process.env.SCORABLE_API_KEY!
});

// Run any of our ready-made evaluators
const result = await client.evaluators.executeByName('Helpfulness', {
  response: "You can find the instructions from our Careers page."
});

• TypeScript SDK Docs

• TypeScript SDK GitHub Repo

Via REST API

You can execute evaluators in your favourite framework and tech stack via our REST API:

Via Command Line Interface (CLI)

roots judge execute <judge_id> --request "What is the capital of France?" --response "Paris"

• Command Line Interface (CLI)

Model Context Protocol (MCP) Server

Our Model Context Protocol (MCP) equips your AI agents and agentic pipelines with evaluation capabilities.

• Scorable MCP