Quick Start

Run your first eval in under 5 minutes.

Install the SDK


npm install @launchgate/sdk

Create an API key


export LAUNCHGATE_API_KEY=lg_live_your_key_here

API keys are displayed in plaintext only once at creation. Store it securely — you won’t be able to view it again.

Create a project and eval suite

In the dashboard , create a new project and add an eval suite. You can start from one of the 6 built-in templates or create a custom suite.

Run your first eval


import { LaunchGate } from "@launchgate/sdk";
 
const lg = new LaunchGate({
  apiKey: process.env.LAUNCHGATE_API_KEY,
});
 
const result = await lg.run("rag-faithfulness", {
  input: {
    context: "The Eiffel Tower was built in 1889.",
    query: "When was the Eiffel Tower built?",
  },
  output: "The Eiffel Tower was built in 1889.",
});
 
console.log(result.status);    // "cleared" ✓
console.log(result.passRate);  // 1.0
console.log(result.scores);    // Individual case scores

Check results in the dashboard

Open your project in the dashboard to see your run results, pass rates, and individual case scores.

What’s next?

Add to CI/CD — Automate eval runs on every PR
Explore scorers — Learn about all 5 scoring methods
Use templates — Start from pre-built eval suites
Set up BYOK keys — Enable AI-powered scoring with your own LLM keys