LLMAssert

Test your AI outputs for hallucinations, PII leaks, tone, format compliance, and semantic accuracy — using matchers you already know from Playwright.

import { test, expect } from "@llmassert/playwright";

test("response is grounded in docs", async () => {
  const response = "Our return window is 30 days from purchase.";
  await expect(response).toBeGroundedIn("Returns accepted within 30 days.");
});

Quick Links

• Getting Started — Install and run your first test in under 5 minutes
• Matchers — All 5 assertion matchers with examples
• Configuration — Judge models, reporters, and thresholds
• Guides — CI integration and best practices
• API Reference — Complete API documentation