Add AI to your Playwright tests | ZeroStep

ZeroStep

4 | 69 | 0
Type:
Open Source Projects
Last Updated:
2025/11/20
Description:
ZeroStep supercharges Playwright tests with AI, using GPT-3.5 and GPT-4 via its ai() function. Write resilient E2E tests with plain-text instructions, eliminating CSS selectors and XPath locators for simpler, faster testing.
Share:
Playwright testing
AI-powered testing
E2E testing
GPT-3.5
GPT-4

Overview of ZeroStep

What is ZeroStep?

ZeroStep is an open-source AI-powered tool designed to supercharge your Playwright tests. It leverages the power of GPT-3.5 and GPT-4 through its ai() function to make end-to-end (E2E) testing simpler and more resilient to changes. Instead of relying on CSS selectors or XPath locators, ZeroStep uses AI to determine the actions to take based on plain-text instructions.

How does ZeroStep work?

ZeroStep integrates directly into Playwright, allowing you to incorporate AI into your tests without altering your existing development workflow. The core functionality revolves around the ai() function, which takes plain-text instructions as input. Here's how it works:

  1. Plain-Text Instructions: You provide instructions in plain English describing the actions you want to perform.
  2. AI Interpretation: ZeroStep's AI assistant, powered by GPT-3.5 and GPT-4, interprets these instructions at runtime.
  3. Dynamic Action Execution: The AI determines the necessary actions to execute within the Playwright test environment.

This approach eliminates the need for hardcoded selectors and locators, making tests more adaptable to changes in the application's UI.

How to use ZeroStep?

To start using ZeroStep, follow these steps:

  1. Installation: Install ZeroStep as a development dependency using npm:
    npm i @zerostep/playwright -D
    
  2. Import the ai function: Import the ai function into your Playwright test file:
    import { test, expect } from '@playwright/test'
    import { ai } from '@zerostep/playwright'
    
  3. Use the ai function: Use the ai function within your tests to execute actions based on plain-text instructions:
    test.describe('Calendly', () => {
      test('book the next available timeslot', async ({ page }) => {
        await page.goto('https://calendly.com/zerostep-test/test-calendly')
    
        await ai('Verify that a calendar is displayed', { page, test })
        await ai('Dismiss the privacy modal', { page, test })
        await ai('Click on the first day in the month with times available', { page, test })
        await ai('Click on the first available time in the sidebar', { page, test })
        await ai('Click the Next button', { page, test })
        await ai('Fill out the form with realistic values', { page, test })
        await ai('Submit the form', { page, test })
    
        const element = await page.getByText('You are scheduled')
        expect(element).toBeDefined()
      })
    })
    

Why choose ZeroStep?

ZeroStep offers several advantages over traditional E2E testing approaches:

  • Resilient to Change: Tests are less likely to break due to UI changes, as the AI can adapt to new layouts and designs.
  • Faster Development: Writing tests becomes quicker and easier, as you can express actions in plain text instead of writing complex code.
  • Test-Driven Development (TDD) Approach: Since tests are not tightly coupled to implementation details, you can write E2E tests before the functionality is fully implemented.
  • Simplified Automation: Complex scenarios become easier to automate using plain-text instructions.

Who is ZeroStep for?

ZeroStep is designed for developers and QA engineers who want to improve the efficiency and reliability of their Playwright E2E tests. It is particularly useful for:

  • Teams working on applications with frequently changing UIs.
  • Developers who want to adopt a TDD approach to E2E testing.
  • QA engineers looking for a more intuitive and less error-prone way to automate complex scenarios.

Pricing

ZeroStep offers a free tier with 500 ai() function calls per month and unlimited users. Paid plans start at $20 per month, which includes 2,000 ai() function calls per month.

By using AI to interpret plain-text instructions, ZeroStep makes E2E testing more accessible, efficient, and resilient. It helps teams deliver high-quality software with greater confidence and speed.

Best Alternative Tools to "ZeroStep"

Checksum
No Image Available
410 0

Checksum is an AI-powered E2E test automation platform for Playwright & Cypress, generating, running, and maintaining tests with self-healing capabilities.

E2E testing automation
ContextQA
No Image Available
614 0

ContextQA provides AI-powered automated testing solutions to accelerate testing, reduce manual effort, and ensure quality with low-code automation and AI-driven insights.

test automation
AI testing
low-code
AutoQA
No Image Available
190 0

AutoQA is an AI-powered automated testing platform. It uses AI agents to validate requirements, explore user flows, and catch regressions in a real browser, automating quality assurance without requiring code.

AI testing platform
Relicx
No Image Available
232 0

Relicx is a Generative AI-powered software testing tool that allows users to create high-quality end-to-end tests in minutes using natural language. It enhances testing ecosystems with advanced capabilities for automating user acceptance testing and integrates seamlessly into CI/CD pipelines.

AI testing automation
BugRaptors
No Image Available
568 0

Elevate your software quality with BugRaptors' AI-powered quality engineering services. Benefit from AI-augmented manual testing, AI-driven automation, and AI security testing.

AI testing
test automation
TestZeus
No Image Available
261 0

TestZeus is an AI-powered Salesforce testing platform. It uses AI agents for test generation, execution, and maintenance. Write tests in natural language and achieve 10x faster testing with 70% cost savings.

Salesforce automation
AI testing
Autify
No Image Available
473 0

Autify's AI-powered Quality Engineering Platform streamlines software testing with AI-driven test automation, test case generation, and mobile testing solutions for iOS and Android applications.

test automation
AI testing
mabl
No Image Available
256 0

mabl is an AI-native test automation platform designed to accelerate software releases and ensure quality across web, mobile, API, and performance. It leverages agentic workflows and low-code automation for all team members.

AI test automation
low-code testing
TestDriver
No Image Available
246 0

TestDriver is an AI-powered QA agent that automates testing with AI vision, offering faster test generation, automated maintenance, and broader coverage for web, mobile, and desktop applications.

AI testing agent
QA automation
Alumnium
No Image Available
483 0

Alumnium is an AI-powered test automation tool that uses natural language to translate test instructions into executable commands. It supports web and mobile testing, integrating with Appium, Playwright, and Selenium.

AI test automation
Codien
No Image Available
11 0

Codien is an AI-powered platform that automatically converts Protractor and Selenium tests to Playwright with 98% accuracy, saving engineering teams weeks of manual migration effort through intelligent analysis and one-click conversion.

test migration
Playwright conversion
PerfAgents
No Image Available
531 0

PerfAgents is an AI-powered synthetic monitoring platform that simplifies web application monitoring using existing automation scripts. It supports Playwright, Selenium, Puppeteer, and Cypress, ensuring continuous testing and reliable performance.

synthetic monitoring
web monitoring
Decipher AI
No Image Available
409 0

Decipher's agents learn from session replays, auto-write regression tests across every flow, and monitor production for user-impacting bugs.

automated QA
test generation
KaneAI
No Image Available
482 0

KaneAI is a GenAI-Native testing agent for high-speed Quality Engineering teams. It enables planning, authoring, and evolving tests using natural language. Discover efficient AI-driven test automation today.

test automation
AI test agent