Imagine this: You describe what you want to test, and AI generates comprehensive test plans, writes the actual test code, and even fixes failing tests automatically. This isn’t science fiction—it’s Playwright Agents, and it’s available today.

Playwright has introduced three powerful AI agents that work together to revolutionize how we approach test automation: the Planner, Generator, and Healer. Let’s dive deep into how these agents are changing the game.

The Planner is your AI test strategist. It explores your application and produces detailed, human-readable test plans in Markdown format.

How It Works:

• Input: A clear request (e.g., “Generate a plan for guest checkout”), a seed test that sets up your environment, and optionally a Product Requirements Document
• Process: Runs the seed test to understand your app’s structure, analyzes user flows, and identifies test scenarios
• Output: Structured Markdown test plans saved in specs/ directory with detailed steps and expected results

Example Output:

# TodoMVC Application - Basic Operations Test Plan

## Test Scenarios

### 1. Adding New Todos
#### 1.1 Add Valid Todo
**Steps:**
1. Click in the "What needs to be done?" input field
2. Type "Buy groceries"
3. Press Enter key

**Expected Results:**
- Todo appears in the list with unchecked checkbox
- Counter shows "1 item left"
- Input field is cleared and ready for next entry

The Generator transforms your human-readable test plans into executable Playwright test code, verifying selectors and assertions in real-time.

Key Features:

• Live Verification: Checks selectors against your actual app while generating code
• Smart Assertions: Uses Playwright’s catalog of assertions for robust validation
• Context Aware: Inherits setup from seed tests and maintains consistency
• Best Practices: Generates code following Playwright conventions and modern patterns

Generated Test Example:

// spec: specs/basic-operations.md
// seed: tests/seed.spec.ts
import { test, expect } from '../fixtures';

test.describe('Adding New Todos', () => {
  test('Add Valid Todo', async ({ page }) => {
    // Type and submit todo
    const todoInput = page.getByRole('textbox', { 
      name: 'What needs to be done?' 
    });
    await todoInput.fill('Buy groceries');
    await todoInput.press('Enter');
    
    // Verify todo appears
    await expect(page.getByText('Buy groceries')).toBeVisible();
    await expect(page.getByText('1 item left')).toBeVisible();
    await expect(todoInput).toHaveValue('');
  });
});

The Healer is your automated maintenance engineer. When tests fail, it diagnoses issues and applies fixes automatically.

Healing Process:

• Step 1: Replays the failing test steps to understand the failure context
• Step 2: Inspects the current UI to locate equivalent elements or alternative flows
• Step 3: Suggests patches like locator updates, wait adjustments, or data corrections
• Step 4: Re-runs the test until it passes or determines the functionality is actually broken

Common Fixes Applied:

• Updating selectors when UI structure changes
• Adding appropriate waits for dynamic content
• Adjusting test data to match new requirements
• Handling new dialog boxes or pop-ups

🤖 Working with Claude Code

Playwright Agents integrate seamlessly with Claude Code, enabling natural language test automation directly from your terminal.

Setup Process:

# Initialize Playwright Agents for Claude Code
npx playwright init-agents --loop=claude

# This generates agent definitions optimized for Claude Code
# under .github/ directory with MCP tools and instructions

Benefits with Claude Code:

• Natural Language Control: Command agents using simple English instructions
• Context Awareness: Claude Code understands your project structure and requirements
• Iterative Refinement: Easily adjust and improve tests through conversation
• Automatic Updates: Regenerate agents when Playwright updates to get latest features

Ready to Transform Your Testing?

Playwright Agents represent a fundamental shift in how we approach test automation. By combining AI with Playwright’s powerful testing capabilities, you can achieve comprehensive test coverage with a fraction of the traditional effort.

Whether you’re starting a new project or maintaining an existing test suite, Playwright Agents can help you move faster, catch more bugs, and spend less time on maintenance.

Get Started with Playwright Agents