Generating Tests

Create tests using Autotest or performance testing.

Paragon generates tests for you. Describe what you want to test, and Paragon handles the rest.

Test Generation Methods

Test TypeMethodWhat It Creates
E2E TestsAutotestAutonomous browser-based tests
PerformanceInline ConfigPerformance test with budgets

Autotest (E2E Tests)

Autotest spawns autonomous agents that explore and test your live application in a real browser. No test files or selectors needed — describe what to test in plain English, and agents navigate your app, find bugs, and generate Playwright test code.

Creating an Autotest

  1. Go to Testing > Autotest
  2. Click New Test
  3. Select the repository
  4. Enter the target URL and a description of what to test
  5. Configure the number of agents and timeout
  6. Run the test

How It Works

  1. Planning — A planning agent analyzes the target app and distributes testing work across agents
  2. Exploration — Each agent navigates the app in a real browser, performing actions like clicking, typing, scrolling, and navigating between pages
  3. Reporting — Findings are compiled into a report with screenshots, reproduction steps, and severity ratings. Playwright test code is auto-generated from the agent's actions
  4. GitHub integration (optional) — Findings are filed as GitHub issues or bundled into a PR

Authentication

If your tests need to access protected pages, Autotest supports three auth methods:

MethodDescription
Login instructionsDescribe login steps in plain English (e.g. "click Login, type user@test.com into email, type pass123 into password, click Submit")
Cookies fileExport cookies from your browser and pass the JSON file
Team sessionShared, encrypted auth sessions stored for team reuse

Use a dedicated test account for authentication.

Running Autotest

Autotest runs against your deployed application (production, staging, or local URL).

  • Manually: Click run button or use the CLI with paragon autotest
  • On Schedule: Daily, weekly, custom
  • Multiple agents: Run 1–8 parallel agents, each with its own browser

Autotest Results

After running, each finding includes:

  • Title and description of the bug
  • Severity rating (critical, high, medium, low)
  • Screenshots captured during the session
  • Reproduction steps from the agent's browser actions
  • Auto-generated Playwright code to reproduce the bug
  • GitHub issues/PRs (when configured)

Performance Tests

Create tests that measure page load performance.

Creating Performance Tests

  1. Go to Testing > Tests
  2. Click New Test and select the repository
  3. Choose Performance as the test type
  4. Enter the pages to test
  5. Configure performance thresholds (budgets)
  6. Set network and CPU throttling conditions
  7. Run the test

Performance Budgets

Set thresholds for key metrics:

MetricDescriptionGood Target
LCPLargest Contentful Paint< 2.5s
FCPFirst Contentful Paint< 1.8s
CLSCumulative Layout Shift< 0.1
TTFBTime to First Byte< 0.8s

Test Conditions

Simulate real-world conditions:

Network Throttling:

  • 4G (typical mobile)
  • Fast 3G
  • Slow 3G
  • No throttling

CPU Throttling:

  • No throttle
  • 2x slowdown
  • 4x slowdown
  • 6x slowdown

Iterations:

  • Run 1-10 times for consistent results

Test Organization

Suites

Tests are organized into suites (folders):

Repository: my-app
├── Suite: Authentication
│   ├── Test: Login flow (E2E)
│   └── Test: Registration (E2E)
├── Suite: Checkout
│   └── Test: Purchase flow (E2E)
└── Suite: Performance
    └── Test: Homepage load

When creating a test:

  • Add to an existing suite
  • Create a new suite

Editing Tests

Click any test to:

  • Update name or description
  • Regenerate code with new prompt
  • Move to different suite
  • Delete test

Next Steps

Test Runner

Learn how tests run on PRs and pushes