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 Type | Method | What It Creates |
|---|---|---|
| E2E Tests | Autotest | Autonomous browser-based tests |
| Performance | Inline Config | Performance 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
- Go to Testing > Autotest
- Click New Test
- Select the repository
- Enter the target URL and a description of what to test
- Configure the number of agents and timeout
- Run the test
How It Works
- Planning — A planning agent analyzes the target app and distributes testing work across agents
- Exploration — Each agent navigates the app in a real browser, performing actions like clicking, typing, scrolling, and navigating between pages
- 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
- 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:
| Method | Description |
|---|---|
| Login instructions | Describe login steps in plain English (e.g. "click Login, type user@test.com into email, type pass123 into password, click Submit") |
| Cookies file | Export cookies from your browser and pass the JSON file |
| Team session | Shared, 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
- Go to Testing > Tests
- Click New Test and select the repository
- Choose Performance as the test type
- Enter the pages to test
- Configure performance thresholds (budgets)
- Set network and CPU throttling conditions
- Run the test
Performance Budgets
Set thresholds for key metrics:
| Metric | Description | Good Target |
|---|---|---|
| LCP | Largest Contentful Paint | < 2.5s |
| FCP | First Contentful Paint | < 1.8s |
| CLS | Cumulative Layout Shift | < 0.1 |
| TTFB | Time 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