Natural Language Tests
Don't want to wait for auto-discovery? Describe your test scenarios in plain English — or in any supported format — and RoostGPT generates complete, runnable Playwright tests from your descriptions.
Supported Input Formats
| Format | Description |
|---|---|
| Plain text | Free-form test scenario descriptions in natural language |
| Markdown | Structured test scenarios with headings and steps |
| Gherkin | Given/When/Then syntax for BDD-style scenarios |
| Word | Test requirements or user stories from .docx documents |
| Test specifications or acceptance criteria | |
| Excel / CSV | Tabular test scenarios with columns for steps, inputs, and expected results |
| JSON | Structured scenario definitions |
How It Works
- Provide your test descriptions through the RoostGPT Web UI or via
USER_SCENARIO_FILE_PATHin the CLI - RoostGPT parses the input, identifies individual test scenarios, and validates which are automatable
- The system maps scenarios against the target application's pages and elements
- Complete Playwright test code is produced with proper navigation, interactions, and assertions
Upload a single file with multiple scenarios and they are automatically split into individual, self-contained tests.
Example: Plain Text Input
Test that a user can log in with valid credentials and see the dashboard.
Test that submitting the contact form with all required fields shows a success message.
Test that searching for "wireless headphones" returns at least one product result.
Test that adding an item to the cart updates the cart count badge.
Each description produces a self-contained Playwright test with navigation, element interaction, and meaningful assertions.
Example: Gherkin Input
Feature: Shopping Cart
Scenario: Add item to cart
Given I am on the product listing page
When I click "Add to Cart" on the first product
Then the cart badge should show "1"
And I should see a confirmation message
Scenario: Remove item from cart
Given I have one item in my cart
When I click "Remove" next to the item
Then the cart should be empty
Smart Validation
Before generating test code, the system evaluates each scenario:
| Status | Meaning |
|---|---|
| Automatable | Scenario can be fully automated as a Playwright test |
| Partially automatable | Some steps require manual verification |
| Needs review | Scenario is ambiguous or references elements that cannot be located |
Scenarios that need review are reported with specific guidance on what to clarify.
Custom Instructions
Guide the generation with your team's coding standards, naming conventions, selector strategies, or any other team-specific requirements. Your words, real tests — the generated tests faithfully reflect your described intent.
Next Steps
- Autonomous Discovery — Let AI discover scenarios automatically instead
- Page Object Model — How generated tests use POM architecture
- Reports & Output — Output formats available
- Configuration Reference — Input-related settings