Fume
FreemiumYour AI QA team for Playwright end-to-end tests
About Fume
Fume is an AI QA team that creates and maintains Playwright end-to-end browser tests. Users describe what they want to test with a single Loom video, and Fume autonomously generates and maintains the Playwright tests. These tests automatically run twice-a-day on Fume's cloud, providing insights and notifications on failures. Fume offers AI agent fallbacks for self-healing tests, free cloud test runners, and ensures 100% Playwright code ownership, allowing users to run tests locally or integrate into CI/CD pipelines. It also supports migrating existing Playwright, Selenium, or Cypress tests.
How to Use
To use Fume, record a screencast of your application (e.g., using Loom) and describe what you want to be tested as you navigate. Fume then extracts test cases from your video in seconds. Once the tests are ready, they automatically run twice-a-day on Fume Cloud, and notifications are sent to a shared channel. Users can also configure advanced settings like CI/CD integration.
Key Features
- AI-powered Playwright test generation from video descriptions
- Automated test maintenance and self-healing (AI Agent Fallbacks)
- Automated daily test runs (twice-a-day) on Fume Cloud
- Free test runners in the cloud
- 100% Playwright code ownership
- Migration of existing Playwright, Selenium, or Cypress tests
- Insights and notifications on test failures
Use Cases
- Generating an extensive Playwright test suite overnight for new applications.
- Automating end-to-end browser testing without manual test design, writing, or maintenance.
- Ensuring application quality and preventing regressions with continuous testing.
- Migrating existing test suites (Playwright, Selenium, Cypress) to leverage AI fallbacks and auto-maintenance.
- Teams looking to move fast without breaking things by getting an autonomous QA department.
Key Features
Pros & Cons
- Generates Playwright tests directly from Loom screencast videos
- Autonomous test maintenance with self-healing AI agent fallbacks
- Free cloud-based test runners with twice-daily scheduled runs
- 100% Playwright code ownership – tests are editable and portable
- Supports migration from Playwright, Selenium, and Cypress
- Provides failure insights and notifications for fast debugging
- Requires recording a screencast (e.g., Loom) to describe test scenarios
- Only generates Playwright tests; does not support other test frameworks natively
- Dependency on external video recording tool for input
- Limited documentation and community support (as of available data)