Promote Sign in Sign up

Agent

Fume

AI QA team creating and maintaining Playwright browser tests from video.

Source rating 5.0 (91) 820 views 820/mo traffic 0 saves Paid
AI testing tool Playwright tests End-to-end testing
More categories (9)
Browser testing Test automation QA Automation AI QA team autonomous QA Test maintenance Cloud Testing Self-Healing Tests no-code testing alternative
Visit website Sign in to save

From $500 / month

Verdict

A quick read before you dig into the full page.

Best if
AI QA team creating and maintaining Playwright browser tests from video
Skip if
You need a free plan with no credit card
Pick this when
Paid · From $500 / month

Overview

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.

Fume screenshot

Access & connections

Where you can use Fume.

Platforms

Web

Capabilities

What this tool accepts, produces, and is strongest at.

Highlights

  • 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

FAQ 9

What is 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 Fume?
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.
What does Fume do?
Fume is your AI QA team. Describe what you want to test with a Loom video and Fume will create and maintain Playwright end-to-end browser tests for you.
How does Fume know how to use my app?
Fume explores your application just like a human QA engineer would and writes Playwright tests.
How do I integrate Fume tests into my CI/CD pipeline?
You can integrate tests into your CI/CD pipeline with a single API call.
Do I own the Playwright code even after I cancel my subscription?
Yes, Fume tests are 100% in Playwright. You have the full codebase ownership and can run them locally.
How does Fume handle broken tests?
Fume tests natively fall back to a browser-use agent to pick up exactly where the script left off. The flaky script is then self-healed in the background.
Who is Fume for?
Fume is for growing teams that need autonomous QA and large organizations requiring custom solutions, effectively replacing entire QA team operations.
Can I migrate my already existing Playwright/Selenium/Cypress tests to Fume?
Yes, you can migrate your existing Playwright, Selenium or Cypress tests to Fume to instantly gain native AI fallbacks and auto-maintenance.
Fume From $500 / month
Visit website