GenAI-native end-to-end QA agent that plans, writes and heals tests in plain language
Fume records 811 monthly visits with +492% month-over-month growth and Free Trial, Paid, Contact for Pricing pricing. Shiplight AI records 33,676 monthly visits with -8.2% growth and Contact for Pricing pricing.

An AI QA team that writes and maintains Playwright tests from a screen recording
| Dimension / Metric | ![]() | ![]() |
|---|---|---|
| Official Domain | fumedev.com | shiplight.ai |
| Pricing Model | Free Trial, Paid, Contact for Pricing | Contact for Pricing |
| Monthly Visits | 811 (811) | 33.68K (33,676) |
| MoM Traffic Delta | +674 (+492%) | -3.02K (-8.2%) |
| Primary Market & Share | 🇹🇷 Türkiye (68.6%) | 🇻🇳 Vietnam (20%) |
| Direct Visits / mo | 331 | 13.84K |
| User Rating | 4.3 | 4.3 |
| Supported Platforms | Website | Website |

An AI QA team that writes and maintains Playwright tests from a screen recording
Record a Loom-style video while narrating what should be tested, and Fume extracts the test cases and writes them as native Playwright code — covering most key user flows in minutes.
When fragile selectors or changed UX break a script, tests fall back to a browser-using AI agent to continue, and the flaky test is self-healed in the background.
Tests run twice a day automatically on Fume Cloud runners at no extra cost, with results and failure insights delivered straight to your team's channel.
Every test is standard Playwright code you own, so you can run it locally or wire it into CI/CD with one API call and keep running even if you cancel.

Agent-native end-to-end testing that maintains itself
Install Shiplight into Claude Code, Cursor, Codex, VS Code or Antigravity so your agent can drive a real browser and author tests.
Tests describe user intent in plain-language YAML committed to your repo, reviewable in pull requests and editable in a local debugger.
Stale locators are re-read and re-resolved with AI mid-run, so intended changes heal automatically while real bugs still fail.
The same test file runs locally, on Shiplight-hosted CI runners, or on your own infrastructure, with results posted to the PR.
GenAI-native end-to-end QA agent that plans, writes and heals tests in plain language

Ship with confidence: one system of record for manual, automated, and CI tests
AI-augmented quality platform for web, mobile, API and desktop testing
Agentic end-to-end testing that writes, runs and heals your test suite
Agentic end-to-end testing that writes, runs and heals your test suite

Write end-to-end test automation in plain English, no code required
Write end-to-end test automation in plain English, no code required
Agentic AI QA engineer for web, iOS, and Android testing
Agentic AI QA engineer for web, iOS, and Android testing

AI testing platform for the entire software testing lifecycle
AI testing platform for the entire software testing lifecycle

Autonomous AI QA agents that verify your web and mobile app on every pull request
Autonomous AI QA agents that verify your web and mobile app on every pull request

Agentic test automation that builds, runs and maintains your enterprise tests
Agentic test automation that builds, runs and maintains your enterprise tests

Natural-language end-to-end testing for mobile and web apps

Agentic QA that tests every change like a real user and opens the fix PR
Agentic QA that tests every change like a real user and opens the fix PR
AI test automation and self-healing QA for enterprise apps and AI agents
AI test automation and self-healing QA for enterprise apps and AI agents