QA Wolf is an AI testing platform that maps, writes and runs end-to-end tests for web, mobile and desktop apps. Agents explore your app to plan the test cases it needs, write those tests in open-source Playwright and Appium, and run them in parallel on QA Wolf's cloud. Tests are picked per pull request, so each change runs only the tests it needs.
When a test fails, an agent reads the error, compares it with the last passing run and checks whether the app or the test is at fault. Broken tests are repaired automatically as the app changes. When a test finds a real bug, the agent reproduces it and files a report with video and trace to Linear or Jira.
The product is aimed at product and engineering teams that ship often and want release-ready test coverage without building an internal QA function. The site also describes connectors for coding agents, GitHub and Slack, so that developers can ask for new flows from the tools they already use. Examples on the site include a booking app where a new host-approval flow was created and checked against twelve related flows.
Pricing is per test run, not per seat or per AI token. Web runs cost $1 each, and mobile and desktop runs cost $2 each. A run is one complete QA cycle for one test on one platform, and each run is attempted up to three times for free to catch flakes. Tests longer than five minutes are billed in five-minute blocks. Unlimited AI usage, parallel execution and unlimited users are included. The site also offers a managed service called Coverage-as-a-Service, and a Jump Start option where QA Wolf's team writes the initial suite; both are priced on request.
