QA Wolf
By QA Wolf. Category: Agentic end-to-end testing. Homepage
QA Wolf's documentation describes QA Wolf as a platform that maps an application, generates end-to-end tests from natural-language prompts and runs them on managed infrastructure. Tests are Playwright and Appium code owned by the customer, wrapped in QA Wolf's flow() helper and run by the QA Wolf runner or the qawolf CLI. Supported surfaces are web, native iOS and Android, and Electron desktop apps. CI integrations include GitHub Actions, GitLab CI and CircleCI. The QA Wolf MCP plugin for Claude Code and Codex can investigate and repair failing flows. The pricing page lists a managed Coverage as a Service option.
Description written from the vendor's documentation.
Status
Status: Active
Facts
| Fact | Value | Evidence | Source | Verified on |
|---|---|---|---|---|
| Status | Active | Documented | qawolf.com | |
| AI capabilities | Documented | docs.qawolf.com | ||
| Test creation | Documented | docs.qawolf.com | ||
| Test output | Mixed | Documented | docs.qawolf.com | |
| Surfaces | Documented | docs.qawolf.com | ||
| Hosting | Documented | docs.qawolf.com | ||
| Pricing model | Documented | qawolf.com | ||
| Free tier | Not documented | Not documented | None found | |
| CI integrations | Documented | docs.qawolf.com | ||
| Self-healing | Documented | Documented | docs.qawolf.com | |
| Agent integration | QA Wolf MCP, installed as a plugin for Claude Code (qawolf/agent-plugins marketplace) and Codex; other coding agents via client-specific setup guide | Documented | docs.qawolf.com |
Published prices
| Plan | Price | Billing |
|---|---|---|
| Platform (AI credits) | 1¢ per AI credit | usage-based |
| Platform (runner minutes) | 15¢ per runner minute | usage-based |
Vendor-stated, verbatim
What QA Wolf says about its product, quoted as published and not confirmed in documentation.
“100% of teams achieve 80%+ automated test coverage in weeks.”
“Guaranteed zero flakes. You will never be alerted to a test flake, only real bugs get flagged.”
“100% parallel test execution”
“The tests run in 11 minutes. There's about 300”
Alternatives
Tools in the same category (Agentic end-to-end testing), ordered by the number of shared creation and surface values, then by name. Each line lists documented facts that differ from QA Wolf.
- Autify: documents creation by recording; hosting self-hosted; a free tier
- Katalon: documents output Proprietary runner; creation by recording; a free tier
- Robonito: documents creation by autonomous from URL, recording; a free tier
- TestDriver: documents output Proprietary runner; hosting self-hosted
- UiPath Test Cloud: documents output Proprietary runner; hosting self-hosted
- ACCELQ: documents output Proprietary runner; creation by recording; hosting self-hosted, hybrid; a free tier
Comparisons
Questions
Is this page a review of QA Wolf?
No. This page is a fact sheet. Each fact shows its evidence level, its source and the date it was checked. We do not rate or rank tools.
Does QA Wolf have a free tier?
A free tier is not documented for QA Wolf as of 2026-09-24.
What test output does QA Wolf produce?
Output: Mixed. This is documented, checked on 2026-09-24.
Is QA Wolf still available?
Status: Active, checked on 2026-09-24.
Sources
- QA Wolf homepage Opened
- QA Wolf pricing Opened
- QA Wolf docs welcome Opened
- QA Wolf docs index (llms.txt) Opened
- Why QA Wolf? Opened
- Test Automation Opened
- QA Wolf MCP Opened
- Integrations Opened
- Anatomy of a flow Opened
- Set up a local-only project Opened
Spotted an outdated or wrong fact about QA Wolf? Send the source and we apply it at the next monthly update.