QA Wolf
Also known as: QA Wolf, QAWolf, QA Wolf Inc
End-to-end testing platform whose agent maps an app and writes Playwright and Appium tests from prompts, run in parallel on deploy, schedule or pull request, sold self-serve by usage or as a managed service with guaranteed coverage.
QA Wolf is an end-to-end testing platform and managed service for web and mobile applications. On the platform, its agent explores an application with computer-use models, maps its workflows into a coverage outline, and turns plain-language prompts into deterministic Playwright and Appium tests that the customer owns and can export at any time. It can work unattended from a prompt or be guided by a person, reads linked documentation and team skill files, and diagnoses and repairs broken tests after failures.
Tests run in parallel on QA Wolf's infrastructure across browsers, Android emulators and real iPhones and iPads, triggered on deploy through GitHub, GitLab or a webhook, on a schedule, or on pull requests where Smart Smoke Suites pick the affected flows. Run Rules sequence flows and their dependencies, and flows can pass data between each other.
Judge-model assertions check AI-generated responses, and tests can validate MCP servers, email and SMS, phone audio and visual diffs. Results sync to Jira, Linear and test management tools, and a REST API, CI SDK, CLI and an MCP server for coding agents open the platform to other tools. QA Wolf is SOC 2 Type II compliant and supports SSO over SAML and OpenID Connect.
QA Wolf sells two ways: a self-serve Platform at 1 cent per AI credit and 15 cents per runner minute, which can be tried for free, and Coverage as a Service, where QA Wolf's own team builds, runs, investigates and maintains the suite with guaranteed coverage, zero flakes and human-verified bug reports, priced per test under management.
Vendor details
Canonical URL
https://www.qawolf.com
Category
Agent infrastructure
Subcategory
Agentic Coverage as a Service E2E testing with human in the loop
Funding status
QA Wolf is independent and headquartered in Seattle. It was founded in 2019 by CEO Jon Perl, a former Zipdrug engineer. It raised a thirty six million dollar Series B in July 2024, led by Scale Venture Partners with participation from Threshold Ventures, Ventureforgood, and existing investors Inspired Capital and Notation Capital. Total funding is reported at roughly fifty seven million dollars across rounds. It serves more than one hundred thirty customers, including Salesloft, Drata and AutoTrader.ca.
Company status
independent
Use cases & customers
Primary use cases
Target customers
Deployment options
Integrations
Integrates directly with the CI pipeline so tests run pre merge on pull request branches and developers ship at the speed of AI, and covers web, iOS, Android, Electron, and Salesforce applications. Agents ingest videos of user flows along with DOM snapshots and browser logs to generate open source Playwright code for web and Appium code for mobile, which the customer owns.
In practice
A team's releases keep getting stuck in QA. QA Wolf's agents map the app and generate Playwright and Appium tests while its engineers maintain the suite, delivering eighty percent coverage in weeks and pre merge smoke tests in CI.
A flaky test would normally page an engineer at 2am. QA Wolf's Zero Flake Guarantee means a human QA engineer verifies every failure before the dev team is ever alerted.
A team ships an AI feature with non deterministic output. QA Wolf uses LLM as a judge assertions to evaluate it, extending E2E testing to the agentic parts of the app.
Sources & related URLs
Related / legacy domains
Agentic Index coverage score
10.0 / 14 capabilities · 71%
| Integrations & Tool Calling | Full |
|---|---|
|
Bug reports flow into Jira and Linear, where QA Wolf automatically creates, syncs and closes issue tickets, and results sync to test management tools (TestRail, Xray, Zephyr, Qase and Testmo). Deployments are heard from GitHub and GitLab, notices go to Slack and Microsoft Teams, and webhooks reach any other bug tracker. Its tests can call APIs, seed databases, toggle feature flags and use email inboxes. Writes into the customer's issue trackers mean access runs both ways, and webhooks and helper libraries extend it to other tools. SourceQA Wolf, docs.qawolf.com Jira, Linear, test management integrations and webhooksread 2026-09-21 |
|
| Workflow Orchestration | Full |
|
Run Rules sequence the order of flows and their dependencies in a suite, and flows pass authentication tokens, user IDs and other values between each other in a coordinated run. Tags build custom suites, runs execute in parallel with automatic reruns of failures, and triggers choose which flows run on each deploy or schedule. SourceQA Wolf, docs.qawolf.com Run Rules, pass data between flows, tags and triggers, and qawolf.com/pricingread 2026-09-21 |
|
| Knowledge Grounding & RAG | Partial |
|
Before it builds or explores, the agent reads documentation linked in a prompt, test plans, product requirements and help docs, and it applies team conventions written into custom skill files in every session. Company knowledge enters as linked pages and skill files the agent reads per session. There is no index, retrieval layer or refresh of the customer's sources. SourceQA Wolf, docs.qawolf.com test automation, coverage mapping and custom skillsread 2026-09-21 |
|
| Human Oversight & Guardrails | Partial |
|
Tests can be created unattended from a prompt, or the agent can work with a person who guides it, and a person can take over the browser during mapping while the agent watches. The generated tests are standard code the team reviews and versions. Choosing guided or unattended working sets an autonomy mode, but there is no approval step that holds the agent's action for a person. SourceQA Wolf, docs.qawolf.com test automation and coverage mappingread 2026-09-21 |
|
| Security, Identity & Governance | Full |
|
QA Wolf is SOC 2 Type II compliant, verified through independent audits, with HIPAA ready infrastructure. Customers can set up single sign-on over SAML 2.0 and OpenID Connect, so people sign in through the customer's identity provider, and credentials are stored securely for use in tests. SourceQA Wolf, docs.qawolf.com why QA Wolf (security and data protection) and single sign-onread 2026-09-21 |
|
| Observability & Auditability | Partial |
|
Each run of the customer's tests is recorded with results, the verdict reached when evaluating each deployment for a trigger is kept, and a person can watch the agent open a browser and explore during mapping. There is no step by step record of the agent's own prompts, tool calls and decisions. SourceQA Wolf, docs.qawolf.com triggers and diagnosing a trigger, coverage mapping, and qawolf.com/pricingread 2026-09-21 |
|
| Memory & State Persistence | Not documented |
|
The coverage map, the test code and run history persist, and skill files the team writes apply in every agent session. There is no session, workflow or long term memory that the agent itself writes and reuses. SourceQA Wolf, docs.qawolf.com custom skills and coverage mappingread 2026-09-21 |
|
| Deployment & Data Residency | Partial |
|
Tests run on QA Wolf's own managed infrastructure, with a shared, allowlisted or private iOS device pool, local runs through its CLI, and Playwright tests customers can export at any time. The platform cannot be deployed in the customer's environment, there is no choice of data region, and QA Wolf does not say where data is kept. SourceQA Wolf, docs.qawolf.com iOS device pools, CLI local execution, and qawolf.com/pricingread 2026-09-21 |
|
| Prebuilt Agents, Templates & Packs | Not documented |
|
QA Wolf offers solution recipes and helper libraries for testing scenarios such as emails, barcodes, video injection and web performance. There is no catalog of ready made agents, templates or packaged workflows that a customer adopts for its own work. SourceQA Wolf, docs.qawolf.com solutionsread 2026-09-21 |
|
| Triggers & Channel Coverage | Full |
|
Triggers run chosen flows whenever an application deploys, reported through GitHub or GitLab deployments or a webhook, or on a schedule. Smart Smoke Suites automatically select the flows affected by each pull request, and the automation agent diagnoses broken tests and refactors test code after failures. Work starts on a deploy, a schedule or a pull request without a person asking. SourceQA Wolf, docs.qawolf.com triggers, Smart Smoke Suites, and qawolf.com/llms.txtread 2026-09-21 |
|
| Model Flexibility & Routing | Full |
|
The judge model is the customer's choice in the non-deterministic AI assertions, and ChatGPT works as a drop in replacement with the same signature and return shape. They are designed for apps that use different AI providers, so the customer makes the model choice in its own tests. SourceQA Wolf, docs.qawolf.com non-deterministic AI assertionsread 2026-09-21 |
|
| APIs, SDKs & MCP Extensibility | Full |
|
A REST API gives direct HTTP access to core platform actions, alongside a TypeScript CI SDK for triggering and reading runs, a CLI for running flows locally, flow and test libraries with API references, and deployment webhooks. An MCP server lets coding agents such as Claude Code and Codex build and run the suite. Together these give a stable API and SDK, an MCP interface and a fit into CI/CD. SourceQA Wolf, docs.qawolf.com REST API overview, CI SDK reference, CLI and QA Wolf MCPread 2026-09-21 |
|
| Testing, Debugging & Optimization | Full |
|
An application's end to end workflows are mapped into a coverage outline, and the agent generates deterministic Playwright and Appium tests from plain language prompts and runs them in parallel on deploy, on a schedule or on pull requests. Judge model assertions return a structured verdict with hard and soft thresholds on a customer's AI generated responses, and tests validate MCP connections and tool execution. Testing happens before release, as a gate in CI and continuously after. SourceQA Wolf, docs.qawolf.com why QA Wolf, test automation, non-deterministic AI assertions and triggersread 2026-09-21 |
|
| Browser & Computer Use | Full |
|
Computer use models let the agent open a browser and explore each feature of the customer's application, documenting the workflows it finds. A person can take control of the browser while the agent watches, and tests run in real browsers and on Android emulators and real iPhones and iPads. So the agent controls a real interface. SourceQA Wolf, docs.qawolf.com coverage mapping and why QA Wolf, and qawolf.com/pricingread 2026-09-21 |
|
The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
Product updates
AI Investigation, now live for all users, puts an agent on each test failure while the suite is still running. It clears environment causes of flakes and re runs the test, repairs broken tests while keeping the same assertions, and reproduces real bugs in its own browser to file a report with video, traces and repro steps. One lead agent routes related failures to the same investigator, so one fix can clear several tests at once.
Bears on: Agent capability
View sourceQA Wolf now runs fully parallel end to end tests against native Windows desktop applications. Users pick Windows as the test target or ask the QA Wolf agent, and the platform provisions a clean Windows VM per test, installs the app and records the run.
Bears on: Browser/computer use
View sourceQA Wolf made its MCP server generally available for Codex, Claude Code and other MCP compatible coding agents. A coding agent can now ask QA Wolf's agents to find existing test coverage, write or update tests, run them, investigate failures and file bug reports with video, traces and logs. The QA Wolf CLI offers the same capabilities when local files or local runs are needed.
Bears on: MCP / tool calling / API
View sourcePricing
1¢ per AI credit and 15¢ per runner minute on the Platform, after a free trial. The managed service, Coverage as a Service, is priced by quote.
Usage on the Platform, at $0.01 per AI credit and $0.15 per runner minute, with no seat fees. Coverage as a Service is priced by the number of tests under management.
What is public
The Platform's rates are public, at 1 cent per AI credit and 15 cents per runner minute after a free trial. Coverage as a Service is public in shape only, priced per test under management with everything included, so costs are locked to the managed test count, and its rates are by quote.
Billing mechanics
The Platform is self serve and billed by usage, per AI credit and per runner minute. Coverage as a Service is sales led and outcome based, billed per test for the number of tests QA Wolf manages and bundling investigation, maintenance, setup, and cleanup, so spend is locked to the managed test count rather than hourly labor.
Cost watchouts
Runner minutes accrue with every parallel test run, so large suites run on each deploy add up. The managed service scales with the number of tests under management.
Variable cost rationale
The Platform meters two things, AI credits and runner minutes. Suite size, run frequency and parallel runs on every deploy make the bill grow, since AI usage and parallel runs are unlimited and no cap or prepaid commitment is published. Seats carry no fee, so adding users costs nothing. Coverage as a Service bills per test under management, with investigation, maintenance, setup and cleanup included. Its cost grows as coverage grows and stays fixed for a given managed test count.
Additional watchouts
On Coverage as a Service, billing scales with the number of managed tests, so growing coverage raises cost. No per test rate or minimum is published, and coverage builds over an onboarding ramp of several weeks.
Sales call required
Mixed (some tiers require a call)
Free / trial
The Platform can be tried for free
Lowest paid plan
Platform, pay as you go at 1¢ per AI credit and 15¢ per runner minute
Commercial notes
QA Wolf sells two ways. On the self serve, usage based Platform, the customer's team automates and maintains its own tests. On Coverage as a Service, QA Wolf's team builds, runs, investigates and maintains the suite for a quote per test under management.
Key ambiguities
How many AI credits typical exploration, creation and maintenance tasks consume is not stated, and Coverage as a Service rates are by quote. Platform browsers are Chrome, Firefox and WebKit, while iOS, Android and Electron are listed under the managed service.
Support SLA / resale
Coverage as a Service includes investigation and maintenance within 24 hours, with guaranteed 80%+ coverage and zero flakes.
Missing data
Per test rates and volume tiers for Coverage as a Service are not published.
Related vendors
- AgentOps — Agent observability and debugging platform: open source SDKs trace…
- AgentPhone — AgentPhone gives the AI agents a team builds their own US or…
- Agno — Python agent framework and AgentOS runtime (formerly Phidata) for…
- AIsa — Resource and payment gateway for AI agents, with one key to 110+…
- Albato — Albato is a no code integration platform that sells an embedded,…
- AlphaBitCore — AI control plane for regulated financial firms: one gateway enforces…
Alternatives to QA Wolf
The closest documented capability profiles to QA Wolf among agent infrastructure platforms tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- Anchor Browser11.0 / 14Adds documented Prebuilt Agents, Templates & Packs
- Paragon10.0 / 14Fuller documented coverage on Knowledge Grounding & RAG and Observability & Auditability
- Pipedream11.0 / 14Adds documented Memory & State Persistence
- Apify10.5 / 14Adds documented Memory & State Persistence and Prebuilt Agents, Templates & Packs
- BotGauge8.5 / 14Adds documented Prebuilt Agents, Templates & PacksQA Wolf vs BotGauge →
- Inworld AI8.5 / 14Adds documented Memory & State Persistence
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded