Shiplight AI
Shiplight AI
Shiplight AI is an autonomous AI-powered end-to-end (E2E) testing platform that generates, runs, and maintains tests automatically, helping teams ship faster without breaking their product.
About Shiplight AI
Shiplight AI is an agent-native end-to-end testing platform. It installs into a coding agent such as Claude Code, Cursor, Codex, VS Code or Antigravity as an MCP server plus a set of Skills, giving the agent control of a real browser. The agent walks the app, verifies UI changes, and writes tests as plain-English YAML committed to the repository, describing user intent rather than selectors.
Shiplight is built on Playwright: each YAML test transpiles to a standard Playwright test at run time, and teams can eject at any time. Tests run locally, on Shiplight-hosted CI runners, or on a team's own infrastructure. Settled steps replay from cache without a model call; when a locator goes stale, Shiplight re-resolves the intent and updates the cache mid-run. Failures land on the pull request with logs, screenshots and traces, and the agent can reproduce, diagnose and update the test, or report an application bug.
The same browser skills support accessibility, security and performance reviews. Users quoted on the site include heads of QA and engineering and CTOs, and the platform offers SOC 2 compliance, audit logs and VPC deployments for enterprise teams.
Best for
- Engineering teams using AI coding agents
- QA teams tired of maintaining Playwright tests
- Startups needing fast end-to-end coverage
- Enterprises requiring SOC 2 and VPC deployment
Pros
- Readable plain-English YAML tests stored in the repo
- Self-healing locators update mid-run without stopping
- Built on Playwright with no lock-in; tests can be ejected
- All core features on free plan, including own LLM key
Cons
- SSO is only available on the Enterprise plan
- Free plan limited to 5 members and 30-day artifact retention
Pricing
Free plan at $0 forever with every core feature and a $10 signup credit, Pro at $60/month with $60 monthly credit and pay-as-you-go, and custom-priced Enterprise; yearly billing saves 17%.
Shiplight AI FAQ
- Do I need an account to start?
- No. Local browser automation and test authoring need no account or API token; an account adds hosted CI runners, result history and dashboards.
- Do I need to know Playwright?
- No. The coding agent writes and maintains plain-English YAML tests, with Playwright used as the execution engine underneath.
- Can I use my own LLM key and infrastructure?
- Yes. On any plan, including Free, you can bring your own Anthropic, OpenAI or Google key and run tests on your own CI runners.
- Which coding agents are supported?
- The site lists Claude Code, Cursor, Codex, VS Code and Antigravity, with a quick start for others.
Compare Alternatives
See what other makers use instead of Shiplight AI
Ekcho
Pseudonymous voice broadcasting app. Record your voice anonymously — no real name, no face. Say the thing you never say out loud.
acta.ai
Acta is a cutting-edge platform designed to streamline meeting conversations, placeholder for all your meeting discussions and structured way of following up on Action points.
1Transcribe
1Transcribe is a transcription app that delivers highly accurate transcripts, allowing users to effortlessly edit while listening to the original audio.