Tutorials

Two worked end-to-end tutorials take the same scenario — a guest checkout on a storefront — from a plain-language test case to automation running in a pipeline and on a schedule. They differ in where you work and what you own, and each can be followed on its own.

Agentic test automation with Step Studio (UI)

Choose this if you own the requirement and the journey the business cares about, and you would rather not write code or selectors. You work in Step Studio: describe the journey in plain language, read what the agent produced and the evidence behind it, run it on a Step instance, and schedule it against the live application.

Agentic test automation from the command line (CLI)

Choose this if you own the code and the pipeline. You drive the agent from the CLI where your code is: generate the package, review it as code, extend an existing test case to cover what the journey does not, and use the result as a merge gate in CI/CD.

They are two halves of one story. The Step Studio tutorial ends where the Developer picks the package up; the command-line tutorial ends where the Tester reviews it and puts it on a schedule. Follow either first.

For the same storefront driven prompt by prompt instead of delegated, see AI-Assisted Testing with the Step MCP Server.