https://step.dev/knowledgebase/31/ai/step-agent/ Recent content in Step AI Agent on Step Documentation Hugo -- gohugo.io en Tue, 29 Sep 2026 00:00:00 +0000 https://step.dev/knowledgebase/31/ai/step-agent/getting-started/ Tue, 29 Sep 2026 00:00:00 +0000 https://step.dev/knowledgebase/31/ai/step-agent/getting-started/ The Step AI Agent ships as a Step Automation Package. You give it the test cases to produce, and collect a finished and validated package when it completes. You choose how you interact with it. Choose your path The three paths below run the same workflow and produce the same automation package. Work from Execution Best for Step Studio Local A visual UI for defining test cases, launching runs and reading reports, with no command line IDE Local Working in your own toolchain, on your existing code base Step Platform Central Running with nothing installed locally, on shared infrastructure, with agentic and automation results visible to the whole team Before you start Check the CLI version. https://step.dev/knowledgebase/31/ai/step-agent/tutorials/ Tue, 20 Oct 2026 00:00:00 +0000 https://step.dev/knowledgebase/31/ai/step-agent/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. https://step.dev/knowledgebase/31/ai/step-agent/configuration/ Tue, 06 Oct 2026 00:00:00 +0000 https://step.dev/knowledgebase/31/ai/step-agent/configuration/ Reference for everything a run accepts. For a first run, Getting started covers the two required parameters and a minimal example. Execution parameters Parameter Required Meaning instructions yes The test cases to produce and what each must cover. apDirectory yes Where the finished package is published. If a package is already there, it is extended rather than replaced. stepApiKey for central runs API key for the Step instance the generated package is executed against. https://step.dev/knowledgebase/31/ai/step-agent/data-privacy/ Tue, 29 Sep 2026 00:00:00 +0000 https://step.dev/knowledgebase/31/ai/step-agent/data-privacy/ The Step AI Agent calls a large language model (LLM) as part of producing automation packages. Content from the application under test therefore reaches a model by design. This page states what does, what does not, and what you decide. Unlike the Step MCP Server, which never calls a model itself and leaves that choice to your own AI assistant, the agent makes those calls within its workflow. What leaves your environment While producing automation, the agent sends to the model: