> For the complete documentation index, see [llms.txt](https://docs.garak.ai/garak/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.garak.ai/garak/automatic-red-teaming/garaks-auto-red-team.md). # garak's auto red-team garak include an auto red-team module, `art`. Plugins in this have different targets; for example, `art.Tox` tries to get a model to produce toxicity. The probe works by loading a red-teaming model, and conducting a "conversation" between the red-team model and the specified generator. The red-team model is prompted with the generator's output, or with nothing if it's the first conversation. It will try to provoke the generator into a failure mode depending on the plugin. Conversation turns progress a fixed number of times, or until the generator repeats itself, or (optionally) if the generator stops responding. There's a blog post detailing the basic version of garak's `art` module here, --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.garak.ai/garak/automatic-red-teaming/garaks-auto-red-team.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.