# AI loops {% embed url="" %} You can convert any `Test` experiment into an `AI loop` experiment. An AI loop requires a goal function, expressed as a formula of your [event types](/concepts/event-types.md). Instead of setting fixed traffic percentages for each arm, Hypertune automatically and continuously learns the best arm for each dimension. If the AI loop has a payload event type, the payload event fields are used as features for personalization. For example, you can set up an AI loop to personalize the content on your landing page for each unique visitor, to maximize conversions. --- # Agent Instructions: 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: ``` GET https://docs.hypertune.com/concepts/ai-loops.md?ask= ``` The question should be specific, self-contained, and written in natural language. 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.