# How to optimise AIME Live AIME Live Recommendation Blocks harness the power of AI to display the most relevant product recommendations to your customers, both new and returning. At the core of this AI-powered process are your store’s product tags. ### Why Product Tags Matter Product tags are a simple but powerful way to give AIME Live more context about your products. They provide signals that help Live’s AI engine understand the relationships between different items in your catalogue. When your products are consistently and accurately tagged, AIME Live can: * Match similar and complementary items more reliably * Improve cross-sell and serve smarter, more personalised recommendations * Adapt more effectively to customer behaviour patterns over time ### Crafting High-Impact Tags Make every tag count by following these guidelines: * Describe the Product. Focus on concrete details: *red, leather, oversized.* * Group Logically. Create tags that a customer would use to filter or search, like *gym-friendly or office wear.* * Avoid Temporary Info. Don't use tags for time-sensitive data like *sale* or *new arrivals.* Use collections for that instead. ### Suggested Tags to Include Add roughly 6–10 tags per product, covering: * **Material:** e.g. cotton, leather, wool-blend * **Style or silhouette:** e.g. oversized, cropped, slim fit, boho * **Occasion or use-case:** e.g. wedding guest, gym, everyday * **Seasonality:** e.g. winter, summer, transitional * **Key features:** e.g. pockets, adjustable straps, stretch * **Colours and tones:** e.g. sage green, neutral, bold prints The more information you can give Live through tags, the better your product blocks will perform. --- # 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.aime.app/aime-live/quickstart-user-guides/how-to-optimise-aime-live.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.