This feature is available in a private preview mode and accessible only on selected workspaces. To get access, contact your account manager or the Synerise support.

This article provides a step-by-step guide on how to configure AI Shopping Assistant — a conversational tool that makes product discovery more intuitive and personalized. Customers can chat with the assistant in natural language, describing exactly what they’re looking for and refining their preferences in real time — whether it’s style, budget, theme, or specific features. Instead of browsing through endless product lists, shoppers receive tailored products that match their needs right away. The assistant adapts to each interaction, helping customers explore alternatives and make confident purchasing decisions faster. Easy to embed into your website or online store, the AI Shopping Assistant improves user experience, boosts engagement, and helps turn interest into sales with a more natural shopping journey. ## Prerequisites 1. Upload an item feed to a catalog through [API request](https://developers.synerise.com/DataManagement/DataManagement.html#tag/Catalogs/operation/addItemsBatchAsync) or through [a workflow](/use-cases/import-product-feed-to-catalog). If you use [Google Merchant Feed](/developers/product-feed), proceed to the next step. 2. [Configure AI engine for your item feed](/docs/settings/configuration/ai-engine-configuration/engine-configuration-for-search). If you use Google Merchant Feed, in this step, you can launch pulling the feed from the URL. 3. Go to **AI Hub > AI Search** and [create an index](/docs/ai-hub/ai-search/create-index). In the configuration of the index, you must: - add the `category` attribute to facetable attributes. - set the [Matching words option](/docs/ai-hub/ai-search/define-search-method-and-ranking#matching-words) to **At least one word must match**. ## Configuration ### Creating an AI Assistant 1. Go to

**AI Hub > AI Assistant > New AI Assistant**. 2. In the **Definition** section, click **Define**. **Result**: A configuration form displays. 3. In the **Workspace** section: - In **Name**, provide the name for your brand or business. - In **Description**, provide a detailed and precise description of your brand or business. 4. In the **Assistant** section: - In **Description**, describe the purpose of the AI Shopping Assistant clearly and precisely. A detailed description helps the assistant be more effectively. **Example**: `This AI Shopping Assistant is designed to help customers quickly find product information, answer common questions, and provide personalized recommendations based on their preferences and previous interactions with our brand.` - From the **Search index** dropdown list, select the index that will serve as the source of items for the AI assistant. 6. In the upper-right corner, click **Save**. ### Mapping item attributes Below the **Search index** dropdown, map item attributes such as itemId, category, and description. Use the dropdown menus in the **Target** column to adjust the selected attributes from your index so that they correctly correspond to the item attribute listed in the **Source** column.

The Definition section before proper mapping of item attributes

### Testing the AI Assistant In the **Preview** tab, you can test the AI Assistant to evaluate its responses and behavior. Use this feature to enter sample queries or commands, observe how the assistant processes information from your configured data, and ensure it meets your expectations. This step helps you identify any issues or necessary adjustments before deploying the assistant for actual use.