OK, I have the hotdogs, the burgers, the buns, the ketchup, the cheese… Hmm, do I have everything? Oh! Beer! I almost forgot the beer!

Next Queries provide shoppers with ideas on what to look for next. In other words, this feature predicts what shoppers might need next before they even know they need it. For example, “nachos”, “guacamole”, or “tacos” might be the next search suggestions for “beer”.

Next queries are related to the initial query, so they usually appear after performing a first search. When a shopper selects a next query, a new search launches without needing to type the search term.

You can identify next queries mostly under labels such as What’s next?, Those who searched for X also searched for, or Other people have also searched.

Organic, curated, and AI Next Queries

With Empathy Platform, you can show organic, curated, and AI next queries in your commerce store:

• Organic next queries: These are generated automatically based on collective behavioral information, offering the most common searches that are performed by other shoppers after the initial search.

• Curated next queries: They let you curate the search experience and suggest search suggestions that shoppers might like to use after their initial search to drive sales as part of a branded campaign. For example, as category manager you decide to guide shoppers towards a branded beer by associating a query containing the brand name as next query after the query “hot dogs”, instead of the organic next query beer.

• AI next queries: They're automatically generated using AI mechanisms from the top queries performed in your store after a given query. For example, for the query "bed" in a furniture store, the LLM can surface next queries like beside table, headboard, and mattress. AI next queries can display together with organic and curated next queries as long as there's enough traffic volume for the initial search query. Since AI next queries are synthetically generated, they effectively address cold start challenges.

How Next Queries types work together

When a shopper performs a search, all three types of next queries can display together in the same list, in the following order: curated, organic, and synthetic.

You can use the Next Queries curation tool in the Empathy Platform Playboard to review the organic next queries generated for a query, create new curated next queries that respond to marketing strategies, change the order in which the curated next queries appear, and choose to show or hide organic next queries. AI next queries aren't yet configurable in the Playboard, so you can't edit or delete them.

A celebrity working on your jewelry new campaign

See how curated Next Queries can benefit your shoppers and your business

Spot the difference

Although Next Queries and Related Tags are suggestions closely related to the initial search, Next Queries prompts a new query in the search box and launches a completely new search. On the other hand, Related Tags refines the current search without changing the query syntax in the search box.

Try Next Queries to...

• Anticipate shoppers' intent by offering new search suggestions that support your merchandising strategy.
• Improve product findability. Guide shoppers to products they want or are likely to need next.
• Speed up query entry, especially on mobile devices.
• Offer shoppers a shopping list-like feature.

The inner workings of Next Queries

Each type of Next Queries follows a different generation path in the background to display in your search experience:

Organic Next Queries

Organic next queries are generated by shoppers’ actions in the search UI. As shoppers perform different searches and actions, behavioral information (queries, clicks, add-to-cart, etc.) is collected using the Tagging microservices.

This information is analyzed by the Query Signals batch process to select the possible query pairs from the same session related to a specific query. So, from the query pairs “milk-cereal”, “milk-cocoa”, “milk-cookies”, cereal, cocoa, and cookies are identified as the organic next queries for the query “milk“ based on the highest interaction.

A review process is performed to check if each query pair is valid according to different filters (that is, it doesn't feature on a blacklist, it isn't duplicated, etc.) and a ready-to-go list of organic next queries is created and stored by the Beacon microservice.

note

Next Queries can also use the local web data stored in the shopper’s browser to determine precisely when a query was written, displaying only those next queries that haven’t been used yet in the current session. For that purpose, you use the History Queries feature.

Curated Next Queries

Curated next queries are created manually by the commerce marketer or merchandiser in the Playboard and sent to the Beacon microservice to be stored with the organic and AI next queries. When the shopper performs a search in your commerce store UI, Empathy Platform Interface X calls the Beacon API to retrieve a list of organic and curated next queries associated with the query, displaying them in the commerce store after the initial search.

interact

Want to learn more about how you can tailor the search experience for Next Queries? Read how to configure next queries in the Empathy Platform Playboard and the options available in the Next Queries UI component.

AI Next Queries

AI next queries are synthetically generated using an LLM. The process takes the store's top search queries, sourced from the Empathize batch process output, as its starting point. For each query, the workflow retrieves its search results and feeds them to the LLM together with the query and a prompt describing the generation task. These results give the LLM context about the store's catalog, so it generates next query suggestions that relate to the products or categories shoppers actually find.

The LLM's output then goes through a review process before it reaches shoppers. Suggested queries are checked against actual search results, and any suggestion that returns no results gets discarded. The remaining next queries are also normalized (for example, converted to lowercase and depluralized) to ensure consistent matching with how shoppers search.

Once validated and normalized, the suggestions are loaded into the Beacon microservice and stored alongside the organic and curated next queries.

When the shopper performs a search in the search UI, Empathy Platform Interface X calls the Beacon API to retrieve all next queries available for that given query regardless of the type.

note

AI next queries are powered by Empathy.AI (opens new window). The generation workflow runs on private, sustainable, self-hosted infrastructure, so no query, catalog, or shopper data gets shared with third parties, guaranteeing data sovereignty and operational resilience.