AI Assist can now draft new rules from a plain-language request, automating one of merchandisers’ most frequent manual tasks. Simple pins, category boosts and advanced consequences can all be built through conversation, with no JSON or developer needed. Drafts are labelled AI-assisted, open in the Visual Editor for review, including a drafted rule description, and these rules never publish without approval.
Analyze rule and category page performance with AI Assist. AI Assist can now analyze the performance of rules and category pages, providing an insight into how merchandising strategies impact search performance. Assist can also provide feature analysis and more complex performance breakdowns, such as by-country, that would have previously required dedicated data science resource.
Agent Studio now supports the Agent2Agent (A2A) protocol, enabling external agents and orchestration frameworks to discover and interact with Agent Studio agents. Standardized agent cards allow compatible clients to identify agent capabilities and delegate tasks without Algolia-specific integrations. This simplifies integration with multi-agent workflows and enables greater flexibility in building AI applications. Click here to learn more.
Agent Studio now supports automated evaluations to help assess agent performance before deployment. Test cases are generated from your search index and scored for relevance, faithfulness, and tone. View scores, pass rates, and confidence levels, then compare evaluation runs to measure improvements after configuration changes. This helps teams make informed updates with less manual testing. Click here to learn more.
Automated suggestions proactively recommends Algolia features based on search performance and potential business impact. The initial release covers Dynamic Re-Ranking, Personalization, and NeuralSearch. View prioritized recommendations in the Algolia dashboard, understand their expected benefits, and access the relevant features to optimize search performance.
Dynamic Re-Ranking now offers a setting that combines clicks and conversions across records in the same Distinct group. This helps rank products based on engagement across their variants rather than treating each record separately, improving how product-level popularity influences search results. Click here to learn more.
The No results agent in AI Assist analyzes searches that return no results and recommends ways to improve search performance. It identifies potential issues with search settings, searchable attributes, and synonyms, then suggests targeted fixes. Apply supported changes directly in AI Assist or follow guidance to address other issues, helping more users find relevant results.
Native retail media network (RMN) orchestration is now generally available for Elevate Ecommerce customers. Connect any RMN provider using HTTP API key authentication and configure sponsored product groups without code in Merchandising Studio. Algolia handles external calls, result merging, and deduplication in a single request, reducing integration effort while maintaining search relevance. Click here to learn more.
No more jumping between two rule editors. You can now build every type of rule right in the Visual Editor - context-only rules, remove or replace a word, replace a query, return custom data, and apply search parameters - along with matching facet placeholders for the Filter and Boost matching attributes consequence. Together with conditionless rules, which landed a few months ago, that means the full set. Set up your rules and preview exactly how they'll behave, all in the place you already merchandise. Click here to learn more.
Query Suggestions can now provide more relevant suggestions when shoppers search within a specific category, department, brand, seller, or other scope. Configure a browsing facet in the Dashboard to use your existing catalog structure and show suggestions that match the shopper’s selected scope. This makes experiences such as “Search within this category” easier to build and more relevant. Click here to learn more.
