The Shopify integration now supports indexing metaobjects, enabling rich and reusable content such as size guides, store locations, and brand stories to be searchable and filterable in Algolia. Configuration is managed directly in the Shopify plugin, including selecting metaobject types, fields, and transformations. Updates sync automatically via webhooks, ensuring records stay current without manual reindexing. This reduces the need for custom pipelines or workarounds while enriching search results with structured content. Click here to learn more.

Safety Controls in Agent Studio introduce guardrails for deploying agents in production. Configure global and per-IP rate limits to handle spikes, set limits on tokens, steps, and conversation depth to manage cost, and restrict access using domain allowlists. This helps prevent abuse, reduce unexpected spend, and ensure agents are only accessible from approved environments.

A new Guardrails configuration in the Safety Controls tab allows defining custom categories to filter harmful or off-topic content across input, output, or both. Each category includes a description, examples, and an optional fallback response, helping teams control how agents handle sensitive or irrelevant queries. This improves response quality, reduces risk, and ensures interactions stay aligned with the intended use case. Click here to learn more.

The Agent Studio widget search bar now features an AI mode button and context-aware prompt suggestions. As shoppers type, relevant suggested prompts appear that transition them directly into the chat experience with a single click. The AI mode button provides a persistent, prominent entry point from search to natural language conversation, reducing friction for users moving between search and chat.

Optional filters now work with virtual replicas, enabling boosting or burying of specific results after sorting. Previously limited to standard replicas, this capability extends advanced relevance tuning to virtual replica configurations without requiring additional replica indices. Search teams can now apply promotion and demotion strategies across all sorting configurations, combining the efficiency of virtual replicas with fine-grained relevance control. Click here to learn more.

Recommend analytics delivers clear visibility into how recommendation models perform across the site. Track clicks, conversions, revenue, and purchase rates for each model within the existing Recommend workflow. Built-in performance dashboards make it easier to quantify impact, optimize placements, and drive measurable growth towards your business goals. Click here to learn more.

Agent Studio now supports user authentication and persistent memory across sessions. This update introduces secure user identification and conversation tagging, enabling agents to maintain continuity over time. By linking interactions to user IDs, agents can retain context, recall preferences, and build on past conversations to deliver more personalized and consistent experiences. Learn more in the Conversations and Memory documentation.

Agent Studio now includes an analytics dashboard that provides clear visibility into agent usage and performance. Track key metrics such as conversation volume, tokens consumed, search calls, and unique authenticated users. These insights help teams better understand engagement, optimize agent behavior and cost, and make data-driven decisions to improve overall effectiveness. Click here to learn more.

A new component, Filter Suggestions, is now available to enhance search and discovery interfaces with the Agent Studio. It can be added to search results or product listing pages to suggest relevant filters based on user queries. These suggestions are grounded in available filters within the index, ensuring accuracy and reliability. By proactively surfacing the most relevant filters, this feature helps users narrow results faster, explore content more efficiently, and achieve higher-quality search outcomes. Click here to learn more. 

The Productivity MCP introduces a new type of MCP Server designed to help users perform internal actions within Algolia environments. Expanding beyond the Public MCP’s initial scope, it now includes read access to Analytics data and includes standard authentication and security flows. This addition enables users to work more efficiently by accessing a broader set of insights and information directly through the MCP, improving productivity when managing Algolia implementations. Click here to learn more.