InstantSearch Android has been updated to support the latest Algolia Kotlin client and the Ktor 3.x framework. This update addresses compatibility gaps introduced by recent ecosystem changes and ensures InstantSearch Android works with modern Kotlin stacks. By aligning with current dependencies, this improvement removes upgrade blockers for Android developers, supports long-term maintainability, and enables continued adoption of newer Kotlin and Ktor versions without relying on workarounds. Click here to learn more.

DocSearch v4.5 introduces a new side-panel Ask AI experience available in standalone mode or triggered from search in hybrid mode, enabling richer assistance without leaving the page. This release also adds Agent Studio support, allowing DocSearch to use the same agent architecture as other Algolia products, and expands framework support with VitePress compatibility and upcoming Docusaurus adoption. Ask AI thread depth controls let customers set a maximum conversation depth, improving response accuracy and cost predictability for longer side-panel or full-page conversations. Click here to learn more.

The Public MCP now offers enhanced configuration options, giving users greater flexibility when setting up their MCP servers. Users can toggle individual tool groups, such as Search or Recommend, to create customized configurations. Additionally, AI-generated index descriptions can now be automatically created to reduce manual setup work and speed up initial configuration, helping teams start faster and maintain consistency across environments. Click here to learn more.

AI Synonyms now suggests only candidates that meet a higher quality threshold. As a result, customers will see fewer recommendations overall, with each suggestion more likely to be relevant and actionable. The updated scoring threshold reflects observed acceptance patterns, where most approved synonyms scored above 0.7 and most rejected ones fell below. Email notifications for AI Synonyms suggestions are now sent monthly instead of weekly, with the option to opt out. This update reduces noise in both the dashboard and inbox.

The latest DocSearch release brings a more powerful, flexible, and conversational experience for both developers and end users. A redesigned Playground Editor offers live previews and deeper configuration control, while DocSearch v4.3 introduces Suggested Questions, a composable API, and improved UI/UX stability. Field Mapping now supports custom data shapes, expanding compatibility beyond crawler-generated content. With enhanced performance and new Ask AI–powered search on Algolia Docs, DocSearch delivers faster setup, richer customization, and smarter discovery. Click here to learn more.

Customers can now promote the winning variant of an AB test with a few clicks from the dashboard UI. This enhancement allows users to declare a winner after an AB test and then copy those settings to their production index. Users can easily promote all query parameters and index settings, as well as settings for Personalization, Dynamic Re-Ranking, and Neural Search. Variant promotion for multi-index tests does not copy rules or synonyms and we recommend reviewing your production settings after promotion. Customers can revert their settings within 14 days of a change, providing flexibility to restore previous configurations if needed. 

AI Assisted No Code Transformations is now available in Public Beta. This enhancement lets business users describe data clean-up or enrichment needs in plain English, with the system automatically generating the data transformation logic. It reduces complexity, speeds up experimentation, and ensures cleaner, better-structured data for improved search and discovery experiences. Click here to learn more.

Collection limits have been significantly increased to support larger-scale operations. Premium plans now include 500 collections per index, Elevate plans support 1,000 collections per index, with each collection supporting up to 10,000 manual records and 50 conditions. This reduces trade-offs between campaigns and enables more targeted seasonal collections for improved user engagement.

Shopify merchants, now benefit from improved indexing performance with a new engine designed for scalability and reliability. Indexing is more consistent during high-traffic periods, ensuring fresher product data is available sooner. The update also unlocks access to data transformations and fetch for greater customization, along with a new Connection Debugger that provides visibility into indexing operations and helps merchants troubleshoot issues directly. Now automatically available to all merchants not leveraging Shopify's Markets feature.

Interpreting A/B experiment results can often be complex, especially when assessing the significance of observed differences. To provide greater clarity and statistical context, confidence intervals have been introduced. These intervals help indicate the range within which the true effect is likely to fall, making it easier to evaluate the reliability of experiment outcomes. Confidence intervals are visualized on a time series chart, positioned directly below the standard A/B test results.