Google AI Search Mode Integrates Third-Party Apps for Direct Actions

Image credit: Search Engine Journal

Google began rolling out connected applications within its AI Mode in Search this week across the U.S., allowing users to send search queries directly to third-party services.

This new functionality allows users to perform operations such as adding groceries to Instacart, locating templates on Canva, or curating playlists on YouTube Music directly from Google‘s AI-powered search interface.

The feature differs from Google’s existing ‘Personal Intelligence,’ which utilizes connected Google applications for contextual information rather than sending direct requests to external services, according to the company.

Initial partners for the launch include Instacart, the design platform Canva, and Google-owned YouTube Music.

The underlying technology for this integration is built upon the Model Context Protocol (MCP), an open standard designed to link artificial intelligence systems with external tools.

Chips Mistry, a Google spokesperson, stated that the company aims to expand the range of integrated applications in the future, noting that the selection process for eligible apps involves a combination of user demand and developer interest.

Biharck Araújo, a product manager at Google, indicated that the integration seeks to streamline user workflows by reducing the need to switch between multiple applications for common tasks.

The introduction of connected apps in AI Mode raised questions regarding the criteria for application eligibility and the potential impact on search visibility for services not yet integrated.

Google has not yet disclosed specific details on how third-party developers can apply for integration or the timeline for expanding the program beyond the initial partners.

Other services such as OpenTable, Dropbox, and Zillow Rentals were cited by industry analysts as potential future candidates for similar integrations, based on their utility for direct user actions.

Source: Search Engine Journal