Google brings Gemini AI directly Into Chrome browser

Google has started rolling out a new feature that integrates its artificial intelligence assistant Gemini directly into the Google Chrome browser. The move allows users to interact with AI tools while browsing websites, making it easier to analyse content, ask questions and summarise information without switching tabs.

The integration is designed to improve the browsing experience by allowing Gemini to understand and respond to the content displayed on the page currently open in Chrome. Users can request explanations, summaries, or clarifications while staying within the same tab.

AI Assistance Within the Browser

With this integration, users can open a dedicated Gemini chat panel within Chrome and interact with the AI assistant in real time. The assistant can analyse articles, documents or other content on the page and provide key takeaways or explanations.

The feature supports both text-based conversations and voice interaction through Gemini Live, enabling users to speak directly with the assistant during browsing sessions.

The rollout began with Chrome version 143, initially targeting most Google Workspace users in the United States who already have access to the Gemini app.

Multi-Tab Context for Smarter Browsing

Google has also introduced a multi-tab context feature in Chrome 143. With this capability, Gemini can analyse up to ten open tabs simultaneously.

This allows users to compare information across different websites, locate specific details quickly, or summarise content gathered from multiple sources. The feature is designed to help researchers, students, and professionals manage large amounts of online information more efficiently.

Integration With Google Services

Gemini in Chrome can also access information from several Google services to deliver more contextual responses. These include Google Search, Google Maps and YouTube.

With the user’s permission, the AI assistant can also connect with personal data stored in Google Workspace services such as Gmail, Drive, Keep, Calendar and Tasks. This integration enables Gemini to provide more personalised assistance while browsing.

New Features Introduced in Chrome 144

Alongside the initial rollout, Chrome 144 introduces additional features that expand Gemini’s capabilities.

One notable feature, called Auto Browse, allows the AI assistant to automatically perform certain browsing actions for some non-enterprise users. In enterprise environments, administrators can manage this functionality through a dedicated policy known as GeminiActOnWebSettings.

Chrome 144 also allows users to upload rendered images directly to Gemini using the browser’s context menu. Once uploaded, users can ask the AI to generate modified or derivative images based on the visual.

In certain situations, Gemini can also use Google Password Manager, with user consent, to sign in to websites automatically.

Enterprise Controls and Security

For enterprise organisations using Chrome in corporate environments, administrators retain control over Gemini’s functionality.

Workspace administrators can disable Gemini integration through GeminiSettings or GenAiDefaultSettings policies, ensuring organisations can manage AI features in line with their security requirements.

Wider Global Rollout Planned

The Gemini integration has already begun reaching select ChromeOS devices with Chrome 144 and will continue expanding across platforms.

Google plans to broaden availability with Chrome 145, gradually rolling out the feature to users in Canada, New Zealand and India, in addition to the United States.

The feature will support multiple languages, including Hindi, Bengali, Gujarati, Kannada, Malayalam, Marathi, Tamil and Telugu, as well as global languages such as Spanish, French, German, Japanese, Korean and Chinese.

As AI continues to reshape how users interact with the internet, the integration of Gemini into Chrome represents another step toward making artificial intelligence a built-in part of everyday browsing.