MENA Newswire, MOUNTAIN VIEW: Google is expanding Gemini artificial intelligence features in its Chrome browser, adding a built-in side panel for the assistant, an image creation and editing tool, and a new automated browsing option designed to carry out multi-step tasks on the web.
The update places Gemini in a persistent panel on the right side of Chrome, allowing users to keep the assistant open while navigating across tabs. Google said the panel is intended to help with common browsing workflows, including asking questions about what is on screen, summarizing content, and working across multiple open pages without switching away from the current tab.
Chrome is also gaining an image feature called Nano Banana that lets users generate images from text prompts and edit images they encounter while browsing. The capability is designed to reduce the steps needed to create or modify visuals, keeping the process inside the browser instead of requiring separate apps or uploads to external tools.
The third major addition is Auto Browse, which Google describes as an agent-style feature that can complete web tasks from a single prompt. Examples described by the company include filling out online forms, comparing items across websites, and handling steps in shopping or subscription management that typically require repeated clicking and copying between pages.
Auto Browse and the new Gemini experiences are built on Google’s Gemini 3 model, according to the company’s product briefing about the Chrome changes. Google said the features are rolling out for Chrome on macOS and Windows, and are also part of the updated experience on Chromebook Plus devices.
Gemini side panel and in-browser image tools
The Gemini side panel is positioned as an always-available assistant within Chrome rather than a pop-up, enabling users to keep a conversation active while browsing. Google said users can use the panel to work alongside web pages, including pulling information from the current page and helping organize or refine information across multiple tabs during research, travel planning, and shopping comparisons.
Nano Banana brings image generation and editing directly into Chrome. Google said users can create images from prompts and make targeted edits to existing pictures, including changes to specific elements, without leaving the browsing session. The company has also described Nano Banana as part of its broader image-generation stack within Gemini, including options aimed at more advanced output and control.
Google said some features depend on user settings and eligibility, including subscription tier and geographic availability. The company has positioned Nano Banana and the Gemini panel as broadly available Chrome additions, while Auto Browse is being introduced with narrower access.
Auto Browse availability and user controls
Google said Auto Browse is initially available in the United States for Google AI Pro and Google AI Ultra subscribers. The feature is accessed through the Gemini experience in Chrome and is designed to follow instructions that span multiple pages and steps, such as searching, comparing, and completing routine web actions.
For actions that could affect accounts or payments, Google said Auto Browse requires user confirmation before completing sensitive steps. The company has described the tool as operating with user oversight, with prompts and approvals intended to keep people in control of sign-ins, purchases, and other consequential actions.
Separately, Google’s “Personal Intelligence” capability, which connects Gemini to Google services such as Gmail and Photos, has been introduced as a beta feature in the United States for eligible subscribers. Google said users can choose to link apps in settings so Gemini can provide responses that draw on the user’s own content, depending on what the user enables.