Anthropic Adds Claude Cowork to Chrome for AI Tasks Across Tabs and Devices

Anthropic Adds Claude Cowork to Chrome for AI Tasks Across Tabs and Devices

Anthropic is bringing Claude Cowork directly into its Claude in Chrome extension, turning the browser side panel into a persistent Cowork session that can carry conversations and tasks across Chrome and Claude’s desktop, web, and mobile apps. The updated side panel is available to Max and Team subscribers today, with Pro access rolling out over the coming weeks.

The change removes a previous separation between work done inside the Chrome extension and conversations in Anthropic’s other Claude apps. Side-panel conversations are now stored in a user’s history, while their existing Claude skills and connectors are also available from the browser. That continuity allows users to begin a task while browsing and resume the same session elsewhere without losing its context. A task can also move in the opposite direction, starting in a Claude app before continuing inside Chrome.

Claude in Chrome gives the AI access to the page a user is viewing and allows it to perform browser actions such as following links, entering text, moving between pages and completing forms using the user’s existing authenticated sessions. The browser access can extend Claude’s ability to work with services that do not connect to it directly, including internal dashboards, older software and vendor portals.

Anthropic illustrates the workflow with a budgeting task involving invoices stored across multiple vendor portals. Claude can navigate the relevant browser tabs, extract invoice dates and amounts, and use that information to create a spreadsheet. The user can then continue the same session in the desktop app, where local files can be added or an earlier budget can be imported for comparison.

The browser integration also comes with security considerations because Claude can take actions on a user’s behalf. Anthropic identifies prompt injection as a primary risk: hidden or malicious instructions embedded in websites, emails or documents can attempt to steer an AI agent toward actions the user did not request.

Anthropic says it has added an additional review mechanism for Claude’s browser actions since the Chrome extension’s pilot. When automatic approval is enabled, Claude can proceed through routine parts of a task without requesting permission at each stage. Before consequential actions such as sending a message, submitting a form or downloading a file, a separate check compares the proposed action with the user’s original instructions and can block actions that do not align with them.

Claude continues to request approval for certain actions that could be irreversible or expensive, including purchases and sharing personal information. Anthropic cautions that its safeguards reduce but do not eliminate prompt-injection risks and recommends initially using the browser agent on trusted sites.

Users can access the new Cowork side panel by installing Claude in Chrome, signing in and opening the extension’s side panel. Enterprise customers have Claude in Chrome disabled by default, though administrators can enable it and restrict access to approved domains.

The Chrome extension still has some boundaries. Working directly with files stored on a computer or interacting with other desktop applications requires the Claude desktop app. Claude in Chrome also does not currently operate on other Chromium-based browsers or on mobile.

See more here:

This analysis is based on reporting from Claude.

Image courtesy of Claude.

This article was generated with AI assistance and reviewed for accuracy and quality.

Last updated: August 13, 2026

About this article: This article was generated with AI assistance and reviewed by our editorial team to ensure it follows our editorial standards for accuracy and independence. We maintain strict fact-checking protocols and cite all sources.

Word count: 541Reading time: 0 minutes

📧 Stay Updated

Get the latest AI news delivered to your inbox every morning.

Browse All Articles
Share this article:
Next Article

AI News Daily

Breaking Intelligence • Since 2023

Join hundreds of thousands of AI professionals who start their day with our curated newsletter. Get breaking news, expert analysis, and exclusive insights.

Stay Ahead of AI

Get the latest AI breakthroughs, tools, and insights delivered to your inbox every week.

Free forever Unsubscribe anytime No spam guarantee

Go Premium

Unlock unlimited AI tools and an ad-free reading experience designed for AI professionals.

• Ad-free experience• Premium AI tools
Start Free Trial

14-day free trial • Cancel anytime
Plus $9/mo • Pro $90/yr (2 months free)

Follow Our Community

ChatAI

Breaking Intelligence

Your daily briefing on what matters in AI. Trusted by developers, researchers, executives, and AI enthusiasts worldwide.

© 2026 ChatAI. All rights reserved.