Anthropic has added an integrated browser to Claude Code that lets the AI open, read, click, and type on external websites directly within the app. The browser includes safety guardrails to prevent unwanted purchases, account creation, or CAPTCHA bypass without user approval, and organizations can control which external sites Claude can access.
Summaries like this, in your inbox every morning.
Sign up free →What happened
Anthropic integrated a browser window into Claude Code that allows Claude to open, read, click, and type on web pages directly within the app. The browser works like a tab-based browser, opens with a keyboard shortcut, and includes safety checks—classifiers screen write actions on external sites, and Claude will not buy anything, create accounts, or bypass CAPTCHAs without user consent.
Why it matters
Claude can now access documentation sites, issue trackers, and other web resources during coding work without leaving the app, potentially speeding up development workflows. Organizations can restrict access through an allowlist or disable the feature entirely, giving teams control over which sites Claude reaches.
What to watch
Users who need Claude to act within their own logged-in sessions should use the Chrome extension instead of the built-in browser, which runs on a clean profile with no saved logins.
Claude Code previously used tools to preview local apps; Anthropic has extended this capability to the open web with extra safety layers. The integrated browser removes friction for developers who need to reference online resources—documentation, GitHub issues, API references—without context-switching to a separate tab or window. By routing web interactions through safety classifiers, Anthropic is attempting to preserve the convenience of automated web access while preventing unintended side effects like unauthorized purchases or account creation.
The allowlist and disable options signal that Anthropic expects organizational buyers to want granular control, reflecting broader tension between automation and trust in AI tooling. The explicit note that logged-in workflows require the Chrome extension also suggests the company is steering users toward a less automated path when sensitive authentication is involved, rather than trying to handle login state within the sandboxed browser.
No comments yet. Be the first to share your thoughts!
Log in to join the discussion
Get curated AI news from 200+ sources delivered daily to your inbox. Free to use.
Get Started FreeFree · takes 30 seconds · unsubscribe anytime
1 minute a day. The AI essentials.
200+ sources · Email / LINE / Slack
