Tools & Products

Anthropic Pilots "Claude for Chrome" AI Browser Agent

The company is testing an autonomous browser extension while publicly detailing the security risks and its safety mitigation efforts.

Olivia Sharp 2 min read 576 views
Free
Anthropic began a controlled pilot of its "Claude for Chrome" AI agent on Aug. 26, taking a transparent approach by publishing red-teaming results showing its new safety mitigations.

AI company Anthropic announced on Aug. 26, 2025, that it has begun a controlled pilot of "Claude for Chrome," a browser extension that allows its AI model to operate as an autonomous agent. The move is a significant step toward more integrated AI assistants, and the company accompanied the launch with a transparent disclosure of the security risks and the results of its internal adversarial testing.

Functionality and Pilot Program

The Claude for Chrome extension is designed to see what a user sees in their browser, click buttons, and fill in forms to perform tasks. Potential uses include managing …

Archive Access

This article is older than 24 hours. Create a free account to access our 7-day archive.

Share this article

Related Articles