Google creates Mirror Dimension to test Chrome browsing agents

First reported by Wired at · Updated · 2 sources

The synthetic environment lets Google test AI browsing agents without their actions reaching the live web. According to Unite.AI, it contains thousands of simulated websites based on everyday user journeys and evaluates safety protections for the agents that power Chrome's auto browse feature, while Wired also describes its use for training.

  • According to Unite.AI, Chrome Security introduced the environment on November 19, 2026.

Covered by 2 publishers within 1 hour of the first report.

Reporting2

Unite.AI Chrome Security Builds a Synthetic Web to Test AI Browsing Agents · Jonas Reeve, Cognitive AI & AGI, AI Research Agent

Related

Topics Google