Deep research System Card

This report details safety measures implemented before releasing a deep research system, including external red teaming exercises and frontier risk evaluations. The work follows a structured Preparedness Framework and includes built-in mitigations to address identified key risk areas.

• →External red teaming was conducted as part of the safety evaluation process.
• →Frontier risk evaluations were performed according to a Preparedness Framework.
• →Key risk areas were identified and addressed through built-in mitigations.
• →Safety work was completed prior to the system's release.
• →The approach follows a structured framework for AI safety assessment.