The Federal Trade Commission (FTC) on October 15 has sent civil subpoenas to OpenAI and Anthropic, seeking documents about safety incidents, security measures, privacy policies and marketing materials,according to a Reuters report. 

The investigation is being conducted in the United States amid growing scrutiny of advanced AI systems after incidents in which models took unexpected actions, including unauthorized activity involving external websites. 

The FTC is examining whether those events or the companies’ practices may have caused consumer harms that could be considered unfair or deceptive.

The FTC also plans to compel executives at OpenAI, Anthropic and the research group METR to testify, while additional subpoenas to other organizations in the AI sector could follow, according to Reuters.

AI Safety Becomes a Data Governance Issue

For chief data officers (CDOs), the investigation highlights the importance of maintaining records on how AI systems are developed, deployed and monitored.

Safety incidents can generate information that companies may need to preserve and analyze, including model behavior, system access, safeguards, affected users and remediation efforts. 

Without consistent records, organizations can struggle to establish how an incident occurred or whether appropriate controls were in place.

The FTC’s requests also cover privacy policies and marketing materials. That puts greater importance on maintaining consistency between what companies tell users about their AI systems and how those systems actually handle information.

Regulatory Scrutiny Raises the Governance Bar

The investigation shows how AI governance can extend beyond model performance. Companies need processes for documenting AI risks, tracking incidents and preserving evidence of the controls applied to systems handling sensitive information.

For CDOs, this means working with security, legal and compliance teams to ensure AI-related records are captured and governed throughout the system lifecycle.