Insurance under pressure: shared AI rules as adoption outpaces governance

In 2023, US insurance regulators faced a concrete problem: insurers were increasingly deploying AI systems for underwriting, pricing and claims handling, but without shared standards to guard against inaccuracies, discriminatory bias and data vulnerabilities. The sector risked a patchwork of state-by-state expectations, with each insurance department potentially imposing different requirements on the same companies operating across multiple markets.

The NAIC (National Association of Insurance Commissioners) responded through collective drafting: its Innovation, Cybersecurity, and Technology Committee, made up of representatives from 15 states and chaired by Commissioner Kathleen Birrane, wrote a Model Bulletin in 2023 on the use of artificial intelligence systems by insurers. It is not a binding law or regulation, but a guiding document meant to bring uniformity to how state regulators approach responsible AI deployment in the industry.

NAIC members adopted the bulletin at the Fall National Meeting in December 2023, explicitly addressing the risks of inaccuracies, unfair bias leading to discrimination, and vulnerabilities in the data feeding these algorithms. The outcome is a common baseline that individual state departments can build their own regulatory expectations on, reducing the risk of an inconsistent patchwork for insurers operating across state lines.

When a regulated industry adopts AI faster than the rules governing it, preemptive standardization, even non binding, is worth more than after the fact correction: it gives companies a clear reference point before bias or accuracy problems turn into litigation or penalties.