ZestyAI, a provider of a risk decision platform for the insurance sector, has secured approval from regulators in Minnesota and Maryland for Z-WATER, its AI-driven model for non-weather water risk, bringing the number of states where the tool can be used for rating and underwriting to 22.
Under the latest decisions, insurers operating in the two states can now include Z-WATER in their rate and rule filings. The approvals add to acceptance the model has already gained in more than 20 states, widening the scope for carriers to bring property-specific risk data into how they set prices.
Non-weather water now ranks as the fourth most expensive peril in homeowners insurance, generating over $15bn in losses each year from more than one million claims, ZestyAI said. Rather than stemming from storms or other weather catastrophes, these claims typically arise from routine events such as burst pipes, ageing plumbing and faulty appliances. Conventional rating methods, which lean largely on geographic territory and the age of a property, struggle to pinpoint which individual homes face the highest exposure.
To tackle this gap, Z-WATER draws on computer vision, aerial imagery, property attributes, permit records, local climate data and surrounding infrastructure to forecast how often non-weather water claims will occur and how severe they are likely to be. The model has been trained and tested against insurer loss data, and the company says it achieves 18x greater risk segmentation than traditional approaches based on territory and property age, helping carriers distinguish more precisely between risks within their books.
The new approvals form part of wider regulatory progress for the firm. In September, ZestyAI passed the milestone of 500 regulatory approvals, covering 317 carrier rate and rule filings across 44 states. These span its models for wildfire, severe storms, hail, wind, non-weather fire, non-weather water and property intelligence.
ZestyAI serves Property & Casualty carriers, reinsurers, brokers and regulators in the US and Europe. Its platform brings together property-level data, predictive AI models and agentic AI automation to change how insurers view, price and manage risk. Using machine learning and computer vision, the company supports underwriting, rating, reinsurance and regulatory processes, with models backed by climate science and historical loss data covering perils including wildfire, severe convective storm and non-weather water.
ZestyAI senior director of regulatory and government affairs Bryan Rehor said, “The continued expansion of Z-WATER’s regulatory footprint reflects growing recognition that non-weather water risk can be assessed with far greater precision than traditional methods allow. With each new approval, more carriers have a pathway to incorporate property-level insights into their rating strategies, helping them better distinguish risk across the homes they insure.”
Copyright © 2026 InsurTech Analyst
