Resources

ZestyAI today announced an expanded partnership with Steadily, a top-rated insurer for rental properties, to deliver advanced hail and wind risk models that enable more precise underwriting. Building on a successful rollout in 2024, Steadily is broadening its use of ZestyAI’s property-specific insights to better assess storm risk and support growth across high-exposure states.

With operations in all 50 states and $300 million in annualized gross written premium, Steadily is one of the fastest-growing insurers in the U.S.

Steadily first adopted ZestyAI’s Z-HAIL™ and Z-WIND™ models in four high SCS states. With a successful proof of concept, the company is now extending usage to additional states in the coming months.

Datha Santomieri, Co‑Founder & COO of Steadily, said:

“Expanding our use of ZestyAI’s hail and wind models reaffirms our commitment to precision and efficiency in landlord underwriting. These insights help us make informed decisions quickly and manage exposure with greater confidence.”

ZestyAI’s platform predicts the likelihood and severity of storm-related claims by analyzing how localized climatology interacts with individual property characteristics — a sharp contrast to traditional models that rely on ZIP code or territory-level assessments. Each model is built and validated on extensive real-world claims data and delivers transparent explanations of the key factors behind every risk score.

Together, Z-HAIL and Z-WIND help insurers identify storm risk at the parcel level by evaluating roof condition, structural complexity, historical losses, and local storm exposure, enabling the granularity needed to underwrite confidently in volatile regions.

“Steadily is modernizing a critical segment of the market with their customer-centric, tech-forward approach,” said Attila Toth, Founder and CEO of ZestyAI.

“We’re proud to support their growth with AI-driven insights that enable better pricing, smarter underwriting, and more resilient portfolios.”

ZestyAI’s severe convective storm models are currently approved by regulators in 19 states and used by leading insurers across the country.

After years of working with leading insurers, one reality has become undeniable: enterprise data quality is one of the biggest hidden risks in the industry. 

The Problem: Carriers Don’t Trust Their Own Data

Data enters the system at the quote stage. That means it often comes directly from agents and policyholders—well-intentioned, but subjective. Did the policyholder really know the exact roof age? Did the agent catch the secondary structures in the backyard?

Inspection resources are limited, and most carriers can’t validate this information at scale. The result is a house of cards: data that looks complete in the policy system, but is riddled with blind spots and inconsistencies.

And even when the data is accurate in the moment, it quickly decays. Structures are living assets, meaning:

• Roofs degrade.
• Weather events roll through.
• Families expand, renovate, and change how they use the property.
• Secondary structures, pools, trampolines, and solar panels appear overnight.

The underwriting file that was “clean” at binding can be outdated and incomplete by renewal. Over time, carriers lose confidence that they have a real view of risk. 

The Six Dimensions of Data Quality

Data quality isn’t one thing—it’s multidimensional. For carriers, the challenge is ensuring property data is:

• Accurate: Correct at the point of use, not just at intake.
• Complete (and unbiased): Captures all risk-relevant details, verified against independent sources so fields aren’t left blank, misstated, or skewed by incentives.
• Consistent: Aligned across systems, from quoting to claims.
• Valid: Structured to meet business and regulatory rules.
• Timely: Refreshed when things change, not years later.
• Unique: De-duplicated, with a single source of truth.

By this standard, most carrier data today is falling short.

From Data Quality to Data Integrity

Data quality is foundational, but it’s only part of the picture. True data integrity comes from combining accurate data with the right context and continuous observability.

That means not just having the right roof age or square footage, but knowing whether that data has changed, and whether it aligns with other signals in the environment. It means having a complete, transparent, and continuously updated picture of every property.

 The ZestyAI Solution: Verified, Transparent Property Data

At ZestyAI, we built our property intelligence platform to solve exactly this problem. By unifying multiple independent data streams—and applying AI to synthesize them—we deliver property data that carriers can trust.

Here’s how we do it:

Imagery + Computer Vision

We ingest aerial, satellite, and terrestrial imagery, then apply over 90 proprietary computer vision models. These models don’t just “see” a property; they interpret it. That means extracting hard-to-get details like:

• Roof condition and penetrations
• Yard debris and overhanging vegetation
• Secondary structures and solar panels

This creates a dynamic, objective record of what’s on the ground, property by property.

Geospatial and Hazard Data

Context matters. We overlay geospatial layers to understand how a property interacts with its environment, including wildfire exposure, flood risk, and more.

Building Permits

Using large language models (LLMs), we extract and synthesize the real changes reflected in building permits: bathrooms added, kitchens renovated, roof replacements, solar installations. Permits reveal what’s changed, not just what was once approved.

Market and Public Records

We enrich the picture with MLS transactions, tax assessments, climatology, topography, and infrastructure data. Together, these data sources confirm and contextualize what imagery and permits reveal.

Standards and Designations

We integrate authoritative designations, such as IBHS Fortified™ standards, to validate resilience features.

Each data source adds a layer of verification. Together, they create a comprehensive, continuously updated property record that carriers can rely on.

 
Why This Matters: Enterprise Data Quality Transformed

When carriers bring ZestyAI data into their systems, the impact is immediate:

• More Accurate Underwriting and Rating: Quote data is validated against independent sources. That means fewer surprises at claim time, more consistent rating, and appropriate premiums.
• Change Detection and Accurate Renewals: Our models detect what’s changed since policy inception, leading to smarter renewal decisions, more proactive outreach to policyholders, and reduced leakage.
• Better Reinsurance Negotiations: Clean, transparent data helps carriers secure the right terms, conditions, and pricing from reinsurers—because they can prove their book is based on verified risk, not guesswork.
• Operational Efficiency: By replacing guesswork and manual inspection with AI-verified data, carriers reduce expenses and focus resources where they matter most.
• More Accurate Customer Communications: Data quality isn’t just about pricing and underwriting. It’s about trust. Verified property details enable carriers to send personalized, timely, and accurate communications.
• Renewal notices, policy updates, or even hurricane prep guidance land with credibility because they reflect the customer’s real property. That strengthens engagement, reduces confusion, and builds long-term retention. 

The Bottom Line

Carriers can’t compete in today’s market with messy, decaying data. Enterprise data quality is no longer a “back office” concern. It’s a competitive edge.

ZestyAI’s property intelligence platform solves the problem at its core: by continuously verifying property data with imagery, geospatial science, permits, and AI-powered interpretation.

That’s how carriers build trust in their data. That’s how they write better risks, renew smarter, negotiate stronger, and communicate with customers more effectively. 

Want to see how ZestyAI can transform your enterprise data quality? Contact us for a demo.

ZestyAI today announced a new partnership with Applied Home National Underwriters to adopt ZestyAI’s full suite of regulatory-approved models and property insights in support of more accurate underwriting, pricing, and portfolio management across its U.S. property insurance operations.

This includes peril-specific models for non-weather water (Z-Water™), wildfire (Z-Fire™), hail (Z-Hail™), wind (Z-Wind™), and severe convective storm (Z-Storm™). It also includes property insights that combine aerial imagery, building permits, and parcel-level data to identify risk-relevant features such as roof condition, vegetation overhang, and secondary structures.

ZestyAI’s models use proprietary AI trained on billions of data points, including aerial imagery, parcel-level attributes, building permits, climatology, and real-world loss data, to deliver precise, property-specific risk intelligence that supports confident risk selection, loss ratio improvement, and more robust concentration management across perils.

Brian Voorhees, Chief Operating Officer, Applied Home National Underwriters, said:

“ZestyAI’s AI-powered risk models offer the kind of granular, verified intelligence that strengthens risk evaluation across a broad spectrum of perils, from climate-related threats to non-weather water.”

“This partnership deepens our commitment to innovation and precision in underwriting and portfolio management.”

“Applied Home National Underwriters is known for taking on complex risks with clarity and conviction,” said Attila Toth, Founder and CEO of ZestyAI. “We’re proud to support that with trusted, property-specific insights that help sharpen underwriting, align pricing with true risk, and strengthen portfolio performance.”

In property insurance, roof age is one of the most critical factors in assessing risk. Yet too often, carriers rely on self-reported or agent-supplied data that is incomplete or inaccurate.

ZestyAI’s recent analysis of 500,000+ properties revealed widespread discrepancies in reported roof age. The result? Mispriced policies, unexpected losses, and operational inefficiencies that impact the bottom line.

As climate volatility grows and reinsurance pressure intensifies, overlooking the true condition and age of a home’s largest, most exposed surface is a risk no carrier can afford.

What’s Inside

• Uncover the biggest myths and blind spots in roof age records.
• Understand why traditional data sources, like claims systems and permits, fall short in providing accurate roof age.
• Learn how a multi-source verification strategy, combining aerial imagery, permits, tax records, and AI, offers a blueprint for improvement and 97% national coverage.
• Explore why roof age is a predictor of losses across multiple perils, not just wind and hail.
• Discover the one-two punch of verified roof age and real-time condition insights, delivering a complete view of risk, even for young roofs with hidden problems.
• Align your roof age data with growing regulatory expectations, particularly in states like Florida.

Access the Guide.

ZestyAI has secured regulatory approval to use its AI-powered Severe Convective Storm models in underwriting and rating in Nebraska and Kansas. The move greenlights Z-HAIL™, Z-WIND™, and Z-STORM™, for use in property-level hail and wind scoring, giving carriers more transparency and precision in two of the nation’s most storm-prone states.

2024 Loss Trends Highlight Urgency

Kansas recorded 495 major hail events (≥1 inch) in 2024, the second-highest total of any U.S. state. Nebraska saw 100 confirmed tornadoes, the most in over 20 years. According to 2024 NAIC reporting, Nebraska posted the highest loss ratio of any state at 135.74%, while Kansas ranked 13th at 67.98%, evidence of the severe financial pressures facing insurers in the region.

Why Property-Level Intelligence Matters

ZestyAI’s Severe Convective Storm models analyze the interaction between localized climatology and property-specific characteristics, such as roof condition, design, and complexity, to predict the likelihood and severity of hail, wind, and storm damage claims. In contrast, many models still rely on broad ZIP code or territory-level risk assessments, missing critical property-level signals.

Each model is trained and validated on extensive real-world claims data and provides clear, transparent explanations of the key factors driving each score, enabling more confident underwriting and rating decisions.

Capabilities of the ZestyAI SCS Suite

• Z-HAIL: Predicts hail damage risk and claim severity using property-specific attributes such as roof complexity and accumulated damage to identify which homes are most likely to file a claim, even within the same neighborhood.
• Z-WIND: Analyzes AI-generated 3D roof condition, complexity, and potential failure points alongside local climatology to deliver pivotal insights into property-specific wind claim vulnerability and severity.
• Z-STORM: Assesses the frequency and severity of storm damage claims, including hail and wind, examining the interaction between climatology and the unique characteristics of every structure and roof.

“Securing approval in the storm epicenter of the U.S. reflects both the transparency of our models and our alignment with rigorous regulatory standards,” said Bryan Rehor, Director of Regulatory Affairs at ZestyAI.

“It gives carriers the confidence to use precise, property-level hail and wind insights where they’re needed most, supporting risk-aligned underwriting and pricing in markets facing escalating storm losses.”

ZestyAI’s Severe Convective Storm models are now approved for use in over 20 states across the Great Plains, Midwest, and U.S. South—regions most impacted by hail, wind, and tornado losses.

VYRD, a Florida-based homeowners insurance company focused on delivering stability and protection in a challenging coastal market, has partnered with ZestyAI, the leading provider of AI-powered property risk analytics, to gain deeper visibility into property condition and risk exposure across its book of business.

By leveraging the ZestyAI platform, VYRD gains access to advanced risk insights that help identify vulnerabilities contributing to hurricane-related losses, such as roof degradation, overhanging vegetation, and yard debris. These insights support more accurate underwriting, proactive portfolio management, and better visibility into changing property conditions over time.

VYRD is using two core capabilities of Z-PROPERTY: Digital Roof applies AI to high-resolution aerial imagery to assess roof complexity, materials, and condition, highlighting structural vulnerabilities before they become claims. Location Insights evaluates the broader parcel, surfacing risk factors like vegetation overhang, yard debris, and secondary structures that can amplify storm losses or drive claims severity.

“Staying ahead of risk requires strong partnerships and smarter data,” said David Howard, President and CEO of VYRD.

“ZestyAI’s ability to deliver timely, property-level insights helps us strengthen our understanding of exposure across the homes we protect and continue delivering on our promise of dependable coverage for Florida policyholders.”

Z-PROPERTY helps VYRD assess properties at scale, surface emerging risk patterns, and make more informed decisions across the policy lifecycle. This partnership extends VYRD’s tech-forward, policyholder-first strategy—using trusted data not just at point-of-quote, but throughout ongoing portfolio management.

“Florida is one of the most unforgiving insurance markets in the country,” said Attila Toth, Founder and CEO of ZestyAI. “VYRD is taking a proactive, data-driven approach—using AI to uncover hidden property-level vulnerabilities, strengthen portfolio decisions, and build resilience where it matters most.”