Zesty.ai Inc.

Z-FIRE, Z-FLOOD

Zesty.ai applies AI and computer vision to high-resolution aerial and satellite imagery to assess property-level climate and catastrophe risk, with flagship models Z-FIRE (wildfire) and Z-FLOOD built for P&C insurers, reinsurers and regulators. It derives building- and parcel-specific features — roof condition, vegetation, defensible space — and combines them with hazard data to produce scores approved in multiple US state insurance filings for rating and underwriting, delivered via API and a decision platform. Distinctive for that regulatory acceptance and for individual-property feature extraction in the US underwriting market.

Vendor methodology

Transparency Score

Beta

Public transparency, not model quality iThe Transparency Score (0–3) estimates public methodological transparency: the degree to which the vendor's analytical approach to modeling climate and nature risk can be assessed from publicly available sources. It is explicitly not a measure of vendor quality or accuracy.

2

Methodology-relevant: vendor websites or external resources explain methodological details.

Methodology-relevant: a public model deep-dive documents the two-level structure (exposure: vegetation, slope, WUI, burn patterns, climatology; vulnerability: building materials and defensible space via computer vision), validated on millions of claims; DOI-approved models carry third-party-reviewed technical documentation with variable lists. Full technical doc partly regulatory-gated.

For further information, see the section 'Transparency Score methodology' in the Readme.

Contact us to point out or add relevant source or references.

Links

i

Level 1 signals