Simulytic provides insurers with evidence‑based risk scores for autonomous vehicle deployments by generating synthetic driving histories that reflect an AV’s behavior in specific locales and use cases. The platform delivers hyperlocal, continuously updated assessments of first‑ and third‑party injury and property damage liability, enabling underwriters to price policies accurately and transparently without accessing proprietary vehicle technology.
Funding
Funding not disclosed
Founders
Product
Problem
Insurers face difficulty pricing autonomous vehicle (AV) policies because traditional risk models lack data on AV performance, especially in specific locales and use cases. This results in uncertain premiums and limited ability to underwrite emerging AV deployments such as robotaxis and passenger shuttles.
Solution
Simulytic delivers evidence‑based risk scores that quantify the liability exposure of AV deployments. By generating synthetic driving histories that reflect how a particular AV operates in its local environment, the platform produces hyperlocal risk insights for both first‑ and third‑party bodily injury and property damage. The scores support pre‑bind assessments and can be updated continuously as software versions or deployment conditions change, allowing insurers to adjust premiums and policy terms without accessing proprietary AV technology. The methodology is patented and tailored to the underwriting workflow, enabling insurers to price AV policies with greater accuracy and transparency.
Target Audience
Primary customers are insurance carriers and underwriting teams that provide liability coverage for autonomous vehicle fleets, including robotaxi operators and autonomous shuttle services.
Features
- Synthetic driving history generation that models AV behavior in specific geographic and operational contexts
- Comprehensive risk scoring covering first‑party injury, third‑party injury, and property damage liabilities
- Continuous risk re‑assessment tied to software updates and changing deployment conditions
- Hyperlocal analysis that differentiates between use cases such as robotaxis, shuttles, and other autonomous services
- Transparent, evidence‑based scoring framework compatible with existing underwriting processes