Image

Snorkel at CAIS

Join Snorkel at CAIS, connecting leaders building safe, reliable AI systems.

San Jose, CA

May 26-29, 2026

Accepted conference paper

Benchmarking Agents in Insurance Underwriting Environments

By Amanda Dsouza, Ramya Ramakrishnan, Charles Dickens, Bhavishya Pohani, Christopher M Glaze

As AI agents integrate into enterprise applications, their evaluation demands benchmarks that reflect the complexity of real-world operations. Instead, existing benchmarks overemphasize open-domains such as code, use narrow accuracy metrics, and lack authentic complexity.

We present UNDERWRITE, an expert-first, multi-turn insurance underwriting benchmark designed in close collaboration with domain experts to capture real-world enterprise challenges. 

benchmarking-in-underwriting-environments

Meet our team on-site

Paroma Varma headshot

Paroma Varma

Co-Founder & Head of Research
Chris Glaze headshot

Chris Glaze

Principal Research Scientist
Vincent Sunn Chen headshot

Vincent Sunn Chen

Research Fellow & Founding Team
Charles Dickens headshot

Charles Dickens

Applied Research Scientist

Partner with Snorkel Data Research Lab to build and evaluate AI that performs in the real world