Ledger Library

Demo of Workbench: AI Work Environment for Reinsurance 🛠️

At the Casualty Actuarial Society Reinsurance Seminar on June 5, 2025, Ledger presented a live demo of Workbench, an AI-powered tool for reinsurance that is currently in development. This video demonstrates how an actuary and an underwriter can collaborate to use Workbench and 5 AI agents to review a reinsurance submission, analyze the accompanying data, stochastically model the portfolio and forecast losses, and evaluate alternative financial terms.

The demo features the following AI agents: Patterson to analyze and compare reinsurance submissions, Bermuda to manage loss data and manipulate triangles, Carnac to forecast losses and cash flows, Quill to analyze reinsurance contract key terms, and Tully to model the financial terms.

Workbench emulates AI IDEs used by developers to create a similar interface for reinsurance professionals. It has a multi-player interface to allow collaboration. Although this demo showcases reinsurance actuarial and underwriting process, other AI agents can be added to provide tools for other reinsurance roles: finance, accounting, claims, etc.

Casualty ILS: The New Corporate Finance

At the 2025 @CasualtyActuarialSociety Reinsurance Seminar, Samir Shah spoke about the rise of casualty insurance-linked securities (ILS) — and how it can serve as the new tool of corporate finance.

Casualty ILS Part 1: What is Casualty Insurance?

Casualty insurance is a financial safeguard provided by insurance companies to individuals and businesses. It covers them against losses stemming from third-party claims due to accidents.

Casualty ILS Part 2: Cash Flows of Casualty Insurance

Ledger gives investors exposure to the full cash flow engine of casualty insurance—upfront premiums, long-tail claim payouts, investment income, and low-volatility risks—by structuring ILS offerings that prioritize steady cash flows.

Casualty ILS Part 3: Capital Investment in Casualty Insurance

Learn how Ledger unlocks steady, upfront cash flows and strong returns by letting investors participate directly in insurance through a capital-efficient trust model.

Loss Ratio Dynamics

We rely on time series models for estimating the loss ratios insurers will achieve in future years. Our choice of models is not arbitrary or purely driven by backtesting performance.

Casualty Insurance Lines of Business

Property & casualty insurance includes a wide number of distinct insurance products with widely varying characteristics. We describe what, fundamentally, property & casualty insurance includes and its implications for business.

Property & Casualty Insurance Companies

We look at basic features of insurance companies by exploring statutory filings data. We see how many property & casualty insurance companies there are, and how insurance groups are structured.

Line of Business Volume and Diversification

The US property & casualty industry is subdivided into 22 separate lines of business in Schedule P of the annual statements mandated by the NAIC. We explore the relative size of each line of business and the implications for risk diversification.

Line of Business Development Patterns

When an insurance company issues a policy, the company knows the amount of premium it will receive, but it may not know for many years exactly how much it will cost to settle all obligations connected to that policy.

Line of Business Loss Ratio Behavior

The core measure of an insurance company's performance is its loss ratio. We describe what loss ratios are, and how they tend to behave. We explore how loss ratios vary by line of business and underwriting practices.

Prior Distributions for Link Ratios

Many traditional loss development models center around the notion of link ratios. We describe the importance of prior distributions in the context of Bayesian modeling, and some of the implications for reinsurance and risk assessment.

Loss Ratio Volatility and Insurer Skill

Many investors are interested in understanding just how volatile insurer loss ratios are, and how much of that volatility is intrinsic to the insurance environment. We present a thorough analysis of historical data and modeling approaches.

Property and Casualty Insurance Industry Analysis

This anthology is a collection of articles we've written on the property and casualty insurance industry. It covers basics of the property and casualty insurance space, analyses of market trends, and theoretical frameworks for understanding insurance risks.

A Bayesian workflow for securitizing casualty insurance risk

In this paper, we lay out our Bayesian workflow for securitizing casualty insurance-linked securities that uses theoretically informed time-series and state-space models to capture relevant dynamics.

Joint estimation of insurance loss development factors using Bayesian hidden Markov models

Loss development modeling is typically conducted in two steps: one model to estimate the link ratios from the main portion of the training data and another for predictions. We explore advancements in this dual modeling approach.