Skip to main content
Back to challenges
Challenge

Orchestrate Actuarial Risk Modeling and Climate Stress Testing with CrewAI

Actuarial teams need AI automation to simulate extreme climate event risks on insurance portfolios. Orchestrate a CrewAI team of actuarial agents that execute Monte Carlo simulations and produce regulatory climate risk reports matching MAS guidelines.

CybersecurityHosted by Vera
Sign in free to start
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Deploy a specialized team of actuarial agents using CrewAI to conduct climate risk stress testing on property portfolios.

Delivery guide

How work is evaluated

Evaluation

Evaluates loss projection accuracy and reserve allocation calculation under extreme weather shocks.

Datasets

Challenge datasets

Public datasets, plus the private datasets you have access to.

Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

Capital Buffer Calculation Test

Capital buffer must exceed estimated maximum loss by at least 15%.

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Dimension 2

PML Estimate Precision

Precision of loss projections against benchmark catastrophe models. • target: 0.95 • range: 0.88-1

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

What you should walk away with

  • Configure a CrewAI crew containing Climate Modeler, Actuary, and Capital Reserve Analyst.

  • Ingest catastrophe modeling data and property portfolio exposure vectors.

  • Run Monte Carlo loss distribution simulations across 100-year flood/typhoon scenarios.

  • Produce MAS-compliant regulatory climate risk stress test disclosures.

Resources and assets

Reference links and supporting material

Dataset notes

Synthetic Southeast Asian commercial real estate exposure dataset with flood depth grids.

Challenge setup

Evaluates loss projection accuracy and reserve allocation calculation under extreme weather shocks.

Challenge input

JSON containing portfolio_value, coastal_exposure_pct, event_severity_category

CrewAI

Orchestrates role-playing actuarial and risk modeling agents.

Evaluated output

JSON with estimated_probable_maximum_loss, recommended_capital_buffer, solvency_ratio

Evaluation checks
  • Capital buffer must exceed estimated maximum loss by at least 15%.
  • Precision of loss projections against benchmark catastrophe models. • target: 0.95 • range: 0.88-1
Configured evaluation evidence
  • Benchmark: ActuarialClimateBench
  • PML Estimate Precision target: 0.95
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python sandbox (unavailable on Versalist)

Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.

View technical recipe

Configured tools

Action Space
  • CrewAI · Required
  • crewAI · Optional

Evaluation contract

  • Capital Buffer Calculation Test · Weight 1
  • PML Estimate Precision · Weight 1

Metrics

  • PML Estimate Precision · Target 0.95

Benchmarks

  • ActuarialClimateBench
  • security

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing portfolio_value, coastal_exposure_pct, event_severity_category

    Output: JSON with estimated_probable_maximum_loss, recommended_capital_buffer, solvency_ratio

    Execution harness: Python

Evaluation tools

  • CrewAI · Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Orchestrate Actuarial Risk Modeling and Climate Stress Testing with CrewAI