Skip to main content
Back to challenges
Challenge

CrewAI Catastrophe Monitor: Parametric Industry Loss Warranties

Settling Industry Loss Warranties requires real-time aggregation of PCS catastrophic index updates and automated consensus verification. Build a CrewAI multi-agent team to monitor catastrophe loss indexes, evaluate policy thresholds, and issue verified payout triggers with zero false positives.

Machine LearningHosted by Vera
Sign in free to start
Challenge brief

What you are building

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

Orchestrate a CrewAI team consisting of Index Monitor, Verification Analyst, and Settlement Officer agents to process parametric Industry Loss Warranty (ILW) contracts.

Delivery guide

How work is evaluated

Evaluation

Evaluates CrewAI team execution and accurate verification of ILW industry loss triggers.

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

zero_false_positives

Ensures payouts are never triggered below threshold.

Binary check

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

Dimension 2

settlement_accuracy

Accuracy of payout decision and amount across test suite. • target: 1 • range: 0-1

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

  • Build a CrewAI team with defined roles, goals, and backstory context.

  • Integrate simulated PCS industry loss data lookup tools.

  • Evaluate industry loss trigger limits ($20B, $50B PCS thresholds).

  • Generate automated settlement notices with 100% precision.

Resources and assets

Reference links and supporting material

Dataset notes

Dataset of 30 catastrophe events with reported PCS loss estimates and 60 ILW contract conditions.

Challenge setup

Evaluates CrewAI team execution and accurate verification of ILW industry loss triggers.

Challenge input

JSON containing event_name, pcs_reported_loss_usd, contract_trigger_threshold_usd

CrewAI

Framework for orchestrating task-focused agent crews.

Evaluated output

JSON containing payout_triggered (boolean), verification_status, settlement_amount_usd

Evaluation checks
  • Ensures payouts are never triggered below threshold.
  • Accuracy of payout decision and amount across test suite. • target: 1 • range: 0-1
Configured evaluation evidence
  • Benchmark: Role-Playing Agent Orchestration Benchmark
  • Settlement Accuracy target: 1
  • 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
  • Alibaba · Optional

Evaluation contract

  • zero_false_positives · Weight 1
  • settlement_accuracy · Weight 1

Metrics

  • settlement_accuracy · Target 1

Benchmarks

  • Role-Playing Agent Orchestration Benchmark
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing event_name, pcs_reported_loss_usd, contract_trigger_threshold_usd

    Output: JSON containing payout_triggered (boolean), verification_status, settlement_amount_usd

    Execution harness: Python

Evaluation tools

  • CrewAI · Role-Playing Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about CrewAI Catastrophe Monitor: Parametric Industry Loss Warranties