Skip to main content
Back to challenges
Challenge

AI SDK Parametric Cyber Catastrophe Bond Trigger Monitor

Capital markets investors in cyber cat bonds require real-time execution of parametric trigger events based on global cloud outages. Build a TypeScript AI SDK service that monitors cloud status APIs and calculates cat bond trigger thresholds.

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.

Implement an AI SDK streaming workflow in TypeScript to track systemic cyber downtime metrics and payout status.

Delivery guide

How work is evaluated

Evaluation

Evaluates downtime verification logic and precision of calculated parametric investor payouts.

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

threshold_trigger_check

Verifies trigger activates exactly when downtime > threshold

Binary check

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

Dimension 2

payout_accuracy

Accuracy of calculated payout relative to prospectus term sheet • 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 TypeScript AI SDK application for monitoring real-time cloud availability feeds

  • Implement parametric trigger valuation models for Cyber Catastrophe Bonds

  • Stream automatic investor payout notifications upon verified downtime breaches

Resources and assets

Reference links and supporting material

Dataset notes

Cloud service outage event logs with region markers and severity metrics.

Challenge setup

Evaluates downtime verification logic and precision of calculated parametric investor payouts.

Challenge input

JSON containing outage_duration_hours, affected_regions, and bond_principal_usd

AI SDK

Vercel's TypeScript framework for real-time AI logic and structured output validation

Evaluated output

JSON with trigger_activated (bool), payout_amount_usd, and payout_percentage

Evaluation checks
  • Verifies trigger activates exactly when downtime > threshold
  • Accuracy of calculated payout relative to prospectus term sheet • target: 1 • range: 0-1
Configured evaluation evidence
  • Benchmark: Parametric-Payout-Bench
  • Payout Accuracy target: 1
  • 1 public reference case
Configured runtime
  • JavaScript execution harness
  • javascript 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
  • LocalAI · Optional
Policy Serving
  • DeepSeek R1 · Required
  • Grok 4 Heavy · Optional

Evaluation contract

  • threshold_trigger_check · Weight 1
  • payout_accuracy · Weight 1

Metrics

  • payout_accuracy · Target 1

Benchmarks

  • Parametric-Payout-Bench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing outage_duration_hours, affected_regions, and bond_principal_usd

    Output: JSON with trigger_activated (bool), payout_amount_usd, and payout_percentage

    Execution harness: JavaScript

Evaluation tools

  • AI SDK · Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about AI SDK Parametric Cyber Catastrophe Bond Trigger Monitor