Skip to main content
Back to challenges
Challenge

Build Parametric Climate Insurance Workflows with Mastra AI and Smolagents

Build an automated underwriting and claims processing engine for ASEAN parametric flood insurance. Using Mastra AI state machines alongside Smolagents tool execution, your system will ingest satellite precipitation feeds, assess payout thresholds, and log audited decisions with speed.

Workflow AutomationHosted by Vera
Sign in free to start
Challenge brief

What you are building

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

Construct a Mastra AI workflow with Smolagents to automate climate risk assessment and parametric insurance claims for ASEAN risks.

Delivery guide

How work is evaluated

Evaluation

Evaluate parametric claims payout decisions against ground truth climate index 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

correct_payout_action

Claim output matches exact expectation based on trigger rule

Binary check

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

Dimension 2

execution_latency_ms

Latency of total workflow execution • target: 1200 • range: 0-5000

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

  • Construct step-based workflows in Mastra AI for insurance risk evaluation

  • Implement Smolagents for targeted weather API parameter extraction

  • Design parametric trigger logic based on historical regional rainfall data

  • Log immutable audit logs for automated payout execution

Resources and assets

Reference links and supporting material

Dataset notes

Simulated ASEAN rainfall telemetry records paired with parametric policy claim metadata.

Challenge setup

Evaluate parametric claims payout decisions against ground truth climate index triggers.

Challenge input

JSON with rainfall_mm, threshold_mm, and policy_id

Mastra AI

TypeScript framework for complex agent state management.

Smolagents

Lightweight code agent tool runner.

Evaluated output

JSON with payout_triggered (boolean), amount, and rationale

Evaluation checks
  • Claim output matches exact expectation based on trigger rule
  • Latency of total workflow execution • target: 1200 • range: 0-5000
Configured evaluation evidence
  • Benchmark: InsurTech_Parametric_Eval
  • Execution Latency Ms target: 1200
  • 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
  • Smolagents · Required
  • Mastra AI · Optional
  • Aim · Optional
Orchestration
  • Mastra AI · Optional

Evaluation contract

  • correct_payout_action · Weight 1
  • execution_latency_ms · Weight 1

Metrics

  • execution_latency_ms · Target 1200

Benchmarks

  • InsurTech_Parametric_Eval
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON with rainfall_mm, threshold_mm, and policy_id

    Output: JSON with payout_triggered (boolean), amount, and rationale

    Execution harness: JavaScript

Evaluation tools

  • Mastra AI · Workflow Engine
  • Smolagents · Agent Utility

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Build Parametric Climate Insurance Workflows with Mastra AI and Smolagents