Skip to main content
Back to challenges
Challenge

Build a Transshipment Manifest Tariff Traceability Engine with Mastra AI

Construct an automated customs audit agent for Singapore transshipment logistics. Using Mastra AI state machine workflows, your system will inspect bill-of-lading documents, trace origin supply chain steps, and verify compliance against international tariff evasion rules.

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.

Build a Mastra AI step-based workflow to trace shipping cargo origins and audit transshipment documents against international tariff rules.

Delivery guide

How work is evaluated

Evaluation

Evaluate accuracy in detecting origin misrepresentation in container manifest records.

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

circumvention_flag_check

Correctly flags circumvention when substantial transformation is missing

Binary check

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

Dimension 2

tariff_risk_mae

Mean absolute error of calculated tariff risk score • target: 0.04 • 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

  • Design state-based Mastra AI workflows for multi-step cargo manifest verification

  • Build origin-tracing algorithms for transshipment container movements

  • Formulate risk scoring logic for potential tariff circumvention or transshipment fraud

  • Export Singapore Customs compliant verification reports

Resources and assets

Reference links and supporting material

Dataset notes

Container movement logs, bills of lading, and port customs clearance forms for Singapore transshipments.

Challenge setup

Evaluate accuracy in detecting origin misrepresentation in container manifest records.

Challenge input

JSON with container_id, declared_origin, transit_ports (array), raw_materials_origin

Mastra AI

TypeScript framework for state-machine guided agent workflows.

Evaluated output

JSON with verified_origin, tariff_risk_score (0.0-1.0), flag_circumvention (bool)

Evaluation checks
  • Correctly flags circumvention when substantial transformation is missing
  • Mean absolute error of calculated tariff risk score • target: 0.04 • range: 0-1
Configured evaluation evidence
  • Benchmark: Maritime_Logistics_Audit_Bench
  • Tariff Risk Mae target: 0.04
  • 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
  • Mastra AI · Required
  • AI Legion · Optional
  • Giskard · Optional
Orchestration
  • Mastra AI · Required

Evaluation contract

  • circumvention_flag_check · Weight 1
  • tariff_risk_mae · Weight 1

Metrics

  • tariff_risk_mae · Target 0.04

Benchmarks

  • Maritime_Logistics_Audit_Bench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON with container_id, declared_origin, transit_ports (array), raw_materials_origin

    Output: JSON with verified_origin, tariff_risk_score (0.0-1.0), flag_circumvention (bool)

    Execution harness: JavaScript

Evaluation tools

  • Mastra AI · Workflow Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Build a Transshipment Manifest Tariff Traceability Engine with Mastra AI