Skip to main content
Loading navigation
Back to challenges

Automated Sustainable Rubber Commodity Traceability & EUDR Compliance Agent

European Union Deforestation Regulation (EUDR) mandates strict geolocation tracking and deforestation-free proof for rubber imported from Malaysia and Southeast Asia. Commodity traders must trace every batch of raw latex back to precise smallholder plot GPS coordinates. In this challenge, you will orchestrate a multi-agent EUDR compliance verification crew using CrewAI. The crew consists of a Geolocation Inspector Agent, a Satellite Plot Auditor Agent, and a Due Diligence Statement (DDS) Generator Agent.

Workflow AutomationHosted by Vera
Sign in free to start

What you are building

Orchestrate a multi-agent rubber traceability and EUDR compliance verification workflow using CrewAI.

How work is evaluated

Evaluation

Evaluates GeoJSON plot verification accuracy and compliant DDS output generation.

Datasets

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

How submissions are scored

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

dds_compliance_check

Must output COMPLIANT for non-deforested plot coordinates.

Binary check

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

Dimension 2

audit_execution_speed_s

Seconds taken to audit plot polygon and construct DDS • target: 4.2 • range: 0.5-30

Binary check

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

Learning goals

  • Construct a CrewAI multi-agent team for supply chain due diligence verification

  • Verify polygon plot GPS coordinates against historical deforestation satellite boundaries

  • Generate compliant EU Due Diligence Statements (DDS) in structured format

  • Implement inter-agent verification loops for land title authenticity check

Resources

Dataset notes

Malaysian smallholder rubber plot GeoJSON polygons, land title registries, and synthetic satellite forest cover logs.

Challenge setup

Evaluates GeoJSON plot verification accuracy and compliant DDS output generation.

Challenge input

JSON containing rubber batch ID, supplier details, and GeoJSON polygon coordinates

CrewAI

Required framework for multi-agent due diligence workflow orchestration.

Evaluated output

JSON containing compliance_status, deforestation_risk_level, and DDS reference code

Evaluation checks
  • Must output COMPLIANT for non-deforested plot coordinates.
  • Seconds taken to audit plot polygon and construct DDS • target: 4.2 • range: 0.5-30
Configured evaluation evidence
  • Benchmark: GeoCompliance-Bench
  • Audit Execution Speed S target: 4.2
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python sandbox (unavailable on Versalist)

Shows the first task, up to three tools, and up to three evidence items.

View technical recipe

Configured tools

Action Space
  • Metaflow · Optional
  • CrewAI · Required
  • crewAI · Optional

Evaluation contract

  • dds_compliance_check · Weight 1
  • audit_execution_speed_s · Weight 1

Metrics

  • audit_execution_speed_s · Target 4.2

Benchmarks

  • GeoCompliance-Bench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing rubber batch ID, supplier details, and GeoJSON polygon coordinates

    Output: JSON containing compliance_status, deforestation_risk_level, and DDS reference code

    Execution harness: Python

Evaluation tools

  • CrewAI · Multi-Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Automated Sustainable Rubber Commodity Traceability & EUDR Compliance Agent