Skip to main content
Loading navigation
Back to challenges

Hazmat Supply Chain Compliance Agent for Nizwa Industrial City

Nizwa Industrial City signed a $10.4m chemical and oilfield project in Oman. Build an automated chemical tracking and safety compliance agent in Python that validates chemical transport documentation against international Hazmat transport codes. Maintain 100% detection of unflagged hazardous chemical combinations.

Business OperationsHosted by Vera
Sign in free to start

What you are building

Construct an automated chemical safety compliance agent in Python to inspect chemical supply chain manifests and storage compatibility for oilfield products.

How work is evaluated

Evaluation

Evaluates hazmat compliance checking and chemical incompatibility detection.

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

incompatibility_flag

Ensures oxidizers and flammable liquids are strictly flagged

Binary check

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

Dimension 2

violation_detection_recall

Recall metric on detecting prohibited chemical co-loadings • 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

  • Parse Chemical Abstracts Service (CAS) numbers and UN Hazmat numbers from shipping manifests.

  • Cross-check chemical compatibility matrix to detect hazardous reactions during transit/storage.

  • Validate safety data sheets (SDS) against Omani environmental safety standards.

  • Issue automated handling guidelines and emergency spill protocols.

Resources

Dataset notes

UN Hazmat database records and oilfield chemical shipment manifests.

Challenge setup

Evaluates hazmat compliance checking and chemical incompatibility detection.

Challenge input

JSON array of chemicals with UN_number, class, and quantity_kg

Python Safety Rules Engine

Evaluates chemical combination matrices.

Evaluated output

JSON with safe_to_ship_together, rule_violations, and risk_category

Evaluation checks
  • Ensures oxidizers and flammable liquids are strictly flagged
  • Recall metric on detecting prohibited chemical co-loadings • target: 1 • range: 0-1
Configured evaluation evidence
  • Benchmark: HazmatComplianceBench
  • Violation Detection Recall target: 1
  • 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
  • NNI (Neural Network Intelligence) · Required
  • Evidently AI · Optional
  • Cartesia · Optional

Evaluation contract

  • incompatibility_flag · Weight 1
  • violation_detection_recall · Weight 1

Metrics

  • violation_detection_recall · Target 1

Benchmarks

  • HazmatComplianceBench
  • security

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON array of chemicals with UN_number, class, and quantity_kg

    Output: JSON with safe_to_ship_together, rule_violations, and risk_category

    Execution harness: Python

Evaluation tools

  • Python Safety Rules Engine · Rule Enforcement

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Hazmat Supply Chain Compliance Agent for Nizwa Industrial City