Skip to main content
Loading navigation
Back to challenges

Port Logistics Exception & Maritime Demurrage Arbitrage Crew with CrewAI

Port congestion at southern crude export terminals can cause unexpected demurrage costs. Build a multi-role exception handling crew using CrewAI to identify logistics bottlenecks, re-route vessels to vacant offshore SPM (Single Point Mooring) buoys, and perform demurrage cost arbitrage.

Business OperationsHosted by Vera
Sign in free to start

What you are building

Develop an automated maritime exception and port congestion handling crew using CrewAI.

How work is evaluated

Evaluation

Evaluates demurrage cost reduction from automated vessel redirection.

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

redirect_recommended

Verify redirection recommended when net savings are positive.

Binary check

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

Dimension 2

arbitrage_math_accuracy

Accuracy of computed net savings. • target: 0.98 • 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

  • Build CrewAI agents specialized in port operations and demurrage arbitrage.

  • Implement dynamic tool use for SPM buoy berth re-assignment.

  • Calculate cost-benefit metrics for vessel rerouting.

Resources

Dataset notes

25 port queue scenarios with vessel demurrage rates and SPM buoy availability.

Challenge setup

Evaluates demurrage cost reduction from automated vessel redirection.

Challenge input

JSON with berth_wait_hours, spm_available, demurrage_rate_hr, redirect_cost_usd

CrewAI

Framework for defining role-playing agent workflows.

Evaluated output

JSON with action_recommended, net_savings_usd

Evaluation checks
  • Verify redirection recommended when net savings are positive.
  • Accuracy of computed net savings. • target: 0.98 • range: 0-1
Configured evaluation evidence
  • Benchmark: CrewAI-Logistics-Bench
  • Arbitrage Math Accuracy target: 0.98
  • 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
  • CrewAI · Required
  • crewAI · Optional
  • Synthflow · Optional

Evaluation contract

  • redirect_recommended · Weight 1
  • arbitrage_math_accuracy · Weight 1

Metrics

  • arbitrage_math_accuracy · Target 0.98

Benchmarks

  • CrewAI-Logistics-Bench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON with berth_wait_hours, spm_available, demurrage_rate_hr, redirect_cost_usd

    Output: JSON with action_recommended, net_savings_usd

    Execution harness: Python

Evaluation tools

  • CrewAI · Agent Orchestration

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Port Logistics Exception & Maritime Demurrage Arbitrage Crew with CrewAI