Skip to main content
Back to challenges
Challenge

Develop a Port Logistics Berth Scheduling Agent with OpenAI Agents SDK

Port authorities face berth congestion due to unpredictable vessel arrivals and supply chain delays. Implement an OpenAI Agents SDK autonomous workflow that evaluates vessel AIS telemetry, optimizes berth assignments, and outputs real-time schedule adjustments while reducing simulated vessel waiting times by 20%.

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 an autonomous port berth management agent using OpenAI Agents SDK to optimize vessel schedules and reduce port congestion.

Delivery guide

How work is evaluated

Evaluation

Evaluates vessel wait time reduction and collision/overlap avoidance in berth assignments.

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

no_berth_overlap

Ensures two vessels are never assigned to the same berth concurrently.

Binary check

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

Dimension 2

wait_time_reduction

Percentage reduction in cumulative vessel queue waiting hours. • target: 0.2 • 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

  • Master OpenAI Agents SDK agent definitions, function calling, and dynamic handoffs

  • Integrate maritime operations research algorithms into LLM tool configurations

  • Process real-time vessel AIS telemetry stream inputs for schedule re-optimization

  • Evaluate queue turnaround times and berth allocation efficiency

Resources and assets

Reference links and supporting material

Dataset notes

Synthetic vessel AIS telemetry and port berth assignment simulator dataset for Singapore waters.

Challenge setup

Evaluates vessel wait time reduction and collision/overlap avoidance in berth assignments.

Challenge input

JSON vessel arrival queue with ETA and container load

OpenAI Agents SDK

OpenAI official SDK for multi-agent handoffs and autonomous tool usage.

Evaluated output

JSON schedule matrix mapping vessel IDs to berths and timeslots

Evaluation checks
  • Ensures two vessels are never assigned to the same berth concurrently.
  • Percentage reduction in cumulative vessel queue waiting hours. • target: 0.2 • range: 0-1
Configured evaluation evidence
  • Benchmark: PortLogisticsBench
  • Wait Time Reduction target: 0.2
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python 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
  • OpenAI · Required
  • /dev/agents · Optional
Policy Serving
  • Vercel AI Gateway · Optional
Orchestration
  • Vercel AI Gateway · Optional

Evaluation contract

  • no_berth_overlap · Weight 1
  • wait_time_reduction · Weight 1

Metrics

  • wait_time_reduction · Target 0.2

Benchmarks

  • PortLogisticsBench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON vessel arrival queue with ETA and container load

    Output: JSON schedule matrix mapping vessel IDs to berths and timeslots

    Execution harness: Python

Evaluation tools

  • OpenAI Agents SDK · Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Develop a Port Logistics Berth Scheduling Agent with OpenAI Agents SDK