Port Container Terminal Queue & Berth Planner with CrewAI
Container terminals like the HMM Seattle-Tacoma terminal and Southeast Asian hubs are expanding capacity by up to 50 percent, driving unprecedented container throughput. Efficient yard management requires coordinating multiple specialized roles: Berth Allocator, Quay Crane Scheduler, and Yard Truck Controller. In this challenge, you will orchestrate a multi-agent port yard management team using CrewAI. The specialized agent crew works collaboratively to resolve berth allocation conflicts, optimize container stack positioning, and reduce vessel turnaround times.
What you are building
The core problem, expected build, and operating context for this challenge.
Orchestrate a multi-agent port container operations team using CrewAI to optimize berth allocation and vessel turnaround time.
How work is evaluated
Evaluates vessel turnaround optimization and berth schedule validity.
Challenge datasets
Public datasets, plus the private datasets you have access to.
How submissions are scored
These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.
berth_conflict_check
No two vessels may occupy the same berth simultaneously.
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
turnaround_time_reduction
Percentage reduction in average vessel queue waiting hours • target: 20 • range: 0-100
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
What you should walk away with
Build a multi-agent crew with distinct Agent roles, goals, and tools using CrewAI
Define sequential and hierarchical CrewAI Tasks for port operation planning
Resolve container vessel berth collisions dynamically through agent delegation
Generate optimal gantry crane allocation schedules for ultra-large container ships
Reference links and supporting material
Terminal operational log dataset containing vessel arrival logs, TEU crane rates, berth specs, and yard stack layouts.
Challenge setup
Evaluates vessel turnaround optimization and berth schedule validity.
Challenge input
JSON with vessel arrival list, TEU count, draft requirements, and berth availability
CrewAI
Required framework for multi-agent role-playing and sequential task delegation.
Evaluated output
JSON with schedule matrix, total port waiting time, and crane assignments
- No two vessels may occupy the same berth simultaneously.
- Percentage reduction in average vessel queue waiting hours • target: 20 • range: 0-100
- Benchmark: LogiBench-PortOps
- Turnaround Time Reduction target: 20
- 1 public reference case
- 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
- CrewAI · Required
- crewAI · Optional
- Zed · Optional
Evaluation contract
- berth_conflict_check · Weight 1
- turnaround_time_reduction · Weight 1
Metrics
- turnaround_time_reduction · Target 20
Benchmarks
- LogiBench-PortOps
- general
Reference cases
- 1 public reference case
Workflow tasks
- Task 1
Input: JSON with vessel arrival list, TEU count, draft requirements, and berth availability
Output: JSON with schedule matrix, total port waiting time, and crane assignments
Execution harness: Python
Evaluation tools
- CrewAI · Multi-Agent Framework
Recipe freeze marker
No recipe freeze time is recorded.