Johor-Batam Truck Ferry Logistics Scheduling Agent with Pydantic AI
The proposed Johor-Batam Ro-Ro truck ferry service aims to streamline cross-border freight between Malaysia, Singapore, and Indonesia. However, delays in infrastructure readiness require dynamic contingency scheduling for cross-straits logistics providers operating multi-modal routes. In this challenge, you will build a type-safe freight scheduling agent using Pydantic AI. The agent validates truck manifest inputs, evaluates queue delays at sea ports (Johor, Batam, Singapore), dynamically re-routes cross-border freight via alternative sea or land routes, and guarantees strict output schema validation.
What you are building
The core problem, expected build, and operating context for this challenge.
Develop a type-safe cross-border truck ferry logistics optimization agent using Pydantic AI.
How work is evaluated
Evaluates dynamic re-routing accuracy and Pydantic schema validation adherence.
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.
pydantic_schema_validation
Output must pass strict Pydantic model validation without exceptions.
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
transit_time_efficiency
Optimized route transit time relative to direct baseline • target: 15 • 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
Implement type-safe agent workflows with Pydantic AI models and dependency injection
Model multi-modal transit delays across Johor, Batam, and Singapore ports
Dynamically select optimal transport routes (Direct Ferry vs Feeder Barge vs Causeway Trucking)
Generate structured, schema-validated route itineraries with cost and time estimates
Reference links and supporting material
Cross-straits truck transit log dataset containing ferry schedules, causeway delay metrics, and port barge schedules.
Challenge setup
Evaluates dynamic re-routing accuracy and Pydantic schema validation adherence.
Challenge input
JSON with origin, destination, cargo urgency, and port disruption flags
Pydantic AI
Required Python framework for type-safe structured output parsing.
Evaluated output
JSON matching Pydantic schema for selected itinerary, transit time, and estimated cost
- Output must pass strict Pydantic model validation without exceptions.
- Optimized route transit time relative to direct baseline • target: 15 • range: 0-100
- Benchmark: LogiBench-Routing
- Transit Time Efficiency target: 15
- 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
- Pydantic AI · Required
- RAI · Optional
- Aim · Optional
- Pydantic AI · Required
Evaluation contract
- pydantic_schema_validation · Weight 1
- transit_time_efficiency · Weight 1
Metrics
- transit_time_efficiency · Target 15
Benchmarks
- LogiBench-Routing
- general
Reference cases
- 1 public reference case
Workflow tasks
- Task 1
Input: JSON with origin, destination, cargo urgency, and port disruption flags
Output: JSON matching Pydantic schema for selected itinerary, transit time, and estimated cost
Execution harness: Python
Evaluation tools
- Pydantic AI · Agent Framework
Recipe freeze marker
No recipe freeze time is recorded.