Skip to main content
Back to challenges
Challenge

Geospatial Crude Maritime Routing & Strait Guard Agent with LlamaIndex

Oil exports leaving Arab Gulf ports through the Strait of Hormuz face localized maritime security risk and narrow shipping channels. Developers must build a geospatial reasoning agent using LlamaIndex and custom spatial vector indices. The agent ingests vessel AIS location telemetry, maritime security notices, and port congestion alerts to compute optimal, low-risk transit corridors for crude tankers bound for foreign markets.

Business OperationsHosted 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 a geospatial maritime routing and risk agent using LlamaIndex spatial query capabilities.

Delivery guide

How work is evaluated

Evaluation

Evaluates dynamic maritime detour generation for crude tankers.

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

reroute_triggered

Ensure reroute is correctly mandated when vessel is inside hazard polygon.

Binary check

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

Dimension 2

spatial_safety_margin

Distance in nautical miles between waypoint and hazard boundary. • target: 10 • range: 0-50

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

  • Implement geospatial metadata indexing with LlamaIndex.

  • Evaluate maritime hazard zones against live tanker trajectories.

  • Generate dynamic rerouting suggestions to mitigate transit risk.

Resources and assets

Reference links and supporting material

Dataset notes

AIS coordinates and Arabian Gulf maritime security alert zone polygons.

Challenge setup

Evaluates dynamic maritime detour generation for crude tankers.

Challenge input

JSON with vessel_coord, hazard_zone_polygon

LlamaIndex

Provides spatial metadata filtering and query capabilities.

Evaluated output

JSON with reroute_required, suggested_waypoint

Evaluation checks
  • Ensure reroute is correctly mandated when vessel is inside hazard polygon.
  • Distance in nautical miles between waypoint and hazard boundary. • target: 10 • range: 0-50
Configured evaluation evidence
  • Benchmark: Geospatial-Logistics-Bench
  • Spatial Safety Margin target: 10
  • 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
  • Llama Index · Required
  • RAI · Optional
  • Zed · Optional

Evaluation contract

  • reroute_triggered · Weight 1
  • spatial_safety_margin · Weight 1

Metrics

  • spatial_safety_margin · Target 10

Benchmarks

  • Geospatial-Logistics-Bench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON with vessel_coord, hazard_zone_polygon

    Output: JSON with reroute_required, suggested_waypoint

    Execution harness: Python

Evaluation tools

  • LlamaIndex · Indexing Engine

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Geospatial Crude Maritime Routing & Strait Guard Agent with LlamaIndex