Skip to main content
Back to challenges
Challenge

Al-Maktoum Airport Automated People-Mover Traffic Assistant with OpenAI Agents SDK

Dubai's mega Al-Maktoum Airport expansion demands autonomous People-Mover (APM) fleet routing to prevent terminal passenger congestion. Build an autonomous agent using OpenAI Agents SDK with function calling to monitor terminal foot-traffic streams and dynamically dispatch APM shuttles. Maintain average terminal passenger wait times under 3 minutes.

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.

Develop an automated airport passenger transit routing agent using OpenAI Agents SDK.

Delivery guide

How work is evaluated

Evaluation

Evaluates APM shuttle dispatch decisions against terminal passenger surge inputs.

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

Wait Time Threshold Check

Ensures expected wait time is strictly under 3.0 minutes.

Binary check

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

Dimension 2

Passenger Handling Efficiency

Score measuring optimal shuttle usage relative to passenger queue size. • target: 0.95 • 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

  • Build an agent using OpenAI Agents SDK and Python function tools

  • Parse real-time terminal camera passenger density numbers

  • Execute dynamic APM fleet dispatch commands automatically

  • Balance energy consumption with passenger wait time metrics

Resources and assets

Reference links and supporting material

Dataset notes

Passenger traffic arrival profiles and APM vehicle telemetry at Al-Maktoum International Airport.

Challenge setup

Evaluates APM shuttle dispatch decisions against terminal passenger surge inputs.

Challenge input

JSON object with terminal_id, waiting_passengers, available_shuttles, shuttle_capacity

OpenAI Agents SDK

Assigned framework requirement.

Evaluated output

JSON object with dispatched_shuttles, expected_wait_time_minutes, energy_mode

Evaluation checks
  • Ensures expected wait time is strictly under 3.0 minutes.
  • Score measuring optimal shuttle usage relative to passenger queue size. • target: 0.95 • range: 0-1
Configured evaluation evidence
  • Benchmark: TransitAgentBench
  • Passenger Handling Efficiency target: 0.95
  • 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
  • AutoGluon · Optional
  • LiveKit · Optional

Evaluation contract

  • Wait Time Threshold Check · Weight 1
  • Passenger Handling Efficiency · Weight 1

Metrics

  • Passenger Handling Efficiency · Target 0.95

Benchmarks

  • TransitAgentBench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON object with terminal_id, waiting_passengers, available_shuttles, shuttle_capacity

    Output: JSON object with dispatched_shuttles, expected_wait_time_minutes, energy_mode

    Execution harness: Python

Evaluation tools

  • OpenAI Agents SDK · Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Al-Maktoum Airport Automated People-Mover Traffic Assistant with OpenAI Agents SDK