Skip to main content
Back to challenges
Challenge

Airport People-Mover Anomaly Monitoring with Mastra AI

Contractors confirmed the Al-Maktoum airport automated people-mover (APM) award. Build a TypeScript telemetry agent using Mastra AI to ingest real-time sensor streams (vibration, door cycle count, motor temp), detect anomalies, and auto-dispatch maintenance tickets. Maintain an anomaly detection accuracy above 95% with zero false negative critical warnings.

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 Mastra AI TypeScript workflow with built-in memory and tools to monitor telemetry and manage predictive maintenance for airport transit systems.

Delivery guide

How work is evaluated

Evaluation

Evaluates APM telemetry anomaly detection and ticket generation accuracy.

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

critical_detection

Ensures temps over 90C trigger immediate high priority ticket

Binary check

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

Dimension 2

detection_precision

Precision of detected anomaly categories against benchmark • 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

  • Initialize Mastra AI agent with memory storage and dynamic tool definitions in TypeScript.

  • Stream APM train telemetry data through Mastra workflows.

  • Define heuristic and LLM-assisted anomaly evaluation tools.

  • Automate maintenance work-order creation in response to persistent telemetry alerts.

Resources and assets

Reference links and supporting material

Dataset notes

Telemetry logs simulated for airport automated people-mover system bogies and door actuators.

Challenge setup

Evaluates APM telemetry anomaly detection and ticket generation accuracy.

Challenge input

JSON telemetry object with car_id, motor_temp_c, vibration_hz, and door_cycles

Mastra AI

Offers robust TypeScript agentic and memory tooling.

Evaluated output

JSON containing status flag, detected anomalies, and generated ticket

Evaluation checks
  • Ensures temps over 90C trigger immediate high priority ticket
  • Precision of detected anomaly categories against benchmark • target: 0.95 • range: 0-1
Configured evaluation evidence
  • Benchmark: IoTTicketBench
  • Detection Precision target: 0.95
  • 1 public reference case
Configured runtime
  • JavaScript execution harness
  • javascript 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
  • Mastra AI · Required
  • Metaflow · Optional
  • Hamming · Optional
Orchestration
  • Mastra AI · Required

Evaluation contract

  • critical_detection · Weight 1
  • detection_precision · Weight 1

Metrics

  • detection_precision · Target 0.95

Benchmarks

  • IoTTicketBench
  • robotics

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON telemetry object with car_id, motor_temp_c, vibration_hz, and door_cycles

    Output: JSON containing status flag, detected anomalies, and generated ticket

    Execution harness: JavaScript

Evaluation tools

  • Mastra AI · Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Airport People-Mover Anomaly Monitoring with Mastra AI