Back to challenges
Challenge

Build eVTOL Mobility Risk Monitor with Google ADK and Aider

Urban air mobility routes require real-time atmospheric collision and safety constraint monitoring. Build an AI flight monitoring agent using Google ADK with Gemini Multimodal capabilities and refactor code pipelines using Aider to guarantee sub-100ms risk detection on flight telemetry.

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 aerial safety analysis agent with Google Agent Development Kit and automated code refactoring using Aider.

Delivery guide

How work is evaluated

Evaluation

Evaluates dynamic flight risk identification and system optimization metrics.

Datasets

Shared data for this challenge

Review public datasets and any private uploads tied to your build.

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

latency_threshold

Ensures flight risk processing completes in under 100ms

Binary check

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

Dimension 2

risk_detection_recall

Recall metric on hazardous flight corridor events • target: 0.98 • 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

  • Develop multimodal flight corridor risk analyzers using Google Agent Development Kit (ADK)

  • Use Aider AI engineering tooling to automatically refactor vector processing routines for low latency

  • Assess dynamic aerial traffic conflicts and weather constraints using Gemini vision models

Resources and assets

Reference links and supporting material

Dataset notes

Simulated urban eVTOL radar frames and atmospheric weather telemetry vectors.

How this agent runs

Evaluates dynamic flight risk identification and system optimization metrics.

Challenge input

JSON containing drone altitude, speed, wind vector, and camera snapshot URI

Google ADK

Provides Gemini multimodal agent integration

Aider

Automates local code refactoring for performance optimization

Evaluated output

JSON containing risk level, action, and latency ms

Checks for
  • Ensures flight risk processing completes in under 100ms
  • Recall metric on hazardous flight corridor events • target: 0.98 • range: 0-1
Proof of success
  • Benchmark: eVTOL-Safety-Bench
  • Risk Detection Recall target: 0.98
  • 1 public reference case
Runtime evidence
  • Python execution harness
  • Python sandbox (unavailable on Versalist)
View technical recipe

Configured tools

Action Space
  • Aider · Required
  • Google ADK · Optional
  • Google · Optional
Observation
  • Aider · Required

Evaluation contract

  • latency_threshold · Weight 1
  • risk_detection_recall · Weight 1

Recipe state

This is a preview. The configuration can change before the evaluation recipe is locked.

Frequently Asked Questions about Build eVTOL Mobility Risk Monitor with Google ADK and Aider