Build an Electric Air Taxi Flight Corridor Safety Agent with CrewAI
Urban air mobility pioneers like The ePlane Company are innovating autonomous aerial transportation in India. In this challenge, you will implement a multi-agent flight corridor risk assessment and airspace monitoring agent using CrewAI. The system coordinates agents (Meteorological Analyst, Airspace Corridor Controller, and Safety Compliance Officer) to analyze low-altitude weather conditions, urban obstacle density, and regulatory clearance parameters before authorizing eVTOL flight paths.
What you are building
The core problem, expected build, and operating context for this challenge.
Orchestrate low-altitude eVTOL flight corridor safety agents using CrewAI role-playing crews.
How work is evaluated
Evaluates flight corridor risk assessment and safety clearance output.
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.
high_wind_rejection_test
Ensures flight clearance is denied when wind speed exceeds safety threshold (25 knots).
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
safety_precision
Correct detection of dangerous flight conditions. • target: 1 • range: 0-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
What you should walk away with
Orchestrate CrewAI agents with defined aerospace safety role constraints.
Analyze micro-weather telemetry and low-altitude wind gust hazards.
Compute corridor clearance safety metrics for urban drone/eVTOL paths.
Produce automated pre-flight safety clearance logs for DGCA regulatory audit.
Reference links and supporting material
Telemetry dataset of low-altitude urban weather conditions and 3D building obstacle models.
Challenge setup
Evaluates flight corridor risk assessment and safety clearance output.
Challenge input
JSON with flight_id, origin, destination, wind_speed_knots, obstacle_clearance_m.
CrewAI
Required framework for multi-agent safety verification.
Evaluated output
JSON with clearance_approved, risk_level, hazard_warnings.
- Ensures flight clearance is denied when wind speed exceeds safety threshold (25 knots).
- Correct detection of dangerous flight conditions. • target: 1 • range: 0-1
- Benchmark: Autonomous Flight Safety Benchmark
- Safety Precision target: 1
- 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
- CrewAI · Required
- crewAI · Optional
- Hamming · Optional
Evaluation contract
- high_wind_rejection_test · Weight 1
- safety_precision · Weight 1
Metrics
- safety_precision · Target 1
Benchmarks
- Autonomous Flight Safety Benchmark
- space
Reference cases
- 1 public reference case
Workflow tasks
- Task 1
Input: JSON with flight_id, origin, destination, wind_speed_knots, obstacle_clearance_m.
Output: JSON with clearance_approved, risk_level, hazard_warnings.
Execution harness: Python
Evaluation tools
- CrewAI · Agent Framework
Recipe freeze marker
No recipe freeze time is recorded.