World Cup Stadium Schedule Crew with CrewAI
Morocco tendered a $291m package for the World Cup 2030 stadium construction. Build a multi-agent collaborative crew using CrewAI where specialized agents (Civil Engineer, Procurement Specialist, Risk Officer) collaborate to evaluate construction schedule conflicts. Achieve complete conflict detection across a 500-task gantt chart.
What you are building
The core problem, expected build, and operating context for this challenge.
Orchestrate role-playing AI agents using CrewAI to simulate schedule alignment and vendor coordination for major World Cup stadium construction packages.
How work is evaluated
Evaluates the Crew's ability to identify overlapping critical path dependencies and generate resolutions.
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.
conflict_completeness
Ensures all resource collisions in input are detected
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
recommendation_feasibility
Score measuring whether proposed timeline resolution maintains final deadline • target: 0.95 • 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
Define CrewAI agents with specific roles, goals, and backgrounds for stadium EPC.
Build tasks that require inter-agent communication and schedule conflict resolution.
Parse Gantt schedule dependencies (MS Project / Primavera P6 output format).
Produce consolidated milestone risk reports ahead of tender submission.
Reference links and supporting material
Synthetic Primavera P6 schedule outputs for FIFA-standard stadium developments in Morocco.
Challenge setup
Evaluates the Crew's ability to identify overlapping critical path dependencies and generate resolutions.
Challenge input
JSON array of task objects with start_date, end_date, resource, and dependencies
CrewAI
Provides structured multi-agent collaboration features.
Evaluated output
JSON summary of detected conflicts and crew recommendations
- Ensures all resource collisions in input are detected
- Score measuring whether proposed timeline resolution maintains final deadline • target: 0.95 • range: 0-1
- Benchmark: CrewSchedulingBench
- Recommendation Feasibility target: 0.95
- 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
- Zed · Optional
Evaluation contract
- conflict_completeness · Weight 1
- recommendation_feasibility · Weight 1
Metrics
- recommendation_feasibility · Target 0.95
Benchmarks
- CrewSchedulingBench
- general
Reference cases
- 1 public reference case
Workflow tasks
- Task 1
Input: JSON array of task objects with start_date, end_date, resource, and dependencies
Output: JSON summary of detected conflicts and crew recommendations
Execution harness: Python
Evaluation tools
- CrewAI · Agent Orchestration
Recipe freeze marker
No recipe freeze time is recorded.