Orchestrate a CrewAI Industrial Feasibility Squad with Pydantic AI for GCC Green Iron Projects
Oman's Meranti green iron project and Saudi Arabia's push to localize desalination production require rigorous feasibility analysis. This challenge tasks you with building a multi-agent system using CrewAI to evaluate the economic and technical viability of these industrial projects. You will create three specialized agents: a 'Regional Compliance Expert', a 'Supply Chain Analyst', and a 'Sustainability Consultant'. Each agent will utilize Pydantic AI for structured data validation, ensuring that all findings (e.g., water requirements, carbon footprint, local content spend) adhere to strict data schemas. The agents must collaborate to produce a final 'Go/No-Go' report that accounts for Oman's water supply constraints from Marafiq and Saudi's localization targets. The goal is to move from manual PDF-based feasibility studies to an automated, structured agentic analysis pipeline.
What you are building
Build a collaborative multi-agent squad using CrewAI and Pydantic AI to automate industrial feasibility studies for GCC green energy and manufacturing projects.
How work is evaluated
The system is evaluated on the structural integrity of its findings and its ability to synthesize data from disparate sources into a cohesive feasibility report.
Datasets
Public datasets, plus the private datasets you have access to.
How submissions are scored
Schema Validation
Validates that the output exactly matches the Pydantic FeasibilityModel.
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
Collaborative Synthesis
Quality score for how well agents integrated each other's data • target: 4.5 • range: 1-5
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
Learning goals
Design and orchestrate role-playing AI agents with CrewAI for complex industrial analysis
Implement strict data validation for agent outputs using Pydantic AI models
Develop collaborative task dependencies where agent outputs feed into subsequent processes
Analyze water-energy nexus constraints in GCC green hydrogen and iron projects
Resources
Project profiles for GCC industrial initiatives including desalination localized production specs, Marafiq water volume data, and Oman green iron technical requirements.
Challenge setup
The system is evaluated on the structural integrity of its findings and its ability to synthesize data from disparate sources into a cohesive feasibility report.
Challenge input
Project description and resource constraints
CrewAI
Best-in-class framework for multi-agent role-playing workflows.
Pydantic AI
Ensures AI agent outputs conform to industrial standards.
Evaluated output
Structured JSON following a Pydantic schema
- Validates that the output exactly matches the Pydantic FeasibilityModel.
- Quality score for how well agents integrated each other's data • target: 4.5 • range: 1-5
- Benchmark: Multi-Agent Logic Benchmark
- Collaborative Synthesis target: 4.5
- Protected reference cases support private evaluation
- Python execution harness
- Python sandbox (unavailable on Versalist)
Shows the first task, up to three tools, and up to three evidence items.
View technical recipe
Configured tools
- CrewAI · Required
- Pydantic AI · Optional
- Zed · Optional
- Pydantic AI · Optional
Evaluation contract
- Schema Validation · Weight 1
- Collaborative Synthesis · Weight 1
Metrics
- Collaborative Synthesis · Target 4.5
Benchmarks
- Multi-Agent Logic Benchmark
- general
Reference cases
- Protected reference cases are configured.
Workflow tasks
- Task 1
Input: Project description and resource constraints
Output: Structured JSON following a Pydantic schema
Execution harness: Python
Evaluation tools
- CrewAI · Agent Orchestration
- Pydantic AI · Data Integrity
Recipe freeze marker
No recipe freeze time is recorded.