AI-Driven Green Critical Mineral Supply Chain Optimization with Agentic Workflows
The global push for decarbonization is intensifying the demand for 'green' critical minerals, leading to complex supply chain challenges. From the "green iron" disputes to the volatile pricing of essential commodities like Codelco's copper, and massive infrastructure upgrades like EPA's lead pipe removal, managing these supply chains requires navigating market volatility, geopolitical risks, stringent sustainability standards, and evolving regulations. Traditional supply chain management often struggles with the dynamic nature of these factors. This challenge involves designing and implementing an advanced AI-powered system to optimize the end-to-end supply chain for a hypothetical 'green' critical mineral (e.g., green nickel for EV batteries). The system will leverage a multi-agent framework to simulate and manage procurement, logistics, and risk assessment, focusing on maintaining green certifications and adapting to real-time market changes. This requires integrating large language models with vector databases for knowledge retrieval and intelligent agent orchestration.
What you are building
The core problem, expected build, and operating context for this challenge.
Implement an AI agentic system using Falcon 180B, CrewAI, and Qdrant to optimize green critical mineral supply chains, considering market, sustainability, and regulatory factors.
How work is evaluated
Evaluation will focus on the system's ability to provide actionable, data-driven recommendations, its adaptability to changing conditions, and the robustness of its agentic architecture. Performance will be measured through the efficiency of resource allocation, compliance adherence, and simulated risk mitigation.
Challenge datasets
Public datasets, plus the private datasets you have access to.
What you should walk away with
Design a multi-agent AI system for supply chain management.
Optimize green critical mineral procurement considering sustainability metrics.
Integrate large language models for complex decision-making.
Develop robust risk assessment and mitigation strategies within the supply chain.
Utilize vector databases for efficient RAG on dynamic market and regulatory data.
Reference links and supporting material
Sample data for 2 tasks
Challenge setup
Evaluation will focus on the system's ability to provide actionable, data-driven recommendations, its adaptability to changing conditions, and the robustness of its agentic architecture. Performance will be measured t...
Challenge input
{'mineral_type': 'green nickel', 'quantity_kg': 10000, 'max_budget_usd': 500000, 'sustainability_score_min': 8.5, 'current_market_data': {'nickel_p...
Agent execution
No agent tool is listed for this challenge.
Evaluated output
{'selected_supplier_id': 'supplier_A', 'procurement_cost_usd': 480000, 'estimated_sustainability_score': 8.9, 'estimated_delivery_days': 25, 'justi...
- Ensures all task outputs are valid JSON.
- Checks if the selected supplier in 'SimulateGreenProcurement' adheres to minimum sustainability score and b...
- Verifies that a 'mitigation_strategy' is present for 'high' or 'medium' risk levels in 'AssessSupplyChainRi...
- ProcurementCostEfficiency target: 0.95
- Python execution harness
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
No tool records are attached.
Evaluation contract
- Ensures all task outputs are valid JSON.
- Checks if the selected supplier in 'SimulateGreenProcurement' adheres to minimum sustainability score and budget.
- Verifies that a 'mitigation_strategy' is present for 'high' or 'medium' risk levels in 'AssessSupplyChainRisk'.
Metrics
- ProcurementCostEfficiency · Target 0.95
- SustainabilityScoreAchievement · Target 0.98
- RiskAssessmentAccuracy · Target 0.9
Workflow tasks
- Task 1
Input: {'mineral_type': 'green nickel', 'quantity_kg': 10000, 'max_budget_usd': 500000, 'sustainability_score_min': 8.5, 'current_market_data': {'nickel_price_per_kg': 45, 'carbon_credit_cost_per_ton': 80, 'shipping_cost_per_km_ton': 0.15}}
Output: {'selected_supplier_id': 'supplier_A', 'procurement_cost_usd': 480000, 'estimated_sustainability_score': 8.9, 'estimated_delivery_days': 25, 'justification': 'Detailed rationale for supplier selection and strategy.'}
Execution harness: Python
- Task 2
Input: {'current_route': 'Route_Pacific_Rim', 'simulated_disruption': {'type': 'port_strike', 'location': 'Shanghai', 'duration_days': 7}, 'supply_chain_context': {'inventory_days_remaining': 30, 'alternative_routes_available': ['Route_Indian_Ocean']}}
Output: {'risk_level': 'high', 'impact_assessment': 'Increased lead time by 10 days, potential 5% cost increase.', 'mitigation_strategy': 'Divert shipments to alternative port, renegotiate contracts with flexible delivery clauses.', 'justification': 'Detailed explanation of risk assessment and mitigation choice.'}
Execution harness: Python
Recipe freeze marker
No recipe freeze time is recorded.