AI-Powered Critical Mineral Supply Chain Security Assessment
Critical infrastructure relies heavily on secure supply chains for essential resources like critical minerals. Geopolitical shifts, mergers, and acquisitions can introduce significant vulnerabilities. This challenge requires you to design and implement an advanced AI agent system that proactively assesses the security implications of such corporate actions on critical mineral supply chains. The system should identify potential points of failure, geopolitical risks, and regulatory non-compliance, providing actionable insights for mitigation. Leveraging a powerful Large Language Model like Llama 3.3 (70B) orchestrated through LangGraph, you will build dynamic, multi-step reasoning capabilities. The solution should be deployed on Google Vertex AI for scalable and managed execution, integrating real-time geopolitical data, trade statistics, and regulatory frameworks to simulate expert analysis of complex, evolving scenarios.
What you are building
The core problem, expected build, and operating context for this challenge.
Develop an AI agent system using Llama 3.3 (70B), LangGraph, and Google Vertex AI to assess supply chain security risks in critical mineral mergers and acquisitions.
How work is evaluated
The evaluation will assess the AI system's ability to accurately identify and quantify supply chain security risks, propose relevant mitigation strategies, and generate structured, comprehensive reports based on provided merger scenarios.
Challenge datasets
Public datasets, plus the private datasets you have access to.
What you should walk away with
Master advanced prompt engineering techniques for Llama 3.3 (70B) on Google Vertex AI, focusing on generating nuanced geopolitical and economic analysis.
Design and implement multi-agent workflows using LangGraph to simulate specialized roles such as geopolitical analyst, supply chain expert, and regulatory compliance officer.
Build robust data retrieval and integration modules capable of ingesting and structuring real-time news, geopolitical risk indices, critical mineral trade data, and relevant regulatory documents.
Orchestrate the deployment and continuous management of Llama 3.3 (70B) models via Google Vertex AI endpoints, ensuring scalability and reliability.
Develop a sophisticated risk scoring mechanism that quantifies potential vulnerabilities, assessing disruption probability, impact severity, and strategic importance of critical mineral assets.
Integrate compliance checks against specific international trade regulations, national security frameworks, and critical minerals policies relevant to the proposed merger.
Optimize LangGraph agent reasoning paths for efficiency and accuracy, enabling the system to adapt to new information and evolving geopolitical scenarios.
Generate comprehensive, structured reports that include detailed risk assessments, recommended mitigation strategies, and policy implications for stakeholders.
Reference links and supporting material
Sample data for 2 tasks
Challenge setup
The evaluation will assess the AI system's ability to accurately identify and quantify supply chain security risks, propose relevant mitigation strategies, and generate structured, comprehensive reports based on provi...
Challenge input
{ 'merger_details': {'acquiring_company': 'string', 'target_company': 'string', 'key_assets': ['string'], 'geographies_involved': ['string']}, 'cur...
Agent execution
No agent tool is listed for this challenge.
Evaluated output
{ 'identified_risks': [ {'risk_type': 'string', 'description': 'string', 'probability': 'float (0-1)', 'impact_score': 'int (1-10)', 'mitigation_st...
- System identifies at least 80% of major geopolitical and supply chain risks present in the test case.
- Proposed mitigation strategies are logically sound and directly address identified risks.
- AverageRiskScoreAccuracy target: 1
- 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
- System identifies at least 80% of major geopolitical and supply chain risks present in the test case.
- Proposed mitigation strategies are logically sound and directly address identified risks.
Metrics
- AverageRiskScoreAccuracy · Target 1
- ComplianceIssuePrecision · Target 0.8
Workflow tasks
- Task 1
Input: { 'merger_details': {'acquiring_company': 'string', 'target_company': 'string', 'key_assets': ['string'], 'geographies_involved': ['string']}, 'current_geopolitical_context': 'string' }
Output: { 'identified_risks': [ {'risk_type': 'string', 'description': 'string', 'probability': 'float (0-1)', 'impact_score': 'int (1-10)', 'mitigation_strategy': 'string', 'justification': 'string'} ], 'overall_risk_score': 'float (0-10)', 'strategic_recommendations': ['string'] }
Execution harness: Python
- Task 2
Input: { 'merger_details': {'acquiring_company': 'string', 'target_company': 'string', 'sector': 'string', 'key_markets': ['string']}, 'relevant_regulation_name': 'string', 'regulation_text': 'string' }
Output: { 'compliance_status': 'string (Compliant|Non-Compliant|Requires Review)', 'identified_issues': ['string'], 'recommended_actions': ['string'] }
Execution harness: Python
Recipe freeze marker
No recipe freeze time is recorded.