Build a Mineral Supply Chain Risk Agent
The US government is implementing a new strategy in Latin America to secure critical minerals like copper and rare earths, as evidenced by the $1.6B deal for USA Rare Earth and Ivanhoe's Chilean exploration. In this challenge, you will build an autonomous Supply Chain Intelligence Agent using the Mastra AI framework. The agent must orchestrate a RAG-based workflow that monitors mining news, identifies geopolitical risks in specific jurisdictions (e.g., Chile, Venezuela), and calculates a 'Supply Security Score' for specific commodities. You will integrate Arize AI to provide observability into the agent's decision-making process. Mastra AI's built-in memory will be used to track the evolution of mining M&A trends (like Zijin's $4B Allied Gold acquisition), while Arize AI will monitor for hallucinations or drift in the risk scoring logic. The final system should provide actionable alerts for supply chain managers when policy shifts or price surges (like Gold's recent warning signal) indicate impending volatility.
What you are building
The core problem, expected build, and operating context for this challenge.
The US government is implementing a new strategy in Latin America to secure critical minerals like copper and rare earths, as evidenced by the $1.6B deal for USA Rare Earth and Ivanhoe's Chilean exploration. In this challenge, you will build an autonomous Supply Chain Intelligence Agent using the Mastra AI framework. The agent must orchestrate a RAG-based workflow that monitors mining news, identifies geopolitical risks in specific jurisdictions (e.g., Chile, Venezuela), and calculates a 'Supply Security Score' for specific commodities. You will integrate Arize AI to provide observability into the agent's decision-making process. Mastra AI's built-in memory will be used to track the evolution of mining M&A trends (like Zijin's $4B Allied Gold acquisition), while Arize AI will monitor for hallucinations or drift in the risk scoring logic. The final system should provide actionable alerts for supply chain managers when policy shifts or price surges (like Gold's recent warning signal) indicate impending volatility.
Shared data for this challenge
Review public datasets and any private uploads tied to your build.
How submissions are scored
These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.
Mastra Agent Initialization
Checks if the Mastra agent starts correctly with its defined tools.
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
Arize Connectivity
Verifies that traces are being successfully sent to the Arize endpoint.
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
Risk Precision
Accuracy of the risk score relative to human-labeled policy news. • target: 0.85 • 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
Master the initialization of Mastra AI agents using TypeScript and the @mastra/core library
Implement persistent storage for agent memory to maintain context across multi-session mining trend analysis
Design custom Mastra Tools to interface with external news APIs and commodity price feeds
Integrate Arize AI Phoenix or SDK to capture traces of tool execution and evaluate prompt effectiveness
Build a RAG pipeline that indexes Latin American mining policy documents and M&A reports
Optimize agent workflows to handle high-volume commodity market signals like the 'Gold Surge' warning
Deploy the agent as a resilient service that provides automated risk reports via a REST API
How this agent runs
The system must accurately identify a geopolitical risk and update a commodity security score.
Challenge input
JSON object with commodity name and a simulated news headline
Agent execution
The configured agent processes the input under the challenge policy.
Evaluated output
JSON object with updated Risk Score and Arize trace ID
- Checks if the Mastra agent starts correctly with its defined tools.
- Verifies that traces are being successfully sent to the Arize endpoint.
- Accuracy of the risk score relative to human-labeled policy news. • target: 0.85 • range: 0-1
- Risk Precision target: 0.85
- 1 public reference case
- Node.js execution harness
View technical recipe
Configured tools
No tool records are attached.
Evaluation contract
- Mastra Agent Initialization · Weight 1
- Arize Connectivity · Weight 1
- Risk Precision · Weight 1
Recipe state
This is a preview. The configuration can change before the evaluation recipe is locked.
Run this agent on your dataset and AI stack
Bring your dataset, model providers, and success criteria. We will scope the right managed run for your team.
Scope a managed run[ok] Wrote CHALLENGE.md
[ok] Wrote .versalist.json
[ok] Wrote eval/examples.json
Requires VERSALIST_API_KEY. Works with any MCP-aware editor.
DocsFind another challenge
Jump to a random challenge when you want a fresh benchmark or a different problem space.