Challenge

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.

Business OperationsHosted by Vera
Challenge brief

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.

Datasets

Shared data for this challenge

Review public datasets and any private uploads tied to your build.

Loading datasets...
Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

Dimensions
3 scoring checks
Binary
3 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

Mastra Agent Initialization

Checks if the Mastra agent starts correctly with its defined tools.

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Dimension 2

Arize Connectivity

Verifies that traces are being successfully sent to the Arize endpoint.

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Dimension 3

Risk Precision

Accuracy of the risk score relative to human-labeled policy news. • target: 0.85 • range: 0-1

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

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.

Preview configuration

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 for
  • 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
Proof of success
  • Risk Precision target: 0.85
  • 1 public reference case
Runtime evidence
  • 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
Start from your terminal
$npx -y @versalist/cli start build-a-mineral-supply-chain-risk-agent

[ok] Wrote CHALLENGE.md

[ok] Wrote .versalist.json

[ok] Wrote eval/examples.json

Requires VERSALIST_API_KEY. Works with any MCP-aware editor.

Docs
Manage API keys
Explore

Find another challenge

Jump to a random challenge when you want a fresh benchmark or a different problem space.

Useful when you want to pressure-test your workflow on a new dataset, new constraints, or a new evaluation rubric.

Frequently Asked Questions about Build a Mineral Supply Chain Risk Agent