Back to Prompt Library
planning

Initial Mastra Agent Setup

Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.

Linked challenge: Mastra-Powered Critical Mineral Risk Orchestrator with Patronus AI Evaluation

Format
Text-first
Lines
1
Sections
1
Linked challenge
Mastra-Powered Critical Mineral Risk Orchestrator with Patronus AI Evaluation

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines
1 sections
No variables
0 checklist items
Initialize a Mastra AI agent in TypeScript that defines a 'SupplyChainAnalyst' role. Define the basic structure of the agent including the `name`, `model`, and an initial set of instructions focusing on identifying minerals (copper, tungsten, rare earths) and infrastructure risks (strikes, geopolitical shifts).

Adaptation plan

Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.

Keep stable

Preserve the role framing, objective, and reporting structure so comparison runs stay coherent.

Tune next

Swap in your own domain constraints, anomaly thresholds, and examples before you branch variants.

Verify after

Check whether the prompt asks for the right evidence, confidence signal, and escalation path.