Skip to main content

Fellowship Exercises

One Agent to Watch Them All

Building an AI Test Monitor

A hands-on LOTR-themed tutorial to build an intelligent watcher agent with tools, MCP servers, and event-driven workflows.

MCP Artifacts (Diagram Coming Soon)

This section will hold the main MCP and Agent system diagrams. For now, here are the core concepts you will use throughout the tutorial:

  • Tools: Executable functions that AI applications can invoke to perform actions (e.g., file operations, API calls, database queries).
  • Resources: Data sources that provide contextual information to AI applications (e.g., file contents, database records, API responses).
  • Prompts: Reusable templates that help structure interactions with language models (e.g., system prompts, few-shot examples).