Tools
Executable functions an agent can call to act in the world: trigger jobs, query APIs, and automate operations.
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.
Executable functions an agent can call to act in the world: trigger jobs, query APIs, and automate operations.
Structured context the agent can read: logs, files, run states, and deployment metadata used for grounded decisions.
Reusable instructions and templates that shape reasoning and output style across troubleshooting and delivery flows.