raindrop-ai

Set up Raindrop AI traces for an agent and verify they flow into Workshop.

Set up a local agent replay server for Raindrop Workshop. Use when the user wants Workshop to replay a captured trace against their real local agent code and tools. Creates/updates `.raindrop/agents.yaml`, scaffolds a language-appropriate replay server, registers the project with `raindrop replay register`, and verifies `/health`.

Sets up, debugs, and extends Raindrop (an AI observability/monitoring platform) in a project. Use when adding Raindrop instrumentation, fixing a broken Raindrop integration, or tracking new AI code paths.

Investigates and triages issues in AI applications using Raindrop's MCP tools. Use when investigating AI product issues, triaging bugs in LLM-powered features, analyzing user conversations, debugging agent behavior, or when the user mentions Raindrop signals, events, traces, conversations, or issues — even if they don't say "investigate" explicitly.