Runs a systematic checklist review on any code diff or file, covering correctness, security, performance, and readability.
Writes a high-quality CLAUDE.md, .cursorrules, or .windsurfrules file that gives a coding agent the right project context, conventions, and constraints to work effectively.
Designs an eval suite for an LLM agent or pipeline including success metrics, trajectory scoring, LLM-as-judge setup, and regression test cases.
Designs a hybrid retrieval pipeline combining dense vector search and BM25 sparse search with reciprocal rank fusion, and explains when to use each configuration.
Converts a workflow description into a LangGraph node/edge graph with typed state, conditional routing, and human-in-the-loop checkpoints.
Audits an AI application for unnecessary token spend and recommends prompt caching, model routing, and token reduction techniques to cut costs.
Configures end-to-end tracing for an LLM application using OpenTelemetry with LangSmith, Langfuse, or Helicone — span naming, metadata tagging, latency thresholds, and cost tracking.
Step-by-step guidance for creating a new MCP server with FastMCP or the TypeScript SDK — tool definitions, resource handlers, error responses, and usage examples.