Design and review goal-oriented agent loops to prevent runaway execution, token burning, and verification gaming.

Configure deep agent architectures, built-in middleware, backends, and modular skills for LangChain.

Configure short-term, long-term, and hybrid storage backends for deep agent file operations.

Reference framework for writing predictable agent-consumed documents, skills, and configuration files.

Delegate independent tasks to specialized parallel subagents with isolated context to save time.