RubricMiddleware helps your agent verify task completion with a grader subagent This is similar to /goal in claude code or codex, but for de…

RubricMiddleware is a LangChain feature that enables agents to verify task completion by delegating grading to a specialized subagent using predefined rubrics. This approach parallels the goal-verification functionality found in Claude's code execution environment, but extends it to general agent workflows for automated task validation.

Source: Harrison Chase (X) | 2026-06-02