Wrap agent calls in a grader-and-revise loop keyed to a rubric — Anthropic's 'Performance Outcomes' pattern

MindStudio·medium signal

Anthropic's June 2026 'Performance Outcomes' adds a grader that scores each subagent's result against a rubric and sends it back to revise until it passes — a closed quality loop rather than one-shot generation. You can replicate this without the feature by wrapping any agent call in a judge-and-retry loop tied to an explicit rubric, with a hard cap on iterations. This catches the 'plausible but wrong' outputs that single-pass agents emit and that a final-output-only check would miss.