# Google发布新技能：从你的编码智能体驱动智能体质量飞轮

- 来源：Google Developers Blog（RSS）
- 发布时间：2026-07-01 01:17
- AIHOT 分数：52
- AIHOT 链接：https://aihot.virxact.com/items/cmr0wupt4007fsl40jut5buuu
- 原文链接：https://developers.googleblog.com/driving-the-agent-quality-flywheel-from-your-coding-agent

## AI 摘要

Google推出了一项面向编码智能体的新开发者技能，将评估过程自动化成五阶段飞轮：准备数据、运行推理、使用自适应AutoRaters评分、分析失败聚类、执行针对性优化。该工具可针对生产流量持续运行或通过合成场景按需触发，开发者用自然语言描述测试目标，独立评估服务安全验证并统计实际性能提升。

## 正文

Building AI agents often leaves developers uncertain if prompt tweaks to fix single errors will accidentally cause widespread regressions in production. To bridge this gap, Google has introduced a new developer skill for coding agents that automates a five-stage evaluation flywheel: preparing data, running inference, grading with adaptive AutoRaters, analyzing failure clusters, and executing targeted optimizations. Running continuously against production traffic or on-demand via synthetic scenarios, this tool allows developers to describe testing goals in plain language while an independent evaluation service safely validates and counts actual performance improvements.