Pinterest 如何通过 Loop Engineering 提升 Analytics Agent 合规性

Looking down Spiral Staircase representing loops that are essential to Loop engineering for tuning agents.

俯视螺旋楼梯，它象征着对于调优智能体而言至关重要的循环，这些循环是 Loop engineering 的核心。

The Compliance Problem

合规问题

Compliance means following the right steps at the right time

合规意味着在正确的时间遵循正确的步骤

Pinterest’s Analytics Agent helps teams answer questions such as “How did query latency for the ads reporting pipeline change last week?” It searches the company’s data ecosystem, analyzes the relevant information, and recommends an answer or course of action.

Pinterest 的 Analytics Agent 帮助团队回答诸如“上周广告报告流水线的查询延迟发生了怎样的变化？”之类的问题。它会搜索公司的数据生态系统，分析相关信息，并推荐答案或行动方案。

Not every question requires the same steps. We call the agent compliant when it identifies and follows the steps that apply. Improving compliance is intended to make answers more consistent and reduce the risk of incomplete or inaccurate results. Examples include:

并非每个问题都需要相同的步骤。当智能体识别并遵循适用的步骤时，我们称其为合规。提高合规性旨在使答案更一致，并降低不完整或不准确结果的风险。示例包括：

Read the data-discovery skill when it needs help finding the right tools or sources.
当它需要帮助找到合适的工具或来源时，阅读 data-discovery 技能。
Inspect table metadata before writing SQL to learn what the columns mean, which filters are required, and whether the table has important usage notes.
在编写 SQL 之前检查表元数据，以了解各列的含义、哪些筛选器是必需的，以及该表是否有重要的使用说明。
Search every relevant source type, including tables, dashboards, and metrics, rather than stopping at the first useful result.
搜索所有相关来源类型，包括表格、仪表盘和指标，而不是在第一个有用结果处就停止。

These are three examples from a broader set of compliance rules, and whether they apply depends on the question. If a user provides the appropriate table, the agent may not need the data-discovery skill, while an open-ended question may require a broader search. The agent must decide which rules apply and follow the...