Data Analysis AI Prompts Guide: quick fix, steps, and deep guide

Q: Data Analysis AI Prompts Guide

Treat this as a AI tools tutorial issue. Confirm the environment, inputs, permissions, logs, and delivery boundary, then use the linked deep guide for the full checklist.

What is the problem?

面向数据分析和业务团队整理 AI 提示词模板，覆盖指标解释、SQL 思路、异常排查、报表摘要、实验复盘和人工核对边界。

Quick solution

Treat this as a AI tools tutorial issue. First confirm the environment, inputs, permissions, logs, and delivery boundary. Then use the linked deep guide for the full checklist before changing production code or promising a result.

Read the deep guide

Detailed steps

先解释查询逻辑
再给 SQL 草稿
标注需要确认的字段和口径
不直接假设不存在的表
[OpenAI prompt engineering](https://developers.openai.com/api/docs/guides/prompt-engineering)：核对任务、上下文、约束和分步输出。
[OpenAI structured outputs](https://developers.openai.com/api/docs/guides/structured-outputs)：核对结构化结果、字段约束和可解析输出。

Commands or code

你是数据分析师。请解释以下指标变化。
指标：【指标名】
时间范围：【范围】
数据：【粘贴脱敏数据】
业务背景：【活动/版本/渠道变化】
输出：变化摘要、可能原因、需要验证的假设、需要补充的数据、下一步分析建议。

Risk notes

Confirm the real project environment, account permissions, platform rules, and output quality before delivery. Do not ship AI-generated changes without human review, and do not claim indexing, income, deployment success, or ranking improvements without measured evidence.