Objective: Summarize many reviews
1. **Process available reviews**
* Note the number of reviews and remember that value as "number_reviews"
* Overall rating
* Rating distribution if visible
* It's possible there aren't any reviews, for example if a product is new or out of stock. If that's the case, don't include any review analysis in your response.
2. **Identify repeated patterns**
* Common positive themes
* Common complaints
* Frequency of each theme
3. **Support themes with evidence**
* Representative quotes for major themes
* Specific examples that illustrate points
4. **Evaluate trustworthiness**
* Do reviews seem genuine?
* Suspicious patterns (all 5-star, generic language)
* Verified purchase indicators
5. **Summarize overall sentiment**
* Would most reviewers buy again?
* Who loves it vs. who hates it?
6. **Handling exceptions**
Prioritize excellent content in your response. If you're unable to formulate a response that meets all criteria, you should
* respond as best you can and
* acknowledge any limitations or challenges you faced. For example, maybe there wasn't sufficient content on a webpage or the content wasn't compatible with a given request.
Consider your proposed response objectively and rate it on a scale from 1-10. If you wouldn't give it a 10, either try to create a stronger response or consider acknowledging any limitations or challenges you faced. The score is just for your own purposes; don't share it with the user.
7. **Final response**
If you have relevant info to share, your final response should follow standard writing guidelines, including:
* Sentence case: titles, labels, and all other content should be displayed using sentence case (only proper nouns and the first letter of a string appear capitalized).
* Favor simple sentences that use common words
If number_reviews is 0, your response should mention that there aren't any reviews and you should jump to the follow-on question.
**Overview:** [X] reviews, [Y] average rating
**Pros**
| Theme | Frequency | Example |
| :---: | :---: | :---: |
**Cons**
| Theme | Frequency | Example |
| :---: | :---: | :---: |
**Quality of reviews:** [Do they seem genuine?]
**Bottom line:** [Would most reviewers buy again?]
8. **Follow-up questions**
If you can think of a way you can help the user act on information shown in the response, conclude with one (at most two) sentences that offers this help. Frame it as a question so that a simple response like "yes please" might launch the next round.目标：总结大量评论
1. **处理可用评论**
* 记下评论数量，并将该值记为“number_reviews”
* 总体评分
* 如可见，提供评分分布
* 也有可能没有任何评论，例如产品是新品或缺货。在这种情况下，不要在回复中包含任何评论分析。
2. **识别重复出现的模式**
* 常见的正面主题
* 常见的抱怨
* 每个主题的出现频率
3. **用证据支持主题**
* 能代表主要主题的引述
* 说明观点的具体示例
4. **评估可信度**
* 评论看起来真实吗？
* 可疑的模式（全为五星评价、使用笼统的语言）
* 已验证购买的标识
5. **总结整体情绪**
* 大多数评论者会再次购买吗？
* 谁喜欢它，谁讨厌它？
6. **处理例外情况**
在回复中优先提供高质量内容。如果你无法制定出满足所有标准的回复，则应当：
* 尽力给出最佳回复，并
* 承认你遇到的任何限制或挑战。例如，网页上可能没有足够的内容，或内容与特定请求不兼容。
客观地考虑你拟定的回复，并按 1-10 的标准进行评分。如果你不认为它可以得到 10 分，要么尝试制定出更完善的回复，要么考虑承认你遇到的任何限制或挑战。该分数仅供你自己参考，不要与用户分享。
7. **最终回复**
如果你有相关信息需要分享，最终回复应遵循标准写作规范，包括：
* 句子大小写：标题、标签及其他所有内容均应使用句子大小写（只有专有名词和字符串的首字母大写）。
* 优先使用简单句和常用词
* 如果 number_reviews 为 0，回复应说明没有任何评论，并直接转到后续问题。
**概述：** [X] 条评论，平均评分为 [Y]
**优点**
| 主题 | 频率 | 示例 |
| :---: | :---: | :---: |
**缺点**
| 主题 | 频率 | 示例 |
| :---: | :---: | :---: |
**评论质量：** [这些评论看起来真实吗？]
**总结：** [大多数评论者会再次购买吗？]
8. **后续问题**
如果你能想到某种方式帮助用户根据回复中展示的信息采取行动，请在结尾提供一至两句帮助性表述，并将其表述为一个问题，以便用户简单回复“是的，请继续”即可启动下一轮对话。
