就在今年5月，新加坡政府科技局（GovTech）组织了首届 GPT-4 提示工程大赛，吸引了超过 400 名杰出的参与者。冠军获得者Sheila Teo分享了如何使用一些简单有效的技巧来优化对ChatGPT的使用。
对于AI使用者来说，结构化的提示词框架能够帮助我们以一种更系统、更明确的方式与 AI 交互。这种清晰性对于确保 AI 系统能准确理解用户的意图至关重要，特别是在处理复杂的查询或命令时。
CO-STAR框架是新加坡政府科技部数据科学与人工智能团队的心血，是构建提示的便捷模板。 它考虑到了大型语言模型回答的有效性和相关性的所有关键方面，从而使回答更加优化。
先一起来看下CO-STAR框架：
通过CO-STAR框架图我们可以看到，分为六大点：
Context（C）上下文：
Context非常好理解，即是上下文，我们需要给GPT提供一个清晰的上下文，就比如我们要讲一个故事，需要讲清楚故事的前因后果，听故事的人才能听明白，然后给你准确的反馈。
Objective (O)目标 ：
明确你希望GPT给你提供什么样的帮助，清晰地界定任务目标，可以使大语言模型更专注地调整其回应，以实现这一具体目标。
Style (S) 风格 ：
明确你期望的写作风格，你可以指定一个特定的著名人物或某个行业专家的写作风格，如商业分析师或 CEO。这可以指导大语言模型以一种符合你需求的方式和词汇选择进行回应。
Tone (T) 语气 ：
告诉ChatGPT你期望的表达语气，确保大语言模型的回应能够与预期的情感或情绪背景相协调。可能的语气包括正式、幽默、富有同情心等。如果你希望文章更加正式，就明确说明：“这篇文章的语气应该正式而专业。”
Audience (A) 受众：
识别目标受众针对特定受众定制大语言模型的回应，无论是领域内的专家、初学者还是儿童，都能确保内容在特定上下文中适当且容易理解。比如这样：”我的读者都是AI小白，需要用简单的方式解释复杂的概念“
Response (R) 响应：
最后，规定输出的回应格式，这是为了确保大语言模型按照你的具体需求进行输出，便于执行下游任务。常见的格式包括列表、JSON 格式的数据、专业报告等。对于大部分需要程序化处理大语言模型输出的应用来说，JSON 格式是理想的选择。
看到这里，是不是会觉得有点复杂，有种似懂非懂的感觉。
都说实践是检验真理的唯一标准，那接下来就一起来实操一下，比如现在需要在Fb发布一条帖子，宣传公司的产品。未使用CO-STAR结构的提问可能是：”为我公司的新产品 Cno——一款降噪舒适的蓝牙耳机撰写一条Fb帖子”，得到的结果是这样的：
可以看到这个结果缺乏必要的细节和针对性吸引力，好像套用在任何产品上都合适，而且没有阐述产品的特点给到用户。
那使用CO-STAR结构应该是怎样提问呢？
对于一些AI小白来说，要理解CO-STAR结构并正确使用，会有一点难度，AI工具的出现是为了便捷我们的生活而不是为我们制作困难，而302.AI自研的AI提示词生成器工具替大家解决这个难题。
AI提示词生成器工具操作界面简洁，包含了CO-STAR和CRISPE两种结构。使用方法也非常非常方便！我们只需要输入未使用CO-STAR结构的提问，选择结构类型后点击【生成】，便会得到使用CO-STAR结构后的提问，得出的结果还可以进行修改调整。
接下来将继续我们的实践，我们将使用AI提示词生成器工具后得到的结果复制，再去提问，看下会得到什么结果：
可以看到得到的文案，不仅突出了产品的特点，还能够与使用场景相结合，更能够吸引到目标用户。
参考文章：https://www.bilibili.com/read/cv34387928/?spm_id_from=333.999.0.0
随着AI时代的到来，很多人都开始尝试使用AI去帮助我们的工作或者生活解决问题，无论是CO-STAR提示词结构还是AI提示词工具的出现，都是为了更好的帮助我们使用AI这一工具，通过它们，我们能够训练AI更好地理解我们的需求，更准确地执行我们的指令。这不仅提高了工作效率，也让我们有更多的时间去探索和创造。
评论列表（14条）
I was just searching for this info for a while. After 6 hours of continuous Googleing, at last I got it in your website. I wonder what is the lack of Google strategy that don’t rank this type of informative sites in top of the list. Normally the top web sites are full of garbage.
I love your blog.. very nice colors & theme. Did you create this website yourself or did you hire someone to do it for you? Plz reply as I’m looking to design my own blog and would like to know where u got this from. appreciate it
naturally like your website but you have to check the spelling on quite a few of your posts. Many of them are rife with spelling problems and I find it very bothersome to inform the truth however I¦ll certainly come back again.
Thank you for all of your hard work on this website. My niece take interest in conducting research and it is easy to understand why. A lot of people know all regarding the dynamic means you make insightful guidelines on the blog and as well invigorate response from other ones on the area then our favorite child is without question studying a lot of things. Have fun with the rest of the new year. You have been performing a fantastic job.
Magnificent web site. Plenty of helpful info here. I am sending it to a few friends ans also sharing in delicious. And obviously, thank you in your effort!
Hi! Someone in my Myspace group shared this website with us so I came to check it out. I’m definitely enjoying the information. I’m book-marking and will be tweeting this to my followers! Superb blog and wonderful design.
Respect to author, some great information .
Thank you for another great post. The place else could anybody get that type of info in such an ideal means of writing? I’ve a presentation next week, and I am at the search for such info.
Great amazing things here. I?¦m very glad to see your article. Thank you so much and i’m having a look forward to touch you. Will you kindly drop me a e-mail?
Wow that was odd. I just wrote an incredibly long comment but after I clicked submit my comment didn’t appear. Grrrr… well I’m not writing all that over again. Anyway, just wanted to say great blog!
[…] Prompt Engineering 是一门关于如何设计、优化和构建提示词的技术与艺术，目的是引导 AI 模型产生最符合用户意图的输出。它融合了自然语言处理、认知心理学和人机交互等多学科知识，研究如何通过精心设计的提示来最大化 AI 系统的能力。如在之前的文章《CO-STAR超给力提示词框架，速看》中，我们也对如何构建一个高效的提示词框架进行了介绍。 […]
I was very pleased to find this web-site.I wanted to thanks for your time for this wonderful read!! I definitely enjoying every little bit of it and I have you bookmarked to check out new stuff you blog post.
You actually make it seem so easy together with your presentation however I find this topic to be really one thing that I believe I might by no means understand. It kind of feels too complex and extremely vast for me. I am looking forward to your subsequent put up, I will try to get the hold of it!
Nice read, I just passed this onto a friend who was doing a little research on that. And he actually bought me lunch since I found it for him smile So let me rephrase that: Thank you for lunch! “To be 70 years young is sometimes far more cheerful and hopeful than to be 40 years old.” by Oliver Wendell Holmes.