建立一个基于用户研究数据回答问题的人工智能
Modern products often have a large amount of user research data from different sources: user research interviews, intercom conversations, customer e-mails, surveys, customer reviews on various platforms, etc.
现代产品通常有大量来自不同来源的用户研究数据：用户研究访谈、对讲机对话、客户电子邮件、调查、各种平台的客户评论等。
Making sense of all that data is a challenging task. A traditional way to do that is to maintain a neatly organized database with various corresponding tags.
理解所有这些数据是一项具有挑战性的任务。一个传统的方法是维护一个有各种相应标签的整齐的数据库。
But what if we can have our personal AI chatbot that can answer any question about our user research data?
但是，如果我们可以拥有自己的个人人工智能聊天机器人，可以回答关于用户研究数据的任何问题，那该怎么办？
By querying a large amount of historic user research data, the chatbot can provide insights and recommendations for a new project, product, or marketing campaign.
通过查询大量的历史用户研究数据，聊天机器人可以为新项目、产品或营销活动提供洞察力和建议。
Well, now it’s possible with just a few lines of code. You can do that even without a technical background. In this article, I’m going to explain how to do that step-by-step.
好了，现在只需几行代码就可以了。即使没有技术背景，你也可以做到这一点。在这篇文章中，我将一步步解释如何做到这一点。
This technique was first described by Dan Shipper.
OpenAI API
OpenAI API
You are probably familiar with ChatGPT and hopefully are already using it in your working process. If not, I recommend reading my article about AI's impact on design first.
你可能对ChatGPT很熟悉，并且希望已经在你的工作过程中使用它。如果没有，我建议你先阅读我的关于AI对设计的影响的文章。
OpenAI also provides an API to send the requests. We need that to be able to send the relevant context to the model. And to keep the information private.
OpenAI还提供了一个API来发送请求。我们需要这样做，以便能够向模型发送相关的上下文。并且要保持信息的私密性。
Before we start with API, you can try interacting with GPT-3 model through a user interface in GPT-3 Playground.
在我们开始使用API之前，你可以尝试通过GPT-3 Playground的用户界面与GPT-3模型进行交互。
OpenAI API Playground
OpenAI的API游乐场
Privacy concerns
隐私问题
There are many privacy concerns when we deal with user data. By default, OpenAI will not use data submitted by customers via our API to train OpenAI models or improve OpenAI’s service offering. But of course, there might...