要架构专属自己企业的 AI 系统，可以参考以下步骤：
一、逐步搭建 AI 智能体
搭建整理入库工作流
在外层 bot 中封装工作流，完成整体配置
二、相关术语
以下是一些在 AI 系统架构中可能涉及的术语：
经过上述配置，您可以在「预览与调试」窗口与 AI 智能体对话并使用全部功能。
经过上述的配置，我们现在已经得到了两个可用的工作流（整理入库、选择内容），接下来就是把他们编排成为一个完整的智能体。配置过程如下：1）创建Bot2）填写Bot介绍3）切换模型为“通义千问”：测试下来，通义对我的提示词理解、执行效果最好4）把我们刚才配置好的工作流，添加到Bot中5）新增变量{{app_token}}6）添加外层bot提示词（可以按照需求和实际效果进行优化调整）：到这一步结束，你已经能在「预览与调试」窗口，与AI稍后读智能体对话，使用全部的功能。
接下来开始在Coze中逐步搭建AI智能体。首先搭建整理入库工作流。这一步是支撑整个AI稍后读服务的前置流程。需要实现以下功能流程：在搭建内容入库工作流这一步，我花了相当长的时间，调试飞书多维表格插件的使用方式，因为篇幅原因，不在此详述，我将直接分享最终的设置方式。首先新建工作流「url2table」：根据弹窗要求，自定义工作流信息。工作流全局流程设置如下：
Terminology used in thispaper:50AI or AI system or AI technologies:products and services that are ‘adaptable’ and‘autonomous’ in the sense outlined in our definition in section 3.2.1.AI supplier:any organisation or individual who plays a role in the research,development,training,implementation,deployment,maintenance,provision or sale of AI systems.AI user:any individual or organisation that uses an AI product.AI life cycle:all events and processes that relate to an AI system’s lifespan,frominception to decommissioning,including its design,research,training,development,deployment,integration,operation,maintenance,sale,use and governance.AI ecosystem:the complex network of actors and processes that enable the use andsupply of AI throughout the AI life cycle(including supply chains,markets,and governancemechanisms).Foundation model:a type of AI model that is trained on a vast quantity of data and isadaptable for use on a wide range of tasks.Foundation models can be used as a base forbuilding more specific AI models.Foundation models are discussed in more detail insection 3.3.3below.51Impacted third party:an individual or company that is impacted by the outcomes of theAI systems that they do not use or supply themselves.‘Is ChatGPT a cybersecurity threat?’ TechCrunch,2023.OPWNAI:Cybercriminals starting to use ChatGPT,Check Point Research,2023.These are not intended to be legal definitions for the purposes of the framework.The value chain of general-purpose AI,Ada Lovelace Institute,2023.A pro-innovation approach to AI regulationPart Two:The current regulatoryenvironment2.1 Navigating the current landscape