Build an end-to-end RFI questionnaire workflow using Amazon Quick Automate使用 Amazon Quick Automate 构建端到端的 RFI 问卷工作流程

Build an end-to-end Request for Information (RFI) questionnaire workflow using Amazon Quick Automate to solve a challenge organizations face at every scale. A typical enterprise might handle hundreds of RFI questionnaires each year, and each arrives as a complex, multi-tab workbook packed with hierarchical question sets, category metadata, and varied response types. The volume, variety, and complexity of these documents create a significant operational challenge. Manually extracting, structuring, and resolving RFI questions requires repeated coordination, delays responses, and can introduce errors each time the questionnaire format changes.使用 Amazon Quick Automate 构建端到端的“信息请求”(RFI) 问卷工作流程，以解决各类规模组织所面临的挑战。典型的企业每年可能需要处理数百份 RFI 问卷，每份问卷都以复杂的多标签工作簿形式呈现，其中包含分层的问题集、类别元数据和多种响应类型。这些文档的数量、种类和复杂性带来了巨大的运营挑战。手动提取、结构化和解析 RFI 问题需要反复协调，这不仅会延迟响应，而且每次问卷格式发生变化时都可能引入错误。

Amazon Quick Automate handles multi-agent automation for supported enterprise processes that can span across departments, systems, UI and API interactions, and third-party systems. It uses a team of agents to simplify business process management and cut down on maintenance overhead. You describe your processing goals in plain language, and Quick Automate can produce an executable workflow covering ingestion, transformation, validation, and output. You can refine the workflow through conversation, run it against your data, and promote validated versions across AWS Regions. This approach can help you respond to RFIs faster and reduce formatting inconsistencies and errors. The automation is designed to scale with your workload, and you can adapt it to new questionnaire formats by updating the natural-language instructions.Amazon Quick Automate 为受支持的企业流程提供多智能体自动化功能，这些流程可以跨越部门、系统、UI 和 API 交互以及第三方系统。它利用一组智能体来简化业务流程管理并减少维护开销。您只需用自然语言描述处理目标，Quick Automate 即可生成涵盖摄取、转换、验证和输出的可执行工作流程。您可以通过对话优化工作流程，针对数据运行该流程，并将经过验证的版本推广到各个 AWS 区域。这种方法有助于您更快地响应 RFI，并减少格式不一致和错误。该自动化旨在随工作负载进行扩展，您可以通过更新自然语言指令来使其适应新的问卷格式。

In this post, we show you how to build an end-to-end automation that reads a multi-tab RFI workbook from Amazon Simple Storage Service (Amazon S3), extracts and structures the questionnaire data, and writes clean output back to Amazon S3. This tutorial uses Amazon Quick Automate and Amazon S3. Review Amazon Quick pricing and Amazon S3 pricing for cost details.在本文中，我们将向您展示如何构建端到端的自动化流程，以从 Amazon Simple Storage Service (Amazon S3) 读取多标签 RFI 工作簿，提取并结构化问卷数据，然后将整理好的输出写回 Amazon S3。本教程使用 Amazon Quick Automate 和 Amazon S3。有关成本详情，请查看 Amazon Quick 定价和 Amazon S3 定价。

Solution overview解决方案概览

This walkthrough automates the processing of an RFI workbook stored in Amazon S3. When procurement teams receive an RFI questionnaire, they need to extract each question and preserve its category and response type. The goal is to produce a structured dataset that downstream teams can consume, interpret, and act on. In this example we present a solution that automates the process using Amazon Quick Automate. You start by connecting Amazon Quick Automate to the Amazon S3 bucket where your RFI workbooks are stored. Then you create an automation project, which is where you select your data connectors and organize your workflows. With the project in place, you can describe your processing logic in plain language: what to read, how to structure it, and where to write the output. The result is a working automation that reads a multi-tab RFI workbook, extracts and structures the questionnaire data, and outputs a clean comma-separated values (CSV) file. It does this without requiring custom code for common scenarios. The following diagram shows the high-level sequence of steps.本指南将演示如何自动化处理存储在 Amazon S3 中的 RFI 工作簿。当采购团队收到 RFI 问卷时，他们需要提取每个问题并保留其类别和响应类型。目标是生成一个结构化的数据集，供下游团队使用、解读并采取行动。在本示例中，我们展示了一种使用 Amazon Quick Automate 自动化该流程的解决方案。首先，将 Amazon Quick Automate 连接到存储 RFI 工作簿的 Amazon S3 存储桶。然后，创建一个自动化项目，您可以在其中选择数据连接器并组织工作流程。项目建立后，您可以用自然语言描述处理逻辑：读取什么内容、如何进行结构化，以及将输出写入何处。最终得到一个可运行的自动化流程，它能读取多标签 RFI 工作簿，提取并结构化问卷数据，最后输出一个整洁的逗号分隔值 (CSV) 文件。对于常见场景，无需编写自定义代码即可实现。下图显示了高层级的步骤顺序。

Figure 1: High-level sequence of steps for the RFI workbook automation图 1：RFI 工作簿自动化的高层级步骤顺序

The diagram takes you from connecting your data source through deploying the finished automation in a production environment. Check the AWS Regions page for the latest availability.该图展示了从连接数据源到在生产环境中部署已完成的自动化流程的全过程。请查看 AWS 区域页面以获取最新可用性信息。

The solution follows these steps:该解决方案遵循以下步骤：

1. Set up an Amazon S3 action connector – Connect Amazon Quick Automate to your S3 bucket.设置 Amazon S3 操作连接器 – 将 Amazon Quick Automate 连接到您的 S3 存储桶。
2. Add the S3 integration to an automation group – Share the S3 action with the automation group that will use it.将 S3 集成添加到自动化组 – 将 S3 操作共享给将要使用它的自动化组。
3. Create an automation project – Create the project where you describe your processing logic.创建自动化项目 – 创建用于描述处理逻辑的项目。
4. Describe the processing logic – Enter a natural-language prompt and let the generative AI assistant build the workflow.描述处理逻辑 – 输入自然语言提示，让生成式 AI 助手构建工作流程。
5. Refine through conversation – Iterate on the generated workflow by requesting targeted changes.通过对话进行优化 – 通过请求针对性的更改来迭代生成的工作流程。
6. Validate results – Run the workflow and verify output in your pre-production (development) AWS account.验证结果 – 运行工作流程并在您的预生产（开发）AWS 账户中验证输出。
7. Promote with Import/Export – Export the validated version and import it into your production account or target AWS Region.通过导入/导出进行推广 – 导出经过验证的版本，并将其导入到您的生产账户或目标 AWS 区域。

Now that we have reviewed the high-level steps for the solution, we will go over the environment requirements.了解了解决方案的高层级步骤后，我们将介绍环境要求。

Prerequisites先决条件

Before you begin, confirm that your environment meets the following requirements.在开始之前，请确认您的环境满足以下要求。

1. An Amazon Quick Enterprise subscription with Amazon Quick Automate access.拥有 Amazon Quick Automate 访问权限的 Amazon Quick 企业订阅。
2. An Amazon S3 bucket in the same AWS Region as the Amazon Quick application.与 Amazon Quick 应用程序位于同一 AWS 区域的 Amazon S3 存储桶。
3. Familiarity with AWS Identity and Access Management (IAM) roles and policies.熟悉 AWS Identity and Access Management (IAM) 角色和策略。
4. Basic understanding of Amazon S3 buckets, prefixes, and objects.对 Amazon S3 存储桶、前缀和对象有基本了解。

IAM baseline for this walkthrough本指南的 IAM 基准

You need an IAM role that grants Amazon Quick Automate permission to access your S3 bucket. If you don’t already have one, follow these instructions to create it now:您需要一个 IAM 角色，授予 Amazon Quick Automate 访问您的 S3 存储桶的权限。如果您还没有该角色，请按照以下说明立即创建：

1. Open the IAM console.打开 IAM 控制台。
2. In the navigation pane, choose Roles, then Create role.在导航窗格中，选择“角色”，然后选择“创建角色”。
3. For Trusted entity type, choose Custom trust policy and paste the following trust policy:对于“受信任实体类型”，选择“自定义信任策略”并粘贴以下信任策略：

{
  "Version": "2012-10-17",
  "Statement": [
    {
      "Effect": "Allow",
      "Principal": {
        "Service": "quicksight.amazonaws.com"
      },
      "Action": "sts:AssumeRole"
    }
  ]
}

4. Choose Next and attach a permissions policy that grants s3:GetObject, s3:PutObject, and s3:ListBucket on your target bucket.选择“下一步”并附加一个权限策略，授予对目标存储桶的 s3:GetObject、s3:PutObject 和 s3:ListBucket 权限。
5. Name the role (for example, QuickAutomate-S3-Role) and choose Create role.为该角色命名（例如 QuickAutomate-S3-Role），然后选择“创建角色”。
6. Copy the role Amazon Resource Name (ARN). You will need it when configuring the S3 connector.复制该角色的 Amazon 资源名称 (ARN)。在配置 S3 连接器时，您将需要用到它。

With the IAM role created and the role ARN copied, you’re ready to configure the connection between Amazon Quick Automate and your S3 bucket.创建好 IAM 角色并复制角色 ARN 后，您就可以配置 Amazon Quick Automate 与您的 S3 存储桶之间的连接了。

Set up the S3 connector设置 S3 连接器

After prerequisites are confirmed, configure the S3 connector in the Amazon Quick console.确认先决条件后，在 Amazon Quick 控制台中配置 S3 连接器。

1. In the Amazon Quick console, choose the user icon in the upper-right corner.在 Amazon Quick 控制台中，选择右上角的用户图标。
2. Open Manage Account, then go to Permissions > AWS Actions.打开“管理账户”，然后转到“权限”>“AWS 操作”。

Figure 2: AWS Actions page in the Amazon Quick console图 2：Amazon Quick 控制台中的“AWS 操作”页面

3. Choose New action, then select Amazon S3.选择“新建操作”，然后选择“Amazon S3”。
4. Configure the connector:配置连接器：

• Enter a connector name (for example, ExampleBucket-S3-Connection) and a description.输入连接器名称（例如 ExampleBucket-S3-Connection）和描述。
• Paste the ARN of the IAM role you created in the prerequisites step.粘贴您在先决条件步骤中创建的 IAM 角色的 ARN。

Figure 3: Amazon S3 action connector configuration图 3：Amazon S3 操作连接器配置

5. The console validates the role trust policy automatically. Confirm that the status shows a successful connection.控制台会自动验证角色信任策略。确认状态显示连接成功。
6. Share the connector with users and groups who build and run workflows.与构建和运行工作流程的用户及组共享该连接器。

Create an automation group创建自动化组

1. In the Amazon Quick console, go to Automations > Create Group.在 Amazon Quick 控制台中，转到“自动化”>“创建组”。

Figure 4: Create Group option on the Automations page图 4：“自动化”页面上的“创建组”选项

2. Name the group (for example, RFI-Processing-Group).为组命名（例如 RFI-Processing-Group）。
3. On the Add actions page, select the Amazon S3 connection you created earlier, then choose Next.在“添加操作”页面上，选择您之前创建的 Amazon S3 连接，然后选择“下一步”。

Figure 5: Selecting Amazon S3 for the automation group图 5：为自动化组选择 Amazon S3

With the connector and the automation group configured, create the automation project that will hold your workflow.配置好连接器和自动化组后，创建将容纳您的工作流程的自动化项目。

Create an automation project创建自动化项目

The automation project is where you describe your processing logic and where the generated workflow lives.自动化项目是您描述处理逻辑并存放生成的工作流程的地方。

1. On the Automations page, choose the Projects tab, then choose Create Project.在“自动化”页面上，选择“项目”选项卡，然后选择“创建项目”。
2. In Provide project details, enter a name for the project, select the automation group you created, and optionally add a description and upload existing documentation.在“提供项目详细信息”中，输入项目名称，选择您创建的自动化组，并可选择添加描述和上传现有文档。
3. Choose Next: Business case.选择“下一步：业务案例”。
4. The business case section is optional and is used for tracking return on investment. To complete it, enter hours saved per case, cases per year, project priority, and a target launch date.业务案例部分是可选的，用于跟踪投资回报率。要完成该部分，请输入每个案例节省的小时数、每年案例数、项目优先级和目标发布日期。
5. Choose Create.选择“创建”。

Your project opens on a summary page with Summary, Versions, and Deployments tabs, and a status panel showing the current state of the project.您的项目将在摘要页面打开，其中包含“摘要”、“版本”和“部署”选项卡，以及显示当前项目状态的状态面板。

With the connector, the automation group, and the project in place, you are ready to describe your workflow logic.连接器、自动化组和项目就绪后，您就可以描述工作流程逻辑了。

Describe the processing logic in natural language用自然语言描述处理逻辑

In Amazon Quick Automate, you describe what the automation should do using natural language. You can type directly into the prompt area or upload a file with your requirements. The AI assistant interprets your instructions and generates executable workflow steps.在 Amazon Quick Automate 中，您可以使用自然语言描述自动化应执行的操作。您可以直接在提示区域输入，或上传包含需求的文件。AI 助手会解读您的指令并生成可执行的工作流程步骤。

Step 1: Connect to S3 and read a sheet第 1 步：连接到 S3 并读取工作表

In the automation project, you see a text area where you describe your processing requirements. Enter a prompt that covers the data source, transformation logic, and the output you want. For example:在自动化项目中，您会看到一个用于描述处理需求的文本区域。输入涵盖数据源、转换逻辑以及您想要的输出的提示。例如：

“Connect to my S3 bucket using the ExampleBucket-S3-Connection connector. Read the file SampleDepartment_Version2.xlsx from the sample-folder prefix. Open the Strategy sheet and extract all survey questions. Identify main questions and subquestions based on numbering and indentation. Structure the data with columns for Serial Number, Category, Question, and Response Type. Write the output as a CSV file to the output-folder prefix in the same bucket.”“使用 ExampleBucket-S3-Connection 连接器连接到我的 S3 存储桶。从 sample-folder 前缀读取文件 SampleDepartment_Version2.xlsx。打开 Strategy 工作表并提取所有调查问题。根据编号和缩进识别主要问题和子问题。将数据结构化，包含序列号、类别、问题和响应类型列。将输出作为 CSV 文件写入同一存储桶中的 output-folder 前缀。”

Figure 6: Entering the processing prompt in the automation project图 6：在自动化项目中输入处理提示

Step 2: Review the generated workflow第 2 步：审查生成的工作流程

After you submit the prompt, the AI assistant generates a multi-step workflow. Each step maps to a part of your instructions:提交提示后，AI 助手会生成一个多步骤的工作流程。每个步骤都对应您指令的一部分：

1. Read data – Connects to S3, downloads the workbook, and reads the target sheet with headers.读取数据 – 连接到 S3，下载工作簿，并读取带有标题的目标工作表。
2. Extract and transform – Identifies main questions and subquestions by numbering and indentation, and pulls category metadata from column headers.提取和转换 – 通过编号和缩进识别主要问题和子问题，并从列标题中提取类别元数据。
3. Structure output – Converts subquestions into standalone records by merging parent context. Defines the output schema.结构化输出 – 通过合并父上下文将子问题转换为独立记录。定义输出架构。
4. Write results – Saves structured output as a CSV file to the specified S3 location.写入结果 – 将结构化输出保存为 CSV 文件到指定的 S3 位置。

Figure 7: Generated multi-step workflow图 7：生成的多步骤工作流程

Because the AI assistant relies on generative AI, the exact steps and wording it produces might vary between runs. The workflow you see might differ slightly from this example, but it covers the same logical operations based on your instructions.由于 AI 助手依赖于生成式 AI，它产生的具体步骤和措辞在不同运行之间可能会有所不同。您看到的工作流程可能与此示例略有差异，但它涵盖了基于您指令的相同逻辑操作。

Step 3: Run and validate第 3 步：运行并验证

Choose Run to execute the workflow against your workbook. Review the output to confirm:选择“运行”以针对您的工作簿执行工作流程。检查输出以确认：

1. All questions are extracted (main and subquestions).所有问题均已提取（主要问题和子问题）。
2. Category text matches the source column headers exactly.类别文本与源列标题完全匹配。
3. Subquestions include parent context.子问题包含父上下文。
4. Response types are preserved as-is from the source.响应类型按原样从源中保留。

Figure 8: Workflow run output图 8：工作流程运行输出

Refine the workflow through conversation通过对话优化工作流程

When the output needs improvement, use the conversation interface to request targeted changes. Reference the specific step and describe the expected behavior.当输出需要改进时，请使用对话界面请求针对性的更改。引用特定步骤并描述预期的行为。

Example refinement prompts:优化提示示例：

1. “The step that reads the Strategy sheet should also capture column headers as metadata.”.“读取 Strategy 工作表的步骤也应捕获列标题作为元数据。”
2. “The category field does not match source headers. Update extraction to use exact header text.”.“类别字段与源标题不匹配。更新提取逻辑以使用精确的标题文本。”
3. “In the subquestion transformation step, merge parent context into the question text.”.“在子问题转换步骤中，将父上下文合并到问题文本中。”

Follow this iterative cycle:遵循此迭代周期：

1. Identify the issue – Compare output against your expected results.识别问题 – 将输出与预期结果进行比较。
2. Request a targeted update – Describe the change in natural language, referencing the specific step.请求针对性更新 – 用自然语言描述更改，并引用特定步骤。
3. Review the updated workflow – The AI assistant modifies the relevant step and shows you the change.审查更新后的工作流程 – AI 助手会修改相关步骤并向您展示更改。
4. Re-run and validate – Execute again and confirm the fix.重新运行并验证 – 再次执行并确认修复情况。

Best practices最佳实践

Before promoting your automation to production, follow these best practices:在将自动化推广到生产环境之前，请遵循以下最佳实践：

1. Validate incrementally – Run and check output after each refinement, rather than batching multiple changes.增量验证 – 在每次优化后运行并检查输出，而不是批量处理多个更改。
2. Handle edge cases explicitly – Describe how the workflow should behave when data is missing, duplicated, or formatted inconsistently.明确处理边缘情况 – 描述当数据丢失、重复或格式不一致时，工作流程应如何表现。

Promote automations with Import/Export使用导入/导出推广自动化

Amazon Quick Automate Import/Export supports controlled promotion from pre-production to production and consistent reuse across AWS Regions.Amazon Quick Automate 导入/导出支持从预生产到生产的受控推广，以及跨 AWS 区域的一致性复用。

Export a version导出版本

1. Open the source automation.打开源自动化项目。
2. Go to Versions.转到“版本”。
3. Choose Export version for the validated release.为已验证的版本选择“导出版本”。

Figure 9: Exporting a validated automation version图 9：导出已验证的自动化版本

4. Copy the generated version link.复制生成的版本链接。

Note: The export link expires after a set period. Copy and use it promptly, or generate a new link if it has expired.注意：导出链接会在一段时间后过期。请及时复制并使用，如果过期，请生成新链接。

Figure 10: Generated export version link图 10：生成的导出版本链接

Import a version导入版本

1. Open or create an Amazon Quick Automate project in the destination account or AWS Region.在目标账户或 AWS 区域中打开或创建一个 Amazon Quick Automate 项目。
2. Choose Import version.选择“导入版本”。
3. Paste the version link and choose Start.粘贴版本链接并选择“开始”。
4. Review version details and complete the import.查看版本详情并完成导入。

Figure 11: Importing an automation version图 11：导入自动化版本

5. Configure required connectors, credentials, and deployment settings in the target environment.在目标环境中配置所需的连接器、凭证和部署设置。

Figure 12: Configuring the target environment after import图 12：导入后配置目标环境

Clean up清理

1. Delete the automation project and the automation group.删除自动化项目和自动化组。
2. Remove the S3 connector if no other workflows use it.如果没有其他工作流程使用 S3 连接器，请将其删除。
3. Delete test IAM roles and test S3 objects when no longer required.在不再需要时，删除测试 IAM 角色和测试 S3 对象。

For detailed cleanup guidance, see Using Amazon Quick Automate.有关详细的清理指南，请参阅使用 Amazon Quick Automate。

Conclusion结论

In this post, you built an end-to-end automation for processing RFI questionnaires stored as multi-tab Excel workbooks using Amazon Quick Automate. You connected your data through an Amazon S3 action connector, described your processing logic in natural language, refined the automation through conversation, and promoted it across AWS accounts and Regions using Import/Export.在本文中，您使用 Amazon Quick Automate 构建了一个端到端的自动化流程，用于处理存储为多标签 Excel 工作簿的 RFI 问卷。您通过 Amazon S3 操作连接器连接了数据，用自然语言描述了处理逻辑，通过对话优化了自动化流程，并使用导入/导出功能将其推广到各个 AWS 账户和区域。

You can extend this approach to other business workflows, such as:您可以将此方法扩展到其他业务工作流程，例如：

1. Intelligent document processing (IDP) – Extract structured data from invoices, contracts, or forms.智能文档处理 (IDP) – 从发票、合同或表格中提取结构化数据。
2. Report consolidation – Merge multi-sheet financial reports into a unified dataset.报告合并 – 将多工作表财务报告合并为统一的数据集。
3. UI automation – Automate repetitive browser-based tasks that feed into downstream analytics.UI 自动化 – 自动化重复的基于浏览器的任务，并将结果输入到下游分析中。
4. Survey data aggregation – Consolidate survey responses from multiple sources into a single output.调查数据聚合 – 将来自多个来源的调查回复汇总为单一输出。

For more on automation capabilities, action connectors, and natural-language workflows, see the Amazon Quick documentation. Visit Getting started with Amazon Quick to start using Amazon Quick Automate today.有关自动化功能、操作连接器和自然语言工作流程的更多信息，请参阅 Amazon Quick 文档。访问 Amazon Quick 入门，立即开始使用 Amazon Quick Automate。

About the authors关于作者