您是否曾經想暫停自動工作流程以等待人類的決定？

也許您需要在提供雲資源，將機器學習模型推廣到生產或收取客戶的信用卡之前需要批准。

Have you ever wanted to pause an automated workflow to wait for a human decision? Maybe you need approval before provisioning cloud resources, promoting a machine learning model to production, or charging a customer’s credit card.

您是否曾經想暫停自動工作流程以等待人類的決定？也許您需要在提供雲資源，將機器學習模型推廣到生產或收取客戶的信用卡之前需要批准。

In many data science and machine learning workflows, automation gets you 90% of the way — but that critical last step often needs human judgment. Especially in production environments, model retraining, anomaly overrides, or large data movements require careful human review to avoid expensive mistakes.

在許多數據科學和機器學習工作流程中，自動化為您帶來了90％的途徑 - 但是關鍵的最後一步通常需要人類的判斷。尤其是在生產環境中，模型再培訓，異常覆蓋或大型數據移動需要仔細的人類審查，以避免昂貴的錯誤。

In my case, I needed to manually review situations where my system flagged more than 6% of customer data for anomalies — often due to accidental pushes by customers. Before I implemented a proper workflow, this was handled informally: developers would directly update production databases (!) — risky, error-prone, and unscalable.

就我而言，我需要手動查看我的系統標記超過6％的客戶數據異常數據的情況 - 通常是由於客戶意外推動。在我實施適當的工作流程之前，這是非正式處理的：開發人員將直接更新生產數據庫（！） - 風險，容易出錯且不計。

To solve this, I built a scalable manual approval system using AWS Step Functions, Slack, Lambda, and SNS — a cloud-native, low-cost architecture that cleanly paused workflows for human approvals without spinning up idle compute.

為了解決這個問題，我使用AWS步驟功能，Slack，Lambda和SNS建立了一個可擴展的手動批准系統，這是一種雲本地，低成本的體系結構，可干淨地暫停人工批准的工作流，而無需旋轉閒置計算。

In this post, I’ll walk you through the full design, the AWS resources involved, and how you can apply it to your critical workflows.

在這篇文章中，我將帶您完成完整的設計，所涉及的AWS資源以及如何將其應用於關鍵工作流程。

Let’s get into it 👇

讓我們來👇

The Solution

解決方案

My application is deployed in the AWS ecosystem, so we’ll use Aws Step Functions to build a state machine that:

我的應用程序已部署在AWS生態系統中，因此我們將使用AWS步驟函數來構建一台狀態計算機：

Here is a youtube video showing the demo and actual application in action:

這是一個YouTube視頻，顯示了演示和實際應用程序：

I have also hosted the live demo app here →👉 https://v0-manual-review-app-fwtjca.vercel.app

我還在這里托管了實時演示應用→👉https://v0-manual-review-app-fwtjca.vercel.app

All code is hosted here with the right set of IAM permissions.

所有代碼均在此處託管，其中包含正確的IAM權限。

Step-by-Step Implementation

分步實現

The flow above generates a dataset, uploads it to AWS S3 and if a review is required, then invokes the Manual Review lambda. On the manual review step, we’ll use a Task lambda with an invoke on WaitForTaskToken, which pauses execution until resumed. The lambda reads the token this way:

上面的流量生成數據集，將其上傳到AWS S3，如果需要進行審查，請調用手動評論lambda。在手動審核步驟中，我們將使用一個任務lambda和WaitfortaskToken的Invoke，該任務停止執行直至恢復。 Lambda以這種方式讀取令牌：

This Lambda sends a Slack message that includes the task token so the function knows what execution to resume.

此lambda發送了一個休閒消息，其中包含任務令牌，因此該函數知道要恢復執行什麼。

2. Before the we send out the slack notification, we need to

2。在我們發送鬆弛通知之前，我們需要

I followed the youtube video here for my setup.

我在此處遵循YouTube視頻進行設置。

3. Once the above is setup, setup the variables into the web-hook step of the slack workflow:

3。一旦設置了上述，將變量設置為Slack Workflow的Web-Hook步驟：

And use the variables with a helpful note in the following step:

並在以下步驟中使用有用的說明的變量：

The final workflow will look like this:

最終的工作流程看起來像這樣：

4. Send a Slack Notification published to an SNS topic (you can alternately use slack-sdk as well) with job parameters. Here is what the message will look like:

4.將發布的Slack通知發送到SNS主題（您也可以使用Slack-SDK）與作業參數一起發送。這是消息的樣子：

This Lambda sends a Slack message that includes the task token so the function knows what execution to resume.

此lambda發送了一個休閒消息，其中包含任務令牌，因此該函數知道要恢復執行什麼。

5. Once a review notification is received in slack, the user can approve or reject it. The step function goes into a wait state until it receives a user response; however the task part is set to expire in 24 hours, so inactivity will timeout the step function.

5。一旦在Slack收到審核通知後，用戶就可以批准或拒絕。步驟功能進入等待狀態，直到它收到用戶響應為止；但是，任務零件設置為24小時內到期，因此不活動將超時該步驟功能。

Based on whether the user approves or rejects the review request, the rawPath gets set and can be parsed here: code

根據用戶是批准還是拒絕審核請求，將設置RAWPATH並可以在此處解析：代碼

The receiving API Gateway + Lambda combo:

接收API網關 + lambda組合：

Example:

例子：

Note: Lambda configured with WaitForTaskToken must wait. If you don’t send the token, your workflow just stalls.

注意：用WaitfortaskToken配置的Lambda必須等待。如果您不發送令牌，那麼您的工作流程只是失速。

Bonus: If you need email or SMS alerts, use SNS to notify a broader group.Just sns.publish() from within your Lambda or Step Function.

獎勵：如果您需要電子郵件或SMS警報，請使用SNS通知更廣泛的組。 just sns.publish（）從您的lambda或step函數中。

Testing

測試

Once the manual approval system was wired up, it was time to kick the tires. Here’s how I tested it:

手動批准系統連接起來後，就該踢輪胎了。這是我測試的方式：

I tested all major paths:

我測試了所有主要途徑：

Behind the scenes, I also verified that :

在幕後，我還驗證了：

I highly recommend testing not just happy paths, but also “what if nobody clicks?” and “what if Slack glitches?” — catching these edge cases early saved me headaches later.

我強烈建議您不僅要測試快樂的道路，還建議“如果沒人點擊怎麼辦？”和“如果鬆弛的故障怎麼辦？” - 儘早抓住這些邊緣案件使我頭痛。

Lessons Learned

經驗教訓

Wrapping Up

總結

Adding human-in-the-loop logic doesn’t have to mean duct tape and cron jobs. With Step Functions + Slack, you can build reviewable, traceable, and production-safe approval flows.

添加人類的邏輯並不一定意味著膠帶和Cron工作。使用步驟功能 + Slack，您可以構建可審查，可追溯和生產安全的批准流。

If this helped, or you’re trying something similar, drop a note in the comments! Let’s build better workflows.

如果這有所幫助，或者您正在嘗試類似的事情，請在評論中放下註釋！讓我們構建更好的工作流程。

Note: All images in this article were created by the author

注意：本文中的所有圖像均由作者創建