Use Alibaba Cloud Model Studio and Chat App Message Service to build a WhatsApp chatbot based on your enterprise knowledge base. This enables 24/7 intelligent customer service or sales guidance. This tutorial guides you through the entire no-code configuration process.
Related policies
Starting January 15, 2026, Meta will prohibit the deployment of general-purpose AI chatbots on the WhatsApp Business Platform (API). This policy applies to new API users starting October 15, 2025. For more details, see WhatsApp's 2026 AI policy explained.
Before you begin
Prepare your enterprise knowledge base files. These files serve as the knowledge source for the large language model (LLM) application. You can use unstructured data files, such as DOC, PDF, MD, or TXT, or structured data files, such as XLSX or XLS.
Enterprise knowledge base files:
File type | Description | Example |
Unstructured data file | Document-type files, suitable for systematic knowledge input. These can be complete documents such as product manuals, technical guides, or operating instructions. The system processes these files to extract information and answer detailed user queries. Supported formats include DOC, PDF, MD, and TXT. |
|
Structured data file | Q&A-type knowledge files, suitable for direct, single-point responses. These files consist of predefined question-and-answer pairs. They are ideal for providing quick and specific answers. The system directly uses these pairs to respond to user queries. Supported formats include XLSX and XLS. |
|
Procedure
Step 1: Build a private Q&A application
For detailed steps, see Build a Q&A application with zero code.
You can replace the default prompt with the following:
You are an expert in handling Chat Flow product inquiries, specifically responding to customer questions about the product's functionality. Do not answer questions from other domains.
Please provide concise and competent answers based on the provided knowledge base. Keep each response under 600 characters and insert emojis where appropriate to soften the tone.
Step 2: Configure the flow in Chat App Message Service or the CPaaS platform
Before you begin
Register an Alibaba Cloud account, complete enterprise identity verification, and activate Chat App Message Service.
Register a WhatsApp Business Account (WABA). Bind the approved account and add business numbers to the channel.
The CPaaS platform is ideal for service providers, as it simplifies management and distribution. For more information, refer to CPaaS platform.
Chat App Message Service
In Chat App Message Service, you use Chat Flow to implement multi-turn dialogue with an LLM.
Log on to the Chat App Message Service console. On the Chat Flow page, click the View Template tab, then select Multi-turn dialogue with large language models (LLM).
CPaaS platform
On the CPaaS platform, you use Chat Flow to manage handoffs between the automated chatbot and a human agent.
Log on to the CPaaS platform. On the Chat Flow page, click the View Template tab, select Customer service with large language models and human agents.
The following steps apply to both Chat App Message Service and the CPaaS platform:
In the flow editor canvas, find the Generate Reply from LLM by Previous User Input component.
In the right-side configuration pane, set the Implementation Type to Application. If you are using Alibaba Cloud Model Studio China site, set the protocol to Dashscope. For the International site, set the protocol to Dashscope (International). Then, specify the API key (apiKey) and application ID (appId). Click Create Flow.
NoteTo create or obtain an API key, refer to Create an API key.
To get the ID of your Q&A application, refer to Get Application ID.
Step 3: Publish the chat flow
After you create the chat flow, click Save and Publish, then click Bind and Launch.
In the Bind Account dialog box, select your WABA and mobile number.
Your WhatsApp AI chatbot is ready to provide service now.
