Skip to main content

Configure WeChat Customer Support

Quick configuration enables TCB AI to integrate with WeChat Customer Service and achieve intelligent customer service features.

Prerequisites

Step 1: Obtain the Enterprise ID

Go to the WeChat Customer Service Platform and copy the "Enterprise ID".

Enterprise ID Location

Step 2: Obtain the Token and EncodingAESKey

  1. Go to the "Development Configuration" module in the WeChat Customer Service backend and click "Start Using".

    Start Using

  2. Click "Randomly Obtain" to generate the Token and EncodingAESKey

    Obtain Token

⚠️ Note: Do not click "Complete" at this point. You need to obtain the callback URL in the next step first.

Step 3: Authorize WeChat Customer Service

  1. Go to the TCB AI console and select the Agent module.

  2. Locate the "WeChat Platform" in the "Integration Guide" and select "WeChat Customer Service".

  3. Click "Authorize Immediately", fill in the Token and EncodingAESKey obtained in the previous step, and click "Next".

  4. The system will generate a callback URL. Copy this address.

    WeChat Platform Authorization Portal

  5. Return to the WeChat Customer Service backend, enter the callback URL, and click "Complete".

    Enter Callback URL

  6. Return to the TCB AI console, click "Next", and fill in the Secret and customer service name.

    Enter Secret and Customer Service Name
  7. Click "Complete" to finish the authorization configuration.

📝 Note: Only the customer service corresponding to the filled-in account name will be hosted by AI.

Step 4: Development

After authorization is completed, the Agent needs to be modified to support the WeChat platform message format. Refer to the corresponding development documentation based on your Agent type:

Step 5: Testing

After completing development and deployment, you can test the intelligent customer service feature:

  1. Go to the "Start Integration" module in the WeChat customer service backend.

    Start Integration

  2. Scroll down and select "Integration in App/Web Outside WeChat"

    Select Integration Method

  3. Select the corresponding customer service and click "Generate QR Code" to test

    Generating Test QR Code

  4. Scan the QR code to enter the customer service chat and send a message to test

    Test Result

Notes

After the configuration is completed, do not modify the settings in the "Customer Service" section of the WeChat Customer Service backend, otherwise it will overwrite the current configuration.

Do Not Modify Customer Service Configuration

If the configuration is accidentally overwritten, you can re-enable the customer service in the WeChat Customer Service backend:

Re-enabling Customer Service

Optimization Suggestions

Improve Response Speed

Add the following settings to the Agent prompt to significantly improve response speed:

  • The Agent responds to questions in a minimalist style
  • Simplify complex questions and extract the key information
  • Strictly limit the length and relevance of responses to avoid redundancy
  • Do not output in Markdown format; output plain text directly

⚠️ Note: After changing the prompt, historical conversation records may affect the model's output effectiveness.

Model Selection

  • Recommended: Hunyuan model, DeepSeek V3 (fast response speed)
  • Not recommended: DeepSeek R1 and other deep thinking models (response time is slow)

Better Experience

For a richer conversation experience (such as Markdown rendering and multi-turn conversation display), consider embedding a custom AI conversation page within the web or App.