Learn How to Prioritize Inbound Requests Thanks to ChatGPT

Introduction

In this tutorial, we’ll dive into the powerful world of customer support optimization by harnessing the synergy of Pingstreams Generative AI Chatbot Development and the integration capabilities of ChatGPT by OpenAI. Learn how to tag inbound customer requests and define their priority levels, all with the help of cutting-edge AI technology. Let’s begin!

Step 1: Prepare Your Use Case and Attributes and Create a GPT Task Block

To generate pertinent responses using GPT, you need to define a prompt that instructs GPT on how to generate an answer based on the customer’s feedback. Before you start, it’s essential to have a clear use case in mind. For example, let’s say you want to create a bot that handles support requests based on their urgency or priority.

In the DefaultFallback block, choose the GPT Task action. Assign an attribute to the GPT response as well as the last user’s text. You can create a custom attribute (e.g., “gpt_reply”, “last_user_text”) to intercept the generated response by ChatGPT based on what the user has told you last.

Consider the context of your chatbot. If your use case involves support requests, you might use a prompt like:

"Analyze an incoming customer request via live chat to determine its priority. If the priority is high, you can answer 'high', otherwise 'low'"

Step 2: Set the Max Number of Tokens

Decide the maximum number of tokens you want the GPT response to have. Tokens are chunks of text, and limiting their number can help control the length of the generated responses.

For example:

• If you want concise responses, you might set the max number of tokens to 50
• If you want more detailed responses, you can set it to a higher value, like 150

Step 3: Set Up a Condition with GPT Attribute

Once you’ve configured your GPT Task block, add a “Condition” action below to generate the response based on the set condition.

To set the “Condition”, configure the “gpt_reply” attribute to: “contains Ignore Case” and in the value field insert the word “high”.

This way, if the GPT answer is “high”, it will trigger the appropriate flow without displaying the classification to the user.

Step 4: Configure the Urgent + Not Urgent Blocks

Create an “Urgent” Block

Create a new block called “Urgent” where you can customize your customer service by connecting immediately to a human agent, for example.

Create a “Not Urgent” Block

Create another block for “Low Urgency” where instead you can connect your user’s data and inform them that you’ll look into the issue ASAP.

Flow Logic

• If the condition set up in Step 3 is met (the priority is indeed found to be high by GPT Task), the “Urgent” block will be actioned
• Conversely (or “else”), the conversation will continue to the “Not Urgent” block

Step 5: Test Your Chatbot

Test your chatbot to ensure it generates pertinent responses based on customer feedback:

1. Provide feedback in the chat to see how the GPT-generated response is handled
2. Verify that the response is captured in the “gpt_reply” attribute and processed correctly
3. Confirm that high-priority requests are routed to the urgent flow
4. Ensure low-priority requests follow the standard support flow

Benefits of Automated Request Prioritization

This implementation in Pingstreams allows you to:

• Automatically classify incoming support requests by urgency
• Route high-priority issues directly to human agents
• Streamline support workflows based on request severity
• Improve response times for critical customer issues
• Scale your support operations efficiently

Use Cases for Priority Classification

This system works well for various scenarios:

• Technical emergencies vs. general inquiries
• Billing issues vs. feature questions
• Service outages vs. product feedback
• Urgent account issues vs. general support

Conclusion

You’ve successfully created a chatbot with Pingstreams Design Studio that uses the GPT Task feature to analyze support requests based on user feedback. This can greatly enhance your chatbot’s ability to tag inbound support requests and prioritize the support needed.

This intelligent prioritization system ensures that critical issues receive immediate attention while maintaining efficient handling of routine inquiries, ultimately improving your overall customer support experience.

For more advanced configurations and customization options, explore additional Pingstreams features or contact our support team.