Use Agent Builder to create an AI customer support process


This article will show you how to use OpenAI's Agent Builder to create an AI customer support system that connects with your website, automatically routes questions, and generates insightful answers from your documentation. 

Step-by-step: 

Visit platform.openai.com/agent-builder, log in, and then go to the Billing area to add credits to your account. 

Initiate a new workflow by selecting "+ Create" and adding an agent node as a routing agent with the following prompt: "You are a customer support classifier." 

Sort the user's intent into "product_info" or "billing_info," then set up the output by using enum values in structured JSON. Use conditions such as input.output_parsed.classification == "product_info" to connect your routing agent to a conditional block (if-else node). 

Next, establish two specialized agent nodes: one for product information and one for billing support. 

Finally, use the "File Search" tool to upload pertinent documentation. 

To test several situations, such as "How do I use the analytics feature?" or "I was charged twice this month," click preview. 

Then, click publish to obtain a workflow ID for Chatkit integration. 

This routing pattern can also be used for internal help desk systems, lead scoring, or sales qualification; the same structure is applicable anyplace you require specific responses and intelligent categorization.

Your one-stop shop for automation insights and news on artificial intelligence is EngineAi.
Did you like this article? Check out more of our knowledgeable resources:
📰 In-depth analysis and up-to-date AI news
🤝 Visit to learn about our goal and knowledgeable staff

📬 Use this link to share your project or schedule a free consultation

Watch this space for weekly updates on digital transformation, process automation, and machine learning. Let us assist you in bringing the future into your company right now