In recent years, chatbots have become increasingly prevalent in various business domains, providing services such as booking flights, making hotel reservations, and scheduling appointments. These systems, known as task-oriented chatbots, initiate a conversation to collect the necessary data and subsequently invoke a specific web service to complete the task. Traditionally, they operate on the basis of predefined rules or are trained with specific task data. While effective, this approach is often rigid and lacks adaptability to the evolving peculiarities of individual businesses. For instance, a chatbot designed for general restaurant reservations will request common data such as the number of diners or reservation time, but may fail to accommodate specific preferences such as terrace seating, buffet options, or karaoke availability. To address the limitations of traditional task-oriented chatbots, we propose an innovative approach leveraging generative AI and a novel service specification concept called PPTalk. This approach enables chatbots to dynamically introduce business-specific elements into conversations, enhancing their adaptability to the unique characteristics of each business. We have developed a proof of concept to demonstrate the feasibility and effectiveness of our proposal, obtaining highly positive results.