In my previous blog, I talked about what it takes to build a chatbot using GPT-4, including the engineering efforts required and a rough cost and time estimate. Although it is non-trivial to build a practical chatbot solution for real-world applications, with the right tools, one can build a custom chatbot solution quickly to take full advantage of the state-of-the-art large language models (LLMs) like GPT-4.
With the popularity of ChatGPT and more recently AutoGPT, more and more organizations (or individuals) are considering the adoption of a chatbot for their website or proprietary applications (e.g., a learning program website or a mobile healthcare application). The pressing question is: should I build or buy one?
What is "conversational"? By the Merriam-Webster dictionary, conversation is defined as an "oral exchange of sentiments, observations, opinions, or ideas". Because of the exchange, one-on-one conversations are often considered the most effective way for humans to engage with one another.
Companies around the world are constantly evaluating how to best reach and/or serve their customers, exploring ways to better connect with customers, while always keeping a keen eye on the resources needed to do so. Higher education is no different. It too needs to cut through the clutter and create a connection with potential students, and continue to build the relationship even after those students are part of their university environment.