Episode 2: Beyond the bot: How conversational AI is redefining business communication

Paula Rivera: Welcome to The AI Factor, where we decode the power of artificial intelligence for the real world of business. I’m Paula Rivera, and today we’re diving into the world of conversational AI, what it is, how it’s evolved from the clunky chatbots of the past, and what it means for the future of customer engagement.

Joining us today is Drew Popham, a seasoned solutions engineer who works directly with organizations deploying these technologies. Whether you’re new to AI or already experimenting with it, this episode will give you a fresh perspective and maybe a few laughs along the way.

Drew, welcome.

Drew Popham: Thank you so much. I like being called seasoned versus senior as a solutions engineer. Seasoned is a nice way to put it. I appreciate that.

Paula Rivera: Well, you’re very welcome. That was a bit of a tongue twister, I have to admit.

So in a recent experiment, an AI model was trained on Shakespearean, rewrote modern movies in verse. Think The Fast and the Furious as a Shakespearean drama. If you could have AI rewrite any business tool or workplace process in the style of a Shakespearean play, what would you pick and why?

Drew Popham: That’s a good question. I’d probably go with making my email generation. I’d like to be able to have my email responses go out and be much more eloquent and just dramatic in the style of Shakespeare, I would say. So, doth thee share your use cases?

Paula Rivera: Oh, I love it. I love it.

Let’s dive on in. We’re going to rewind the clock a bit, and before we had AI that could schedule appointments or hold a natural conversation in a Shakespearean style, we had Clippy, rules-based chatbots. Let’s discuss how we got from basic bots to intelligent agents. Can you tell us, Drew, how did chatbots first emerge in the business world?

Drew Popham: Well, I think before we even get to chatbots, we might have to explain to younger people who and what Clippy was. Chatbots really started out being a simple, rules-based system for question and answer, right? So it was really out there to just answer FAQs, handle customer support, assist with any technical questions, and it came with a set of preset responses. So it was something where it asked you if you needed help, you had to enter in what you needed help with. If one of your words or phrases matched something in part of their text, it fed you that information. It was pretty hit or miss on what you would get back and what kind of success, but that was really the beginning.

Paula Rivera: That’s super interesting. Give us a snapshot about how chatbot technology has evolved over the years.

Drew Popham: Sure. Chatbots started with simple rules but eventually evolved with advancements in natural language processing. They can now generate responses based on context, making for a more human-like experience. We’ve come all the way up to today with ChatGPT and other large language models.

Paula Rivera: It’s interesting that you say, “Giving the model more knowledge.” Would you agree that models need to be trained with high-quality data?

Drew Popham: Yes, “garbage in, garbage out” is very true. Models need accurate data to avoid biases and enhance their effectiveness. As models become more specialized, we will likely see cleaner outputs and reduced bias.

Paula Rivera: The term chatbot and conversational AI are often interchangeable, but they’re not the same, right? What sets conversational AI apart from traditional chatbots?

Drew Popham: Chatbots operate on predefined rules and lack context understanding, while conversational AI uses generative AI to create dynamic responses based on the conversation's context. This leads to a higher user acceptance as it can process ambiguous queries better than traditional chatbots.

Paula Rivera: How does conversational AI adapt across channels like voice and chat?

Drew Popham: Different channels require different handling; voice utilizes speech recognition while text-based communications focus on accuracy and context. The quality of response and speed varies across these channels.

Paula Rivera: Can AI systems improve response times during interactions?

Drew Popham: Yes, we are striving for real-time interactions and aim for under three-second response times, especially in voice interactions, while ensuring natural conversation flow.

Paula Rivera: You mentioned integrating emotions into AI interactions. Can AI detect a caller's frustration?

Drew Popham: Yes, sentiment analysis allows AI to interpret emotions based on spoken words or changes in tone, and strategies can be implemented to escalate frustrated callers to a human representative.

Paula Rivera: What platforms and tools are leading the way in conversational AI right now?

Drew Popham: We primarily use OpenAI models but are open to other platforms. The right model depends on specific use cases and customer needs. There are also various small language models being developed for specific tasks.

Paula Rivera: What’s important when integrating AI with existing systems?

Drew Popham: Integration strategies often depend on use cases, and we typically integrate via REST API, allowing seamless access to data needed for effective AI interactions.

Paula Rivera: Can you give examples of common use cases you've encountered?

Drew Popham: Common use cases include “pay my bill” or checking order statuses. Organizations often need AIs capable of handling multistep interactions to improve efficiency.

Paula Rivera: Measuring success with conversational AI typically involves efficiency, customer experience, and revenue growth metrics. Could you share a success story?

Drew Popham: One success story involved a national pizza chain where we improved AI understanding by adding training for common phrases used regionally, boosting successful order placements.

Paula Rivera: How are organizations infusing personality into their AIs?

Drew Popham: Organizations encourage custom naming and personality traits for their AIs, enhancing user engagement and providing a more relatable experience.

Paula Rivera: Thank you so much, Drew. This conversation has provided great insights into conversational AI's evolving landscape.

About this episode

Diving into the world of conversational AI — what it is, how it’s evolved from the clunky chatbots of the past, and what it means for the future of customer engagement. Speaking with IntelePeer’s Drew Popham, this episode aims to provide insights for those looking to understand how AI is shaping the future of customer experience.