A version of this article has been published by our friends over at CDI Services on their blog.
CDI Services (one of our valued partners) are pioneers in driving business value with conversational AI. We asked them why we still need conversation designers now that generative AI — which allows just about anyone to build a chatbot in minutes, no training or maintenance required — has taken the world by storm. Here’s what they had to say.
What is a conversation designer?
Conversation design is the art of facilitating daily interactions with technology, especially AI assistants like chatbots and voice assistants. Conversation designers are what UX designers were during the rise of web interfaces in the 90s. And you might want to hire some now — since AI and conversational interfaces are shaping up to be the next user-interface paradigm shift.
What makes a successful automated interaction?
You can invest in the best technology available on the market, but still build a chatbot that fails to deliver value to your business and your customers. That’s because building great dialogue flows can be hard (unless you have a world-class team of AI experts on hand to support you — which we just happen to have at Ultimate). Not only do you need to understand what people are saying, but people need to feel understood.
Having conversations is so natural that, as people, we don’t have to think about it. But in reality, there are many unwritten rules that govern our daily exchanges — whether that’s at the coffee shop, in a Zoom meeting, or while chatting with a friend. Only by understanding these rules can we design meaningful automated experiences. That’s where conversation designers comes in.
Watch this on-demand event to learn more about human-centric conversation design.
A conversation designer is someone who leverages their knowledge of language, technology, and human psychology to turn an AI bot into a successful conversational partner. It might not be immediately obvious, but language and psychology are deeply connected. When designing chatbots and voice assistants, this connection shouldn’t be underestimated.
Conversation designers take control of this process. If you design your bot with a clear persona in mind, you increase the chances of winning trust. If done right, customers will happily take your chatbot’s advice, follow its instructions, and — if a mistake does happen — be more forgiving. And it’s good for business too. To give an example, when CDI Services redesigned one of the critical voice journeys for a major Dutch bank, call deflection rates went up by more than 40% simply by following conversation design best practices.
Good design pays off. Literally
CDI Services’ expert, Jasper Klimbie, explains that it's not always about getting customers from A to B as quickly as possible. When providing someone with an explanation, it’s much better to go step-by-step — a technique better known as ‘turn taking’. It prevents the dialogue from being a monologue and gives customers some space to breathe.
“Turn-taking is what we do intuitively, anyhow. So why not incorporate it also in your conversation design?”
- Jasper Klimbie, Creative Director
When designing for turn-taking, it might look like the dialogue becomes longer, but it becomes easier for customers to navigate. And ease-of-use leads to faster resolutions. Breaking down information is much more effective than giving all information at once. When CDI Services carried out user testing with a client, it turned out that this step-by-step approach was rated much higher by almost all testers. Tellingly, none of them were able to accurately report how many steps took place within the conversation. Instead, they simply reported that it was easier.
Conversation designers that know this technique will create dialogues that lead to higher containment, which positively affects your bottom line. Another reason to hire one or two of these conversational pros for your team.
What about generative AI?
Investing in the right people (meaning conversation design experts) is especially important as generative AI-powered chatbots take center stage. This is because working with LLMs can be challenging.
Learn more about the challenges of using LLMs for customer support automation.
Similar to the early first-generation chatbot days, the development of LLM-powered models being led mainly by software engineers. But by relying too much on technology, chatbots can end up over-engineered and lacking a human touch. The solution? Developers should be teaming up with conversation designers to ensure this tech provides an experience your customers will love.
Discover the best practices for building a generative AI bot.
This is something that CDI Services has helped organizations like HP Inc., Johnson & Johnson, Vodafone, Salesforce, and others do. It prepared them for a future in which AI assistants are essential not only for meeting higher customer expectations, but in retaining a competitive edge.