The Conversation Design Institute (CDI) sees Conversational UX not as a technical interface, but as a human-centric design discipline that bridges the gap between technology and natural human communication. We always say: we don’t teach humans to speak to computers, but computers to speak with humans.
So, we define Conversational UX as: the deliberate design of interactions between humans and AI that follows the natural rules of human conversation to achieve a specific goal. It’s about using empathetic design to optimize the agency of the person.
As for which design elements are included in Conversational UX, that depends on which Conversational Interface you are creating.
For us, how successful the "UX" of conversational interfaces is, is determined in large part by effort or friction. If a person has to put considerable effort into a conversation with an AI Agent, the UX has failed.
A successful conversational interaction should feel like a "cooperative" dialogue—following Paul Grice’s Maxims:
And, it’s not just the words. Visual elements, audio styles and even support for gestures can add to a total picture of conversational UX. Successful Conversational UX makes use of every aspect of the Conversational Interface that can help the customer get what they want with as little effort as possible.
Conversational UX language elements will include Design Patterns like a good introduction, clear prompts, the application of turn taking and good error handling.
Visual elements include the design of the chat widget itself, the use of an avatar and the use and design of buttons or carousels. Also, which font and font size, the shape and size of chat bubbles - if any - and the tempo in which text is presented. And more!
All these design elements can contribute to a superior Conversational UX. When designing a Conversational UX, it’s important to familiarize yourself with the possibilities of the interface or platform you are using. For example, if you want to build a Whatsapp chatbot, make sure to investigate how Whatsapp presents buttons or interactive lists.
From a corporate perspective it’s also important to adhere to existing guidelines and style conventions. The Conversational UX should feel like an extension of the brand experience rather than something alien to it.
Specifically for voice based Agents, you will need to focus on audio elements like the voice prosody, cadence, speed and timbre. In other words: does the chosen Agentic voice resonate and help deliver good Conversational UX that matches the customers expectations of the brand?
Designing a clear persona that matches the brand will help you make these design decisions with confidence.
Finally, GenAI capabilities have further increased the scope of Conversational UX. For example the context memory of a GenAI powered agent is itself a powerful Conversational UX element. An Agent is much more capable if it can remember what subject it is talking about with a customer. After all, this allows the interaction to be more naturally conversational, leading to better Conversational UX.
CDI provides comprehensive training, live support, coaching, and consultancy services to empower businesses in developing Conversational AI solutions that adhere to best practices. Our experienced team guides you through every step of the process, ensuring your implementation is efficient, effective, and aligned with industry standards.
With our curated selection of partners, you can trust that you're getting access to the best-in-class solutions that meet your needs and propel your business forward.
Become a PartnerDiscover our courses and certification programs for creating winning AI Assistants and enterprise capabilities. Get started today.
Our seasoned experts help brands to design, build and maintain best-in-class AI assistants. So if you want to hit the ground running or you need help scaling your team, get in touch.