Conversational UX is gaining traction in tandem with rapid advancements in AI tech. It seems intuitive that humans would want to communicate with AI agents or bots as naturally as possible. Nothing about conversational UX is new, of course. We just happen to be at a tipping point where various AI technology trends are pushing it into prominence. Substantial research (https://dl.acm.org/doi/book/10.1145/3304087) and successful application of that research for real-world scenarios over the past decade have made conversational UX ubiquitous and ready for primetime, where the best is yet to come.

Timeline of key events in conversational UX

<infographic>

Amazon Alexa > ChatGPT (groundswell) - Bing chat, Bard

Start of an AI-volution

Gone are the days of drab robotic chatbots for sales and support. The new age of sophisticated applications using generative AI demands that designers dig deep into the art of conversation. This is an exciting time to explore possibilities to make a dialogue between humans and bots, natural, meaningful, fun, and engaging. On the B2B SaaS front, we are just scratching the surface.

With AI infused in all kinds of business process automation, there are a ton of possibilities to make conversational UX a key part of such applications. In fact, it begs a radical question. What if there is no traditional UI layer in enterprise applications? Can business outcomes be achieved through good-old easy-going conversations between humans and AI solely through a chat window with no regular app interface to speak of? How can designers design and orchestrate the creation of these environments? Designers must investigate, for instance, what’s the equivalent of a casual business meeting in a cafe versus a mission-critical exchange in a conference room about budgeting between a CFO and their AI assistant.

At Hyperbots, designers are exploring ways to create a humane, relatable avatar for the powerful AI capabilities of our platform, addressing the automation needs of finance processes like Accounts Payable and Expense Processing for the CFO’s office - processes that are still woefully manual.

The core work that the Hyperbots AI Assistants do will mostly be unseen.

Automating tasks like processing expenses, which today involves accountants manually matching invoices with Purchase Orders (POs) and Goods Received Notes (GRNs), flagging invoices with discrepancies or surfacing out-of-policy employee expenses for review, and routing these through appropriate spans of control in the company for approvals.

In addition to the above, the AI Assistants will;

1. Onboard users via conversation and help them with configuration, setting up workflows, and managing day-to-day tasks with ease.
2. Provide real-time assistance and surface pertinent financial information instantaneously, as against using traditional UI to navigate to the desired content in response to queries.

These two aspects of the user experience are what will form the Conversational UX design charter for the design team at Hyprbots.

Begin here

Designers at Hyprbots know that if they want to create distinct AI Assistant identities, they need to focus beyond visual elements of an avatar or the UI layer of a dialogue box. They must ask the question - what makes a dialogue meaningful? Especially between a machine and a human. They must dive deep into the science of Human-Computer Interaction and the art of conversation.

So far, our secondary design research has pointed to some seminal work already in the public domain, like the recent ethnographic study by NNGroup into usage patterns of ChatGPT, Bing, and Bard users, suggesting there could be 6 different types of conversations with generative AI (https://www.nngroup.com/articles/AI-conversation-types/)

1. Search queries
2. Funneling conversations
3. Exploring conversations
4. Chiseling conversations
5. Expanding conversations
6. Pinpointing conversations

These provide a great basis for brushing up on fundamentals and taking the right first step. What should follow is arriving at a solid hypothesis of what specific approaches might work for ur CFOs and their teams, and then testing these hypotheses with a great amount of rigor.

We are early in our exploration of conversational UX at Hyprbots. We are more than convinced this space cannot remain untapped if we are to create a groundbreaking experience for our customers grappling with legacy applications to conduct their finance operations. Central to the customer experience we want to build for our CFOs and their teams. As they say, watch this space.