As a subset within User Experience, Conversation Design considers not only how your customers will interact with your messaging or voice bot, but also what happens behind the scenes to make their experience frictionless, conversational, and intuitive.
As you begin on your conversation design journey, keep these best practices and principles in mind:
Design natural, intuitive conversations
- Understand and implement the rules of Turn-taking, Reciprocity, and the Cooperative Principle.
- Note: Most conversational use cases require that your bot assumes the onus of progressing the conversation, rather than the user. This is particularly important when leveraging generative AI.
- In general, conversational copy should be brief, and low cognitive load.
- Use progressive disclosure. Provide “just enough” information for the conversational turn.
- Re-adapt long website FAQ copy for conversational interfaces.
- Be mindful of channel-specific actions, like “click” or “tap.” Replace with “choose” or “select.”
- For voicebots, follow the “rule of 3” when listing choices, and end your dialog turns with a direct question or call to action. Voice commands should be simple and intuitive.
- Determine if you will use NLU, Generative AI, or both to power your conversational AI’s understanding.
- Plan for how you will handle small talk and other conversational situations and commands:
- Hi, hello
- Thank you, thanks
- Are you a human?
- Can you repeat that? Come again?
- Go back, main menu, start over
- End, Close, Stop
- Agent, I want to speak to a human
- Hold on, wait
- Situations:
- Are there any highly sensitive topics you will auto-escalate to a human immediately?
- How will you handle repetitive abusive sentiment or pranksters?
- Inactivity / Abandonment
- Be on the lookout for any potential looping that could occur in your conversation design, and remove it.
- Check that error messages are written in a helpful manner, enabling users to progress and get back on track.
Set clear expectations & bot-to-human handoffs
- Define a welcome experience that introduces your virtual assistant and set expectations of what it can and can’t handle. Do not pretend to be a human.
- Decide how you’ll handle after-hours escalations when agents aren’t online.
- Determine when you’ll offer a Post-Conversation Survey. Will you ask the same questions for bot only vs agent-handled conversations?
- Determine how and where you’ll close and end the conversation.
- Have a plan for Fallbacks and EscalationsDesign fallback and reprompt strategies to handle unrecognized inputs, api errors, and long processing times.
- Plan for escalation to human agents when a query cannot be resolved or needs further assistance to complete.
Decide when you will auto-escalate vs. asking the user to confirm before escalation.
Design with context
Consider how your design will adapt to context across these five areas:
- User
- Conversation
- Bot
- Situational
- Global contexts
Simplicity over complexity
- When writing dialog copy, consider your customer’s mental model.
- Remember that customers may not be familiar with the terminology of your business.
- Avoid jargon and acronyms.
- Use similar words and phrases that your customer does, especially when designing menus, phrasing dialog prompts, and building out intents and training phrases in Intent Manager.
- In Conversation Builder, leverage dialogs as reusable components. Don’t create duplications of the same dialog. Organize your flows in conversation builder with a numbering and naming system. (ie: 0- Welcome, 1.0 Main Menu, etc)
Finally, don’t forget to….
- Identify team members responsible for conversation design and development work
- Ensure proper stakeholders across your company are involved and aligned with your conversation design strategy. Conversation designers often must collaborate with Product, Engineering, Contact Center teams, Operations, and Marketing.