When completing a task on a device with a screen, you can often understand your possible actions in a single glance. If there's a form asking for your city, state, and zip code, for example, you have a pretty good idea of what information you’ll need to provide.
In contrast, voice is an open-ended medium. When speaking with someone, you have the tools and capacity to move the topic in almost any direction. What starts out as a chat about the local weather can end in a discussion about restaurants in Lyon, France, or your favorite brands of toothpaste. Complicating matters further, usually the exact flow of conversation is unknown to the participants until the conversation is drawing to an end. There's no way to “look ahead” in a conversational experience to know for sure what information the other participant will share or request.
As a result, you can know that users of your skill will most definitely say something you don't expect. Your job, then, is to prepare conversational design elements to react well to unexpected user interactions based on what types of things you think your skill's particular users are likely to say.
Clearly it doesn't make sense for your “restaurant finder” Alexa skill to talk about the types of food in the French countryside, but you'll need to account for the possibility that a user who is super interested in French food might, given the open-ended nature of conversation, head in that direction. To prevent frustration when a user asks for something your skill isn't specifically designed to provide, you'll need to do some looking ahead of your own.
Understanding who your users are and what they want is fundamental to providing a great voice experience.
Realistically, user research should be conducted throughout the lifecycle of your skill. Over time you'll be able to gather information on how user behaviors, needs, and motivations can be used to improve your voice experience, ensuring that design decisions are beneficial. Learn more about how you can do user research and use skill analytics to make enhancements with tools available in the Alexa Developer Console.
In the new Designing for Conversation course, we outline a method for identifying users via user personas when initially designing a skill. Using the method outlined in the course, you'll develop an array of personas and leverage them to bring to light situations where your initial design doesn't work and needs adjustment. You'll learn to recognize and plan for times when the user says something completely unexpected.
Plan ahead and make sure that when your users take the conversation off the rails, you're able to keep them engaged and enjoying the experience.
The Alexa Skills Kit provides developers and voice designers with an opportunity to take advantage of the latest breakthroughs in Alexa's understanding of conversation through advanced features and patterns like dialog management, context switching, conditional slot collection, and memory.
To help you learn how identifying your users can help you plan for the unexpected, check out our free, self-paced online course called Designing for Conversation. Browse over today and get started coming up with the next big idea for voice.
Bring your big idea to life with Alexa and earn perks through our milestone-based developer promotion. US developers, publish your first Alexa skill and earn a custom Alexa developer t-shirt. Publish a skill for Alexa-enabled devices with screens and earn an Echo Spot. Publish a skill using the Gadgets Skill API and earn a 2-pack of Echo Buttons. If you're not in the US, check out our promotions in Canada, the UK, Germany, Japan, France, Australia, and India. Learn more about our promotion and start building today.