This high-level view of how to design conversational experiences is the third in a series of linked posts exploring the future of Experience Design and a follow on from the previous post on The Future of Conversational Design. These posts are a work in progress, the next five years is going to see a series of huge changes, many of which are just coming into view and there’s no right answer, so please get involved, add comments, refine my thought, disagree, etc.
The experience and UX design communities have been working with conversational interfaces for some time now. The past 18 months or so have seen the emergence of a range of new approaches and learnings. This post brings some of them together, as well as looking at some higher level themes and best practice that seem to be emerging in conversational design.
Four high level best practice considerations
There are a range of high-level considerations for experience designers working on conversational experiences:
- clearly define the use case and set user expectations
- design for cross-platform experiences
- think ‘beyond’ text and voice
- design personalities
Use Case and User Expectations
As we’ve seen reliability remains a big issue for voice and chatbot users, with fail rates of up to 70% on Facebook messenger. However, this doesn’t invalidate the use case conversational design. It should, however, force experience designers to consider carefully the use cases for conversational design. So for example, placing them in a front-line customer service context with a 70% fail rate will frustrate users and add costs. Reliability may well be less of an issue if bots are used as part of a marketing campaign or platform where they’re not expected to perform important task for a user.
Experiences designers have to consider the use cases and build in appropriate affordances, so that users understand the limits and uses of the systems. This makes for a better experience as users appreciate what the system can do for them, rather than complain about what it can’t.
Intercom, a pioneering product company in messaging and AI, has some very clear advice learned at the sharp end of implementing chatbots and other consumer AI messaging systems, lessons include:
- Use it sparingly – it’s currently reliably good for a small range of relatively simple task.
2. Keep it very simple – don’t try to make interactions too rich, keep conversations short, and simple with clear scripts and flows.
3. Heavily structure conversations – offer few options, avoid open-ended questions
4. Always have a human fall back – no consumer facing AI can currently deal with complex customer service issues. It is best used to complement and triage queries.
Design Cross Platform Experiences
Voice and chat don’t sit in silos, as we’ve noted they’re platforms. As the technologies improve over the next three-to-five years, and user adoption increased, users will come to expect to interact with voice and chat seamless over a range of different platforms, i.e. at home and then in the car. Equally, they’ll also want to move a voice conversation with their ‘bankbot’ seamlessly from the home hub to the car and then expect to be able to continue the same conversation by switching to mobile text chat when the get on the Underground. This may not be possible right now, however, it’s important that experience designers consider these cross platform handoffs in the meantime to ensure as seamless a possible user experience (see the section on Setting User Expectation above.)
Designing Scripts and Personalities
New more human and natural interfaces require new skills. Chatbots and virtual assistants will increasingly require distinct personalities that will have to be designed. Experience designers now have to consider a new range of questions. T of How casual or informal is the tone of voice, does it line up well with the copy of other touchpoints the gender of the bot, or is it gender neutral – what gender’s going to be best to engage your specific audience – something that may well be different for a fashion business than for an airline or an auto-manufacturer. How closely does the personality of any bot reflect the personality of the brand? If you have more than one bot, then do they have different personalities – e.g. a more serious one for customer service and a more lighthearted one for brand marketing.
Think beyond Text and Voice
On the face of it this advice may seem a little Zen, however, chat interfaces have evolved a long way beyond simple text, with emoji, gifs, videos and images all increasingly used in interactions on chat platforms. And, as we’ve seen, chat platforms are now access points to a much wider set of content and applications than just chat.
As a consequence experience designers need to consider both inputs and outputs to chat, and outputs to voice.
A perfect example is the recently released Dominos chatbot on Facebook Messenger where the posting a simple pizza emoji is enough to initiate an order for pizza.
Experience designers need to consider how different types of input and output can work through any experience, e.g. does a chatbot send back pictures of solutions to common problems faced by people assembling flat packed furniture, rather than attempting to help in text.
There’s already a significant amount of practical advice for experience designing conversational experiences:
There’s also lots of great tips on conversational design in this Google guide from their conversational design team.
For a more detailed view of how to develop experiences for chat. Layer’s best practice guide is a valuable resource.
There’s also always lots for experience designers to learn from the developer platforms, which often have introductions to functionality and interactions – some of the bigger ones include:
Google Actions is the start point for designing conversational interactions and applications for Google Assistant
Alexa Skills is a similar starting point for Amazon Alexa
An in depth guide to the logic and technology used to build a chatbot
Designing Conversational Experiences – Examples
Though 2016 was the year of the chatbot, many of those developed where either small POCs or campaign lead PR stunts, most of which aren’t great examples of conversational design, or haven’t been tested with large numbers of users. However, I’ve picked out three below, that are serious products with large users bases, and that take different approaches to conversational design. (There’s a longer list of chatbots here. )
In 2015 KLM was one of the first businesses to develop for the new more open Facebook Messenger platform, allowing users to confirm booking, get boarding passes and use it as a customer service channel. KLM passengers can now use it as a recommendation service, asking it for directions to the nearest shop, restaurant, shop ATM or transport hub. Soon after launch, KLM said 1.7 million messages have been sent on Messenger by over 500,000 people.
Duolingo’s chat bots let users interact in French, German and Spanish which is a great idea. However, what makes Duolingo’s approach stand out is that the company has created more than one bot, each of which has a different personality – Chef Robert, Renée the Driver and Officer Ada all give subtly different answers and take conversations in different directions.
Swell is a chatbot based social network for making decisions. Ask the community for help or vote help other people with their daily decisions. Questions are binary – do this or that. It may seem like a limited use case, but they have over three million users and it’s an evolving product, so it’s worth exploring what they do and how it works.