Our NLP database manager explains how the hundreds of conversations he’s had with customers informs how he trains machines to respond to customer inquiries.
“For voice recognition technology, grasping all the necessary contextual factors and assumptions in this brief exchange is next to impossible.” Ditte Mortensen, UX Researcher
Why start off with this dire statement?
This sets the expectation that designing bots requires you to embrace the pursuit, but not the expectation, of perfection. Because bots cannot retain context like humans naturally can, we must ask the right questions at the right time and be transparent in why we’re doing so.
Those designing the conversations we can have with a voice interface strive for:
Making conversations sound natural
Enabling users to complete an action with the fewest number of steps, and therefore, as little friction as possible
Asking users the right information and avoid assumptions to provide customized, relevant information.
With these goals in mind, here is my check-and-balance system for designing bots:
Use Time Wisely.
App builders fight for space on mobile. Alexa skill builders fight for time-- people’s attention span listening to a prompt.
This goes for both text-based and voice user interfaces. The same way space is of the utmost importance in text bots, time makes or breaks a voice experience. While we try to mimic natural conversations, we do have to keep in mind that we have less patience with bots than with human interactions.
When we see that someone is nervous, we can feel empathy for them and tell ourselves to be a bit more patient with trying to get an answer out of them. We don’t have the same lenience with technology devices.
So it must get to the point right away, and anecdotes that show personality need to be used sparingly to serve the purpose of the bot.
It’s the same when talking with humans, right?
There are expectations in back-and-forth conversations with humans we apply to bots as well. For example, we don’t appreciate customer service representatives that go on and on about their personal lives, what they had for dinner, etc. when all you want to do is get your router fixed. This applies to machine interactions as well, perhaps even more so. Make it clear what a user can do through the interface, provide action items, then confirm before the bot takes any decisive action.
2. Take advantage of sounds and conversation markers.
In some ways, designing voice can feel easier than designing for text. Designers can take advantage of the fact that they are designing for audio and the UI is simply words. Of course, there are separate factors within delivering these words: speech breaks, tone, pitch, volume, female vs. male, etc. I outline it in detail here, but here’s an example:
After a lengthy sentence, put in breaks so you give user a bit more time to comprehend what they were told or what they were asked to do.
Ex. If someone asks where they can find the verification number for their credit card to confirm a purchase, the bot must provide instructions at a speed at which the user would perform the action.
Wouldn’t you do the same when you explain a step-by-step process to someone?
3.Guide the user and ask for what you need-- but you must justify it.
This is where a designer’s role is important to take advantage of all capabilities with the least impact from limitations, such as retaining context of the conversation.
For a user asking for restaurant recommendations, the conversation may go something like this:
Here’s where the bot could run into trouble. At this point, the user may change the topic by asking how the bot makes these recommendations:
The user now has their question answered about how the bot works, so she wants to go back to getting food recommendations. She wants to see what else is around, so she now asks,
“Well, how about Mexican restaurants?”
Uh-oh, here’s where the trouble begins. The Alexa skill did not store the fact that the person is currently in San Francisco, so it’ll ask,
“Got it, what city should I look for Mexican places in?”
The user will think:
……. I just told you.
Instead, to justify why they’re asking for this and show transparency, the bot can give a quick explanation.
Yes, it’s not ideal. But it shows transparency and makes your questions reasonable.
We apply these principles in designing bots because an automated system, whichever medium it’s on, needs to earn the right to be wrong.
The bot has earned this right if it has tried to clarify and ask relevant questions. It does not have the right to be wrong if it never asked the questions to help the user and it proceeds to expect the user to be understanding of repetitive questions without an explanation of how the answers to these questions will be used.
Maximizing shared knowledge is key to creating better conversations.
Without this mutual understanding, each conversation we delve into with machine creates more opportunities for errors that waste our time. In the end, we as users will have to dig ourselves out of the dark hole we’ve gone into because the right questions were not asked and thus, wrong information was provided. As bot designers, by putting ourselves in the user’s shoes with each iteration, we can design bots that serve our needs with a higher success rate each time.
Chatbots are a great way for customers to engage with any brand. They can give users information about a rugby match, help them purchase flight tickets, or answer questions about their bank account.
One of the main goals of a chatbot is to bring a good customer experience that ends with a positive image for your brand. At Wizeline, we have experience designing successful bots. We create strategies that adapt to our clients by focusing on their needs and their user’s needs. Creating a bot is not only about building, but monitoring over time to make improvements.
With this in mind, here is what you can do to avoid common pitfalls:
1. BUILD WITH A CLEAR OBJECTIVE
How will you know if your bot achieves its goals when you don’t know what they are? There should be a list of objectives that the bot needs to focus on. These objectives will come from discovering who the users are, their lifestyle, and pain points.
2. GUIDE THE USER TOWARD A GOAL
Bots can be built to generate different types of experiences. An important part of a chatbot strategy is to define the different steps in a user journey, and how the bot should be programmed to respond to users through Natural Language Processing. The bot should have a clear path so that the user can take action.
CREATE A PERSONALITY ALIGNED WITH YOUR BRAND
There is a design process behind a chatbot’s personality. It needs to come from knowing your users and what they can and will expect from your bot. It needs to have a voice, a tone, and it should match the brand that it’s representing. Not all bots need to be funny, especially when the brand is recognized as being more formal or serious.
SET IT UP TO LEARN OVER TIME
If you have a bot, you should be able to identify when the bot is not working. This could go from recognizing when a bot’s answers are not the correct ones, when it keeps the user inside of an endless loop without the option of a handoff, or to diagnose if users are getting frustrated. A bot needs to be in constant evaluation and iteration to make sure it’s being improved. It includes regularly training user inputs to be understood, or noticing when several users are asking a question that wasn’t considered in the original strategy.
SERVE USER NEEDS FIRST
A bot will be successful only if it is able to bring users to a solution in an efficient manner. It can be easy to build a bot that looks like it does cool things, but isn't helping users get tasks done. These tasks should be defined not only during onboarding, but throughout each interaction.
TAKE ADVANTAGE OF VISUAL AIDS
It may seem like a conversation through text could be the obvious solution, but what happens with the type of user that prefers clicking a button for a faster interaction? Would a carousel of images be an ideal element? There are different components that can be within a bot, and they should be carefully selected to enable users to soak in information quickly and take action on it.
MAKE DATA-DRIVEN DECISIONS ON IMPROVEMENTS
There is a lot of data around a bot: popular requests from users, messages received, broken conversations, etc. Analytics is a fundamental part of a chatbot strategy because, when you have access to these information, you will be able make an informed decision on fixing broken interactions and increasing successful conversations. As our software engineer Liusha Huang said, “Analytics ensure that every interaction provides value and the chatbot continues to learn”.
Customer satisfaction can be achieved when a bot strategy is carefully developed. At Wizeline, we define chatbot objectives, identify the software integrations that work best, build types of experience, and design intents and flows. After validating the experience of using the chatbot with clients, we get them involved in testing to check if we need to add NLP, edit copy of the messages, shift actions when certain messages are displayed, etc. We also make sure to determine a marketing strategy to launch the bot so that it can be discoverable.
“Some of these companies need to focus at least as much on testing their products as they do drafting press releases.”
Thomas Gouritin calls the lack of focus on user experience the “AI bulls***” — specifically getting one error message after another for tasks that logically should work.
His theory for this widespread problem?
Not enough focus on testing the product before launch, and way too much on the selling. Specifically, those press releases that tout their Artificial Intelligence-powered chatbots(capitalized, mind you) that in reality are programmed questions and answers.
His commentary is caustic, but accurate.
Reserving enough time to test is beyond valuable. It is essential to avoid becoming a screenshot of a failed bot on Twitter.
The goal is to account for both predictable and unpredictable errors. For the latter, the bot does not need to have a solution, but needs to route the user to a place or person with the solution.
1. Predictable Errors
Test ideal user paths and account for unforeseen edge cases to determine impact vs. effort of changes.
Happy paths are ones in which the user is able to complete a task smoothly by providing expected answers. These paths must absolutely work, because the bot is otherwise useless.
In edge cases, a user types or says something the bot was not designed to answer. For edge cases that are discovered during usability testing, we need to determine the value it provides vs. time and effort it takes that may compromise timely delivery.
Ex) When the bot asks the user what type of cuisine they’re looking for, the user may ask for restaurants with the least wait time. Here, the bot should tell the user that it can only give recommendations based on cuisine preference.
The user may misunderstand your bot as broken if you don’t provide an explanation that the feature is not supported at this time, as well as a call-to-action. However, in order tell them why something isn’t working, the bot must be trained to pick up why the error is happening. This is why training the bot to understand common user inputs is important for the overall user experience.
Otherwise, they’ll keep trying the same thing over and over again.
The novelty surrounding chatbots makes people’s expectation of chatbots much greater than what most bots can handle at the moment — and I’ve seen this first-hand in testing.
The point of usability testing is to gather insights, prioritize, then iterate; it is not to make changes to account for every finding.
2. Unpredictable Errors
Reserve time for these to arise, then prioritize again.
Then there are errors that we simply can’t predict, such as platform issues. The restaurant recommendation bot may experience issues pulling up database from Yelp and return an error message. Testing should ideally be done in a specified time window, after which you prioritize solving for usability issues over nice-to-have features.
How do you train the bot to respond to these errors?
Organize a spreadsheet that categorizes each intent* expressed by the user that the bot should understand, then gather a list of common phrases that they would type or say for each intent. One intent could be “unsupported feature,” under which you’d put common features requested, but unavailable in the bot. You can then train the bot to respond with a copy explaining that the feature is not supported at this time.
Example of a spreadsheet categorizing user intents and corresponding phrases
*Intents: what we determine the user is requesting when they say something to the bot
How to get the right help for testing
Allow each team member to use their domain expertise and get involved in the right steps, so that you can create a prototype, deploy to a testing environment, test specific user flows, then iterate. Though you should leave time for design changes, accounting for different scenarios as much as possible from the start will cut the time required to iterate.
Let’s take this scenario: when a user types “help” while shopping for shoes, what options should the bot offer? Are they asking for “help” with navigating the bot or with the item they’re looking at, thus asking for a customer service rep?
The NLP Trainer (link to Aldo interview) would work with the Bot Designer (link to Diana interview) to come up with possible solutions:
Direct user to menu options (one of which is talking to a human agent)
Connect user to a human agent directly
Ask what exactly user needs help with, then redirect
As you may have guessed, I usually go with the third option to avoid assuming the user’s intention.
Getting the answer to “what exactly are they likely asking for?” correct as often as possible — through usability testing and analytics — makes the bot “sticky,” encouraging users to use the bot again and again.
Like any good design process, the decisions must be collaborative and iterative.
In conclusion, you need to consider:
1. Realistic Users
Testing with the intended users informs designers of tweaks, and sometimes entire redesigns, that need to be made.
This includes users in the worst case scenario.
For chatbots, users in the worst case scenario would actually be not people who have never used the chatbot, but those who have used it andhated it.
We want to observe how those who are biased from previous experiences and those who are brand-new would use the bot.
The tone should be in line with how the user speaks, and avoid information fatigue.
For text-based chatbots, the designer’s job is to ensure that text fatigue doesn’t hinder task completion.
As UX Designer Eunji Seo says, “Don’t make users go TL;DR.” Generally, anything more than three lines of text is too long.
3. Handling Errors
The goal is to have as few fallback messages (“Oops, I didn’t get that!”)as possible.
As mentioned above, this requires the designer to adjust wording or change the order of messages so the conversation feels natural and helps users achieve the task quickly.
*Fallback messages: messages noting the request can’t be understood, then often followed by menu options
4. Task Completion Rate
One way to test fatigue is through the 60-second test.
“Can users perform a certain number of tasks with just one hand in under 60 seconds?”
Customer satisfaction can be achieved when a bot strategy is carefully developed. At Wizeline, we define chatbot objectives, identify the software integrations that work best, build types of experience, and design intents and flows. After validating the experience of using the chatbot with clients, we get them involved in testing to check if we need to add NLP, edit copy of the messages, shift actions when certain messages are displayed, etc. We also make sure to determine a marketing strategy to launch the bot so that it can be discoverable. Talk to us here.
Santa’s little helpers are no longer just cheery elves building wooden trains. The true stars helping consumers buy gifts this holiday season are chatbots.
Whether it’s on Alexa, Facebook Messenger, a website or any other platform, chatbots are now a strategic must-have for engaging target audiences.
According to a PWC study, chatbots have matured to the point that 27 percent of consumers weren’t sure if their last service interaction was with a human or a bot.Gartner predicts that chatbots will power 85 percent of all customer interactions by 2020. Business Insider Intelligence agrees the timing is right for businesses to leverage this inexpensive and wide-reaching technology to engage with more consumers.
Here are 10 reasons why consumer brands should leverage chatbots this holiday season.
1 | Chatbots open up a new sales channel
Nearly half of consumers are willing to buy items through chatbots, and on average, users are willing to spend more than $55 on purchases facilitated through chatbots. The good news? Chatbots are relatively inexpensive and quick to deploy for brands to leverage this new channel this holiday season.
2 | Messaging apps are the most engaging platforms on the planet
Text messages have a 98 percent open rate. Today, 66 percent of consumers prefer to interact with brands through messaging apps like Facebook Messenger and WhatsApp, which boast 20 percent more active users than social networks. Chatbots provide a way to interact with consumers in a way that is familiar and flexible. They can help brands grow their following and engage with users on a deeper level than with any other social platform.
3 | Users like chatbots more than consumer apps
According to Quantcast, only 1,000 of 1 million apps have over 50,000 users. Apps simply do not have the draw they used to. Apps are still valuable, but chatbots are keenly optimized for mobile engagement. Chatbots used for events increase user adoption and engagement by 24 percent, versus ordinary event mobile apps.
4 | Generate more sales with instant response times
Delayed responses to consumer inquiries can dramatically affect sales, especially during the holidays when consumers have an urgency to purchase gifts. Sales conversion rates start to drop dramatically when a consumer has to wait more than five minutes for a response. The chance that consumer will make a purchase decreases by 400 percent after 10 minutes. Chatbots give brands the opportunity to engage with customers instantly, capitalize on their interest, and convert them to purchase.
5 | Provide a top sales associate that works around the clock
Good sales representatives know their audience and can answer questions based on expertise to help the potential buyer understand the product. Chatbots allow brands to essentially clone that sales rep hundreds or thousands of times, providing an advantage over the competition.
6 | Increase sales with real-time, actionable analytics
Unlike traditional website analytics, chatbots allow you to measure performance and adjust in real-time to maximize impact. If the chatbot isn’t answering specific questions accurately or directing users to the right pages, bot trainers can update scripts and user workflows to course correct. These modifications are especially valuable during the holiday season because they allow brands to track trends in behavior and adjust to maximize conversions.
7 | Higher click-through rate than email and social ads
The average click-through rate (CTR) for email is five to 15 percent. However, the CTR on external links sent by a chatbot on Messenger is 15 to 60 percent. Chatbots also have a much higher conversion rate than social ads, driving up to 266 percent more clicks than the average social ad in some cases.
8 | Bots can reduce bounce rates and cart abandonment
Chatbots can increase the average time spent on a webpage by up to 40 percent while still helping users find what they need, fast. Chatbots can also significantly reduce cart abandonment. Most companies remind users that they have items in cart via email. Chatbots are tying customers back in more effectively, with a 619 percent higher engagement rate than email.
9 | Good bots can significantly lower operation costs
Chatbots cut costs by over $20 million in 2017 and will account for cost savings of over $8 billion annually by 2022. A report by BI Intelligence states that annual salary cost savings when using chatbots is between 29-46 percent. E-commerce companies can invest those resources into other functions of the business and better support holiday retail initiatives.
10 | Chatbots are essential to staying on the cutting edge
16 percent of Americans own a smart speaker like Amazon Alexa today. These conversational interfaces are at the forefront of modern consumer engagement. Consumer brands need to leverage interfaces or risk missing out on powerful opportunities to connect with users.
If you’re ready to reap the powerful benefits that chatbots can offer, Wizeline can help.
From website bots and Alexa Skills to Messenger bots and everything in between, our collaborative chatbot experts can help you come up with the right strategy.
Our team will help you choose the best solution for your objectives, whether it’s an out-of-box implementation for a particular use case or a highly-customized bot that meets your specific business needs.
When you’re ready to start brainstorming ideas for your ground-breaking new chatbot, click here.
To learn more about how Wizeline is helping businesses succeed with chatbots, check out a few of our case studies or our blog below.
Case Study: Digital Arts Network partners with Wizeline to build Australian Open chatbot
Case Study: USA Rugby partners with Wizeline to launch the Rugby World Cup Sevens 2018 chatbot
Case Study: pmNERDS increased conversion rates and decreased workload for community managers
Case Study: TWG and Wizeline improve the customer experience with artificial intelligence
Innovation and creativity are key pillars of Wizeline’s culture. Having open spaces where both can be exercised is a company-wide commitment. With this in mind, we embarked on an initiative to create a new Alexa skill for the Mexican market. Knowing Amazon would launch in Mexico, we invited all Wizeliners to pitch an idea for useful skills that can be executed through voice conversations.
The challenge was designed to be completed in multiple product development sprints. This approach allowed teams the time to work on their project, while still tending to their client project work.
An Opportunity to Upskill
We organized special workshops as part of the challenge, where participants learned best practices in voice design. The sessions covered topics such as designing for voice interfaces, as well as how to integrate with external API’s so the Alexa skill can pull content from different sites. Amazon supported with resources that illustrate how Alexa skills offer a new approach to solving business problems. We also had an Innovation Frameworks session to learn how to boost user engagement.
The teams consisted of software engineers and project managers. We matched each team with a software engineering mentor. These mentors provided guidance for hitting key milestones, such as finalizing conversation flows and testing on a local server to assure the Alexa skill responds properly to all commands.
Projects included creative skills for blockchain reporting, food recipes, and using an elevator assistant. At the end of the challenge, all teams presented their pitches and we selected three winning projects:
Wizelendar ‒ an assistant for managing conference rooms. This Alexa skill enables seamless scheduling of meetings by communicating a simple phrase to an Echo device. Engineers: José Almaraz González, Dalia De Felipe Vargas, Maytee Sánchez, Diana Sánchez Urbán, Luis Daniel Acevedo, Mentor: Saul Ortigoza
Gasolinazo ‒ a new car feature that allows a user to ask for directions to the nearest gas station. Engineers: Alan Rodriguez, Gustavo Cordova, Juan Carlos Pérez, Antonio Fregoso Mora, Mentor: Luis Amador
ChepOps ‒ a DevOps assistant to monitor the cost of the infrastructure used with just a voice command. Engineers: Aaron Arredondo Sanchez, Antonio de Jesus Santiago Dueñas, Hector Murrieta Bello, Jaime Gutiérrez Sosa, Mentor: Andrés Villavicencio
At Wizeline we make it a priority to experiment and discover new ways to approach technology. We will continue to host more challenges and exercises that allow us to explore technology solutions that improve our day-to-day lives. Stay tuned for the next challenge!
Written by Gabriela Martinez, Platform Architect at Wizeline