Designing a Better Bot, Part 2: Thinking Tactically
The way your bot behaves is just as important to the user experience as the reasons that it exists.
In my previous article, I went over several conceptual and strategic design recommendations to help you deliver a better experience with your bot. We’ll look at several more here, this time going into specific aspects of the bot UX itself, as well as a few initial thoughts on the ethics behind bot design.
Above all, make sure you design a bot that offers something to the person interacting with it, and be acutely aware of their needs and the journey that you encounter them on. To that end, the UX recommendations here will help ensure that your larger goals aren’t derailed by the conversation design itself.
It’s a conversation, not an app.
As convenient as it may seem to have the user say “menu” or “help” like they’re yelling at a frozen macbook, you’re not really taking advantage of the fact that you’re having a conversation with a person. A conversation follows particular paths and is bounded by a person’s ability to retain and process information in that moment. Menus should be used sparingly, if ever. Don’t just shoehorn an entire app or website into your bot.
Furthermore, forcing someone to say things they wouldn’t normally use in conversation is antithetical to the entire concept of conversational interfaces. Don’t make the human speak robot just because your robot can’t understand human.
Get to the point.
That said, “conversational interface” doesn’t mean “have a prolonged exchange with the user.” Sure, a bot with a well-defined personality will likely need to be able to speak outside of its main functionality, but you don’t need to overdo it. People aren’t coming to your bot to talk with it, they’re there to get something done. Conversational interfaces allow us to interact with technology and services in a way that is fast, familiar, and driven by personality.
Use structured input.
When your bot says something without giving the user an idea of where to go next, it makes their experience unpleasantly confusing. To avoid this unnecessary difficulty, use structured input to give options for what they can do with your bot.
Buttons and quick replies will take the burden of choice off of your user and ease their cognitive load. Even though you’re essentially forcing them to say what you want them to, it keeps the user on the journey that you’ve designed. In some cases, you can provide different ways of saying the same thing, to give them freedom to speak how they want. No matter how smart your bot is, structured input will minimize frustration and the chances of it breaking.
Use AI to expect the unexpected.
On that same note, whenever you don’t use structured input, you run the risk of the user breaking your bot. Unless you’re using a service that can help with AI, like Amazon Lex or api.ai, your bot’s “artificial intelligence” is going to be determined by your ability to think of all the things a user could possibly say and all the ways they could say it. Every time your bot says “I don’t understand,” there’s a chance your user will leave and never come back. Your bot doesn’t have to be dumber than a bag of hammers if you don’t want it to be.
Be prepared for your bot to break.
Your bot will break, and there’s no way around that. It’s incredibly easily to derail conversations, but what you do in response will determine whether or not the user sticks around.
You need to provide fallbacks that will alleviate and address frustration, such as default or context-sensitive messages that provide the user with next steps. It must be absolutely impossible for the user to get into a protracted back and forth loop of “I don’t understand” responses.
If having a fallback means having a human at the ready to take the reins of the conversation, go for it. The last thing you want in a customer service situation is your communication tool creating additional stress.
Onboard like you mean it.
Given that your bot might be the first one that someone interacts with, you have a responsibility to introduce the conventions and patterns of the medium to the user. Conversing with bots comes with rules and considerations that are specific to each interaction, despite the fact that it’s a conversation. This will change as the technology evolves, but right now, you need to ease the user into the bot’s capabilities, limitations, and the ways they can interact with it in a quick, tactful, and interactive way.
Testing makes better.
Test your bot repeatedly, like you would when designing any other product or experience. Look for every possibly way to break your bot, and plan for every single thing the user could say or do. Put it in front of everyone. Don’t just test it with UX designers and bot developers, test it with your mom and dad, and anyone who’s less familiar with technology than you. And most importantly, identify who your target user is, and test it with them.
You only get one shot at this.
If someone gets frustrated with your bot, or reaches a dead end, they won’t say “oh, let me restart this and try again.” They’re going to walk away and never come back.
Consider ethical context.
Last, and absolutely not least: you must always consider the design decisions you make in an ethical context. You’re not designing something that exists in a vacuum, but a product or experience that directly affects other people. I’m going to get into this in detail in a later article, but for now, keep the following two pieces of advice in mind.
Don’t pretend to be human.
Don’t have your bot pretend to be a human. Be upfront about your bot’s limitations, and never try to trick your user into thinking it’s a person. Even if it’s with the best of intentions to provide a pleasant customer experience, you’re setting yourself up to fail: If someone goes into the experience expecting a level of conversation and competency that your bot can’t deliver, they’ll eventually figure it out. They’ll rightly feel deceived and misled.
Be honest about data and privacy.
Tell the user who sees their data/input and if it’s going to live somewhere permanent. For example, the fact that Amazon Echo records your words for anyone with device access to see and that Facebook messenger logs all bot messages with the creator by default both surprises, as the two platforms aren’t upfront about either phenomena. Sure, we give up a sense of privacy when we put anything at all on the internet, but there are still plenty of things your audience might be sensitive or unhappy about you knowing.
(If you’d like to know more about the underlying ethics of AI and bot design, please be on the lookout for my upcoming article on the subject.)
At the end of the day, simply asking someone to interact with your bot is asking them to change their existing behavior. Just because someone spends all of their time in messenger, it doesn’t mean that they’re going to think to or want to do something else in it, like order a pizza or check on a UPS delivery. In every case so far, bots have been an additional, alternative way to do something, not a unique and irreplaceable one. A bot will not be your audience’s first choice of a way to do that thing, so you need to make sure they have a reason to use it beyond mere novelty.
Or, better yet, start with the goal of making a bot that offers an invaluable experience.
Thanks for reading!
If you liked it (or didn’t), please let me know. I’d love to hear from you.
Psst. I have a bot.
Do you like games? Do you like mysterious dungeons? Do you like text adventure RPGs? Wait, you DO??? You should say hi here. And by “hi” I mean “Hello, Dungeon.”
More thoughts on bots:
The Underlying Ethics of AI and Bot Design [Coming Soon!]
