The Guide To Designing A Magical Chatbot Experience — Part 1
Why user experience matters.
It is now quite easy to build a simple chatbot which responds to a few keywords or buttons, and they can be fun, however they do not give the user a magical experience.
One of the coolest things about innovative new technologies is that they seem like magic when they are first introduced.
The first car magically moved without horses. The first telephone magically threw a voice into someone’s far away ear. The first video was a magical moving picture, like Harry Potter!
Today, people are craving a similar magic. Where is the future we were promised, where Hal 9000 manages our interplanetary spaceships?
Raising the Bar
To give the public the magic they are craving, we as Botmakers need to do a lot better.
We need to build bots that actually solve our users’ problems. Bots that work quickly, effectively, and don’t force our users to learn complex commands or memorize phrases.
We need bots that seem like magic.
To up us get there, I propose this challenge to the Botmaker community:
Make chatbots that perform just as well as humans.
Humans default to conversation because it is the primary way we have learned operate in the world. However, we only use conversation with other entities (humans mostly) of similar capabilities, who can understand what we are communicating quickly and without explicitly stating context.
When the entity you are conversing with does not understand you as well as most of the other entities you converse with, you get frustrated or even angry.
Right now, humans turn to a conversational channel because dealing with machines is confusing, complex or broken. When the machine does not understand them, or does not provide what they are looking for, they just want to ask a human for help.
If you send users from a GUI based machine that confuses them to a conversational machine that barely understands them, you just frustrate your users even more.
But when your chatbot can match or even outperform humans, it will be magical to the user.
This does not necessarily mean that a bot needs to pass the Turing Test; the bot only needs to perform well in the bot’s area of expertise.
If a human can answer a user query with no follow up question, so should your bot. If a human needs further information, then your bot is allowed to request more.
It is a simple concept, but hard to implement.
So I’ve created a practical set of guidelines to help you build chatbots that perform less like machines, and more like humans.
ELIZA’s 8 Laws For Designing Magical Chatbots
These laws, named after the first chatbot, are designed to help your chatbot perform just as well as humans. When building your chatbot, these laws will help guide you through every interaction to ensure the experience is magical.
- Minimize Questions.
- Remember Everything.
- Predict & Personalize.
- Curate.
- Be Fast & Convenient.
- Don’t Be A Command Line.
- Provide A Way Out.
- Help.
Featured CBM: I Was an Undercover-Bot for 2 Months. Here is What I Learned!
Law #1. Minimize Questions
Chatbot value decreases with number of parameters requested by the bot. Infer context when possible.
Humans can usually infer a lot of implicit information from the way someone asks a question. Humans also do not need your name, address, phone number, email, date of birth, etc. in order to participate in a conversation with you.
When a chatbot needs to ask for more information, put yourself in the conversation. Would you be asking for that information yourself? If not, why? How can it be inferred?
Law #2. Remember Everything
Remember conversation history. Keep track of where the conversation is. Pull any source of information on the user at your disposal.
Most humans do not suddenly forget everything you mentioned 3 sentences ago. Conversation with humans often builds on facts established earlier in the conversation.
Bots should take advantage of the fact that they have perfect recall and keep past contexts in mind during the current conversation.
Law #3. Predict & Personalize
Look at user history to predict future behaviour. Listen for actions they are planning, and follow up.
Humans will adjust their conversation based on what they know about a person and their previous behavior. If you know your co-worker likes tacos, you will invite them when you get tacos for lunch. At the same time you wouldn’t continue to pester a co-worker who has indicated they dislike tacos.
Bots have an advantage here with a bit of intelligent planning.
Law #4. Curate
Humans turn to chat for the best information, not all the information. Be much better than Google.
How many times have you Googled something, only to discover non-useful results, and then asked friends for advice?
As the signal to noise ratio on the internet continues to worsen, and the noisy are getting better at looking like signal, algorithm based searching is getting less effective.
A human will ask another human they consider to be an authority for the best answer to their question. They do not expect other humans to return a list of possible answers.
Bots should also provide the best answer, not a lot of answers. If you can’t do it algorithmically you need to curate manually.
Law #5. Be Fast & Convenient
Immediate response time is necessary. If users have to wait they can do it elsewhere. Be more convenient than other options.
When you ask a human a question, you expect that they will immediately understand what you are asking no matter how you ask.
Humans often turn to conversation because they think it might be quicker than other more complicated options, like sifting through search results. But if conversation is not quick, they will move on.
Since bots are always on, they have an advantage with initial response time, but bots also need to understand what the user is asking nearly immediately. The bar is about as long as it would take a human would take to type out the response.
Law #6. Don’t Be A Command Line
Do not require commands and precise syntax like a command line. Understand regular conversational english.
The whole point of using natural language is to communicate the way you prefer to communicate. Humans understand perceive things differently and ask questions in different ways.
Chatbots need to understand humans just as well as most other humans could.
This does not rule out commands and keywords, as humans often communicate with linguistic shortcuts once a common subset has been established. However chatbots should not require precise syntax.
Featured CBM: Why Emoji Fit Perfectly for Chatbots
Law #7. Provide A Way Out
Humans and bots make mistakes. Users should always be able to start over, make changes, or completely escape.
“We got off on the wrong foot, can we start over?”
Sometimes humans get into conversations without correctly establishing the base facts. It is perfectly natural to start over, erase mistakes, and re-establish the premise of the conversation.
Humans do not continue to drive forward a conversation when it becomes clear that the other party is lost, so chatbots should not either.
Law #8. Help
Provide documentation and guidance when users ask for. Fall back to humans if needed.
Humans let people know what their expertise is and how they can help. Bots should do the same.
Humans also defer to other humans when a request is beyond their abilities.
Bots are restricted to the narrower abilities than most humans, but they can still defer to humans when the user needs to go beyond what a bot has available.
