By now, you already know the benefits of chatbots. They improve customer service experiences, reduce costs, and free up human agents for higher-value work. But, to build a successful chatbot and avoid problems like what happened with Microsoft chatbot TayTweets, it's important to understand chatbot best practices. Let's go through some tips that will set you up for success.
Table of contents: Chatbot best practices
#1: Understand what makes a chatbot successful
#2: Select the right type of chatbot
Artificial Intelligence (AI) chatbot
#3: Choose the right channel
#4: Define what can be automated
#5: Create a process for what can't be automated
#6: Map out the user flow
#7: Use buttons and UI elements
#8: Give your chatbot a personality
Work with a partner that understands the best practices for chatbot development
Before you start building your chatbot, it’s important to understand what separates good chatbots from bad chatbots. The best chatbots are:
- Goal-oriented: they guide the users to their goal with minimal effort.
- Context-aware: they take into account the situation of the user.
- Quick and clear: they use simple language and get to the point.
- Turn-based: they let users take their turn in the conversation and don’t send too many replies at once.
- Polite: they respect the user’s time and objectives. If a customer starts a conversation to solve their problem, they don’t push offers and discounts on them.
- Error tolerant: they anticipate errors and recover seamlessly.
There are two main types of chatbots, each with its own advantages. We usually recommend starting with rule-based chatbots; you can always add artificial intelligence later if necessary. Let’s review the difference between the two.
Rule-based chatbots respond to specific commands. They follow a guided conversational flow based on a decision tree. Usually, the chatbot offers buttons for easy replies. Some are also able to answer questions based on keywords.
The rules defined can be very simple or very complex. The most common type of rule-based chatbot uses a document retrieval system to guide the user with follow-up questions to eventually get to the correct resolution.
This type of chatbot should be used to handle common queries with predictable patterns. It is also known as a decision tree chatbot, where the branches represent the options that the user has available.
AI chatbots are good for unpredictable and broad use cases. They learn from the interactions they have with the end-users. This is made possible, in part, through Natural Language Processing (NLP).
NLP allows chatbots to intelligently respond to a user’s text input by understanding intent and context. When building AI, it's important to regularly test and improve technology. Learn more about how conversational AI works.
Again, usually, our customers don’t need conversational AI to make their chatbots work well. As chatbot best practices go, starting with the minimum level of automation is a big one.
It’s important that you choose the right home for your chatbot. Ideally, you’ll want to choose a channel that your customers already use -- like Facebook Messenger or WhatsApp.
These days, people don’t want to be forced to download yet another application to communicate with a brand. Using the messaging apps that people already know and love makes it easier for them to engage with you.
When it comes to chatbot best practices, Pareto's law usually applies. Pareto's law says that 80% of effects come from 20% of causes. With chatbots, this means that 80% of your customer support ticket volume likely comes from 20% of your FAQs. Which is why FAQ chatbots are one of the most popular and effective types.
First, understand your audience and categorize the 20% of inquiries that drive the largest volume of support tickets. The remaining 20% of FAQs usually represent more challenging or complex support tickets.
The remaining 20% of FAQs usually represent more challenging or complex support tickets. We recommend creating a process for a seamless handover to a human agent. Your customers should always have the option to reach a human when needed, or at least understand when a human will be available to help them.
As you gather more data, you’ll start to identify more FAQs and improve the abilities of your chatbot. Think about what you can do to automate the low-value tasks to free up your human agents for higher-value, more rewarding conversations.
Mapping out the user flow is essential in building a successful chatbot. One of the most common chatbot best practices is to start small. We recommend building a ruled-based chatbot and then later building in AI and NLP capabilities.
This means that you need to start with a decision tree with all the use cases (or FAQs) you want to automate. This will serve as a road map for conversations.
You’ll want to replace text with graphics and buttons wherever possible. The human brain processes images faster than words. Take advantage of buttons, quick replies, carousel selectors, and list selections to improve the conversation flow.
For example, it is easier to select a date on a calendar view than to write out date in a message. Also, if there are two choices in a decision branch, two buttons work better than requiring the words to be written out.
These UI advancements separate today’s chatbots from the chatbots of the past. Good chatbots will use a button where it saves time, allow someone to upload a voice memo where it makes sense, or sign with their finger if applicable.
Finally, a successful chatbot needs a personality. According to chatbot best practices, giving your chatbot a voice makes it more engaging. Focus on your target audience. How can you create a chatbot that relates to your customers?
Giving a tone and personality to your chatbot is an essential phase of the process. But, don't go overboard. Creating a chatbot that is too “friendly” runs the risk of being annoying. Make sure that your chatbot reflects the tone and voice of your brand.
Thankfully, there are platforms like Hubtype that know the ins and outs of chatbot best practices. Many enterprise companies choose Hubtype to efficiently build conversational apps.
Using Hubtype's framework you'll be able to:
- Save time and money
- Easily build a great conversational experience
- Scale effectively over multiple channels and languages
- Iterate and improve your chatbot