How to avoid a bad bot

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.

Example of a whiteboarding session to understand pain points (Credit: Ash Patel)

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.

In order to determine goals, you can start off with having intended users identify what they need to do on a given day (From a Wizeline UX workshop)

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.

Knowing what users are asking for is essential in meeting that demand through design. (Klüg analytics dashboard)

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.

Visual aids should be used to provide context that words would not be able to do (Credit: LINE)

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.

Originally published at www.klug.chat on October 18, 2018.