How To Build A Chatbot: 10 User Experience Design Mistakes To Avoid

AI-driven Chatbots from Certainly are the best online shopping assistants

User experience design is a vital element of successful chatbots, helping companies to improve customer engagement and customer satisfaction.

Chatbots designed according to the best UX practices can create quality interactions with customers in connection with an inquiry to Customer Service.

Users require an instant reply and accurate answers, regardless of the timing or complexity of their request.

For that reason, knowing common UX mistakes helps you to design a bot that will meet the expectations of your users.

Many companies can build their own bots if the technology allows line of business employees to do it, without requiring professional expertise in programming.

However, user experience design mistakes often occur, having a negative influence on the overall user satisfaction from interacting with the chatbot.

Below, we have collected the worst 10 mistakes that might ruin your chatbot.

Learning what mistakes to avoid will help you to discover how to build a chatbot that will lead to higher customer satisfaction and a higher self-service rate.

Alternatively, a chatbot company like Certainly offers a customizable chatbot builder that helps you hit your user experience goals.

Having Only One Type of Interaction Style between Chatbot and User

One of the top user experience design mistakes is having only a predetermined list of questions for the user to choose from.

The predetermined list of options may be convenient and be fit for use if the user wants to decide quickly, as well as for the bot operator.

However, predetermined questions may restrict the possibility to explore all the choices and force users to pick an option that may not be the right topic for them.

Graphic of a great customer experience design with satisfied customer giving 5 star rating.

Having a list of options might diminish the natural conversation flow and feel less human to the customer.

It also might negatively impact user experience, leading to user frustration or anger.

Meanwhile, allowing the users to type their questions may come with the downside of slowing down the conversation.

The customer might have to rephrase the sentence, which requires more effort from the customer to reach the correct answer.

Nevertheless, as the interaction is more natural, a more enjoyable customer experience is created.

Hence, allowing the customer to choose between predetermined questions as well as free written text is the best option when examining how to build a chatbot.

Furthermore, to provide the best user experience design, the conversation should create a fluid experience.

For example, you might improve the user experience by:

  • Breaking long messages into smaller ones, using several speech bubbles.
  • Introducing a popular GIF here and there (do not abuse them though!) to break the text.

It is important to be open to any user input, while clearly stating the scope of the chatbot at the beginning of the conversation, so that the user won’t feel frustrated if the chatbot fails to answer questions beyond their capabilities.

Misleading the User about Who They Are Talking To

Building trust between customer and business is the most critical step in keeping a positive customer relationship.

If the company is hiding that they are using conversational AI and the users later discover this, trust can quickly be lost and user experience compromised.

Consequently, the company can even risk losing a potential customer.

Two phones depicting different responses from a chatbot to a customer.
A conversation with a bot should be a fluid experience.

That is why organizations need to make sure they are transparent and inform the customers that they are chatting to a conversational AI bot (although in some cases it can be rather obvious).

There is a positive aspect of being open about using AI chatbots.

For some users, it is easier to start a conversation with a chatbot.

The end-user feels like he or she is not bothering anyone and does not need to wait for a reply. In this way, you achieve your user experience goals while remaining transparent.

To Improve User Experience Design, Provide the Option of Getting Transferred to a Human

It is also essential to have your bot admit its own limits and shortcomings, when an error or a misunderstanding occurs.

This ensures that your users do not get tired of chatbot responses, and it also adds confidence and reassurance to them.

For example, repeatedly asking a user to rephrase their question can lead to frustration.

You can easily prevent this by providing the customer with the option of transferring to human customer support in case a chat goes south.

Make your bot admit that it is, indeed, just an AI bot that is still learning.

This will give a more personal touch and will reduce the risk of the user feeling alienated or angered.

Replying without Waiting Time

Chatbots can send messages instantly when a customer asks a question.

While it sounds counterintuitive, this can be more more distracting than convenient, in terms of user experience design.

Loading the reply as soon as the question is submitted, without waiting time, does not look like a human reaction and feels unnatural.

Graphic of customer receiving sub par customer experience design by being tricked into thinking they are talking with a person.
Trust is crucial between a customer and a business. It is important to inform the users that they are talking to a chatbot.

Although the user should already know that they are chatting to an interactive chatbot, users prefer to have a conversation with a bot that acts like a human.

This means creating a pause between the question and response.

The longer the message, the better it is to have a longer waiting time that gives time for the user to read the information.

As a rule of thumb, it is good to keep a minimum of 2 seconds before each message the bot sends.

A Badly Designed Bot That Has No Memory and Is Unable to Learn

When looking to meet user experience goals, it’s important to design a bot that is able to learn and remembers information.

A chatbot that is not capable of retaining information – like subjects previously mentioned within the conversation – leads to a nonsensical and repetitive dialogue.

Considering some automated agents are already equipped with machine learning, repetitiveness can quickly generate a feeling of annoyance in the user.

Furthermore, today businesses are expected to program their conversational AI to be capable of resuming and saving the chat log for future reference.

Graphic of overly fast customer response time from a chatbot, an example of a bad customer experience design feature to avoid.
Responding instantly does not look like a human reaction.

This helps users to re-engage with a chatbot more easily in the future.

Failing to address this user experience design problem can have a hugely detrimental effect.

This is particularly true if your bot fails to solve an issue and transfers a customer to a human support agent.

The bot must be able to send a chatlog to human support agents so they can naturally continue the conversation.

This ensure that the transition is smooth and effortless, and your users do not have to restart the entire conversation.

Nevertheless, it is vital to keep GDPR in mind.

Many bots are able to collect zero party data.

This is hugely effective toward marketing efforts, but there are some legal limits to consider.

Undefined Purpose And Incorrect Tone of Voice

A chatbot without purpose and the right tone of voice is a big user experience design mistake to avoid.

When considering how to build a chatbot, make sure that it serves the specific purpose of your company and its desired engagement.

You need to know what your bot is going to be used for before you start building it.

Perhaps it will just help users with customer service queries.

Or maybe it will be more advanced and assist customers with product suggestions.

Image of phone depicting a repetitive chatbot conversation.
A bot without memory can lead to repetitive dialogue.

Either way, the purpose of your bot will help to inform the tone of voice to choose.  

You must also select the tone of voice based on internal research.

It is essential to consider who the customer is and in what way he or she engages with your product or service.

Your bot must have a personal tone, either relaxed and formal, or friendly and informal.

Establishing the voice of your chatbot is a crucial element in solidifying your brand messaging and improving user experience design.

Conversational AI without NLP/ NLU

NLP (Natural Language Processing) and NLU (Natural Language Understanding) are terms relating to the interpretation of human language.

NLP is a blend of computer science, AI, and data analysis that enables the understanding of human language by a machine.

In simpler terms, NLP deals with how technology can meaningfully process and act on human language intake.

Without NLP, AI bot conversations might be harmful to the user experience.

NLU is a subcategory within NLP, which ensures that chatbots understand intent or sentiment.

For example, NLU helps to process comments and orders. Thanks to this, chatbots can more effective interact with a user.

Why are NLP/NLU Vital to chatbot user experience design?

Humans naturally understand what other humans are saying, even with incorrect grammar.

NLP and NLU therefore play dominant roles in the user experience.

Computers can be easily confused, and may struggle to understand what users are saying if they use slang or colloquialisms.

Image of robot speaking to customer in an inappropriate manner, an example of what not to do with customer experience design.
Choosing the right note for a chatbot should be based on customer research.

That is where Artificial Intelligence and Machine Learning come into play.

Algorithms allow the chatbot to understand what customers are saying, even if words are misspelt. They then allow the chatbot to formulate a more effective reply.

The best conversational chatbots on the market use their artificial brain to analyze many aspects of language when a chatbot receives a message.

Sentiment analysis allows a chatbot to discern the mood of the person writing the message and provide an appropriate response.

With NLU/NLP, the bot can detect misspellings, recognize named entities, and can also divide sentences.

Not Focusing on the End-When Adjusting User Experience Design

Learning the target audience’s needs and communication methods will provide value.

It also enables you to create a chatbot that will be faster and better and that the users will enjoy.

During a presentation at Brighton SEO, Purna Virji, Senior Manager of Global Engagement at Microsoft, used the analogy of Homer and Lisa Simpson in describing the importance of the user experience when adopting new conversational interfaces.

The “Homer” stage and the “Lisa” stage are the two systems that determine our decision making.

With conversational user experience design, it is essential to keep people at the Homer stage (emotional and intuitive) where the journey is easy, intuitive and convenient.

If users move forward to Lisa’s stage (logical and thoughtful), the decision-making process rapidly slows down.

Phone depicting repetitive conversation with a chatbot that doesn't have NLP and NLU
NLP and NLU help bot to detect spelling mistakes.

Create a Convenient User Experience

In e-commerce, it might be a good idea to provide some time references, when possible.

For example, when users do an online sign-up or a check-out while shopping, let them see how many steps the process requires or how many questions they have to answer.

Customers will feel like there are no hidden variables, and that you value their time.

A chatbot can do this with messages like “Let me ask you three questions”, “It will just take one minute”, or “This is the last question”.

You can also try to create “wow” moments like: “You did it! Thanks a lot. Now I have all the information to…”

Incorporating overly complex messages as part of your user experience design

When faced with lengthy messages, customers can become impatient.

They might view long messages and boring or unprecise. Short messages offer a better understanding and more relevant information for the customer.

However, if it is impossible to avoid lengthy text, the best practice is to consider splitting it into parts that follow one another simultaneously.

While it may seem appealing to build a sophisticated Alexa–like bot, making your chatbot overly intelligent and multifaceted might be overkill.

Graphic of person and chatbot standing next to each other on computers, depicting conversational ai.
Learning the needs of your customers might allow you to build a successful chatbot.

In most cases, your users are looking for a quick and easy solution for their problem. By giving them too many options and long messages, you may end up confusing and saturating them with information.

A frustrating user experience design mistake is having too many options or long messages.

This leads to lengthy, drawn-out conversations, and adds to the risk of the user dropping out.

Avoid getting the user frustrated as it could easily deter them from buying your products or services in the future.

Make sure you have a clear understanding of what your users need from your chatbot and adjust it accordingly.

Not Integrating Visuals

Visuals are the second most important and useful element contributing to a good chatbot user experience.

According to research conducted by 3M, the company behind the famous yellow Post-its, visuals are processed 60,000 times faster than text.

In other words, a lack of visuals in chatbot messaging is a user experience design mistake to avoid.

In chatbot interfaces, this means that using images in the chatbot’s messages is more likely to engage users and hold their attention.

It also creates a more fun exchange which might add to the overall satisfaction of your customers.

Image of phone featuring exceptionally long first message from a chatbot.
The users tend to prefer short messages from a chatbot.

Leaving them with a fond memory of the interaction will make them more likely to come back for more.

A chatbot can send a map to the customer of the closest store or place, based on their request.

Having visuals integrated into your conversational AI can help with putting a smile on a customer’s face.

They can also add some humor to conversations if you use them in a clever way.

Not Creating a Persona for the Chatbot and Not Adding Any Permanent Personality Traits

Why does a machine need a personality?

It might seem silly that a company should invest time in building a persona for their bot.

However, the initial versions of chatbots were more likely to make the users feel alienated in the conversation, as they knew they were only speaking to a computer.

Those conversations were often considered irritating and unhelpful.

The inability to reach a real person within customer service fostered negative perceptions of the businesses that implemented chatbots.

Persona for company branding

Luckily, advances in Artificial Intelligence have created a wide range of improvements that allow companies to avoid such experience design mistakes.

One development is the creation of a persona as part of the company branding.

Companies can benefit from the chatbot having a persona.

Graphics of emoji faces in different colors.
Visual elements can make interaction with a chatbot more engaging.

Having a persona with a suitable character image that mirrors the target customer and company’s brand is useful.

This is because it reduces the chances of the customers getting frustrated when talking to the bot.

Chatbots are created for humans, and therefore, they need to communicate like humans.

A bot’s way of communicating should represent real–life conversations.

Personality makes the conversation more amusing and makes it feel more human.

Furthermore, it makes the chatbot more relatable and believable.

It’s essential to study and get to know your users. Once you know their age, background, location, and language, you can build your responses accordingly.

To improve user experience design, the bot should simulate person-to-person communication.

Emotions generate a more intimate connection towards the other party.

So you should take into careful consideration the choice of language, tone style, and even mood.

For example, a chatbot might show it listens by using expressions like “Got it” or “I understand, carry on”.

Finally, using suitable GIFs might contribute to the chatbot personality and make end-user to feel more comfortable.

Summary: Improving user experience design with your own Conversational AI

There are many factors to considering when exploring how to build a chatbot.

Since the aim of a chatbot is to support your business’ customer service, the user experience design should contribute to a more personal relationship with the users.

However, common UX mistakes often occur when designing a bot, compromising interaction with the customers.

You might undermine the user experience by having only one type of interaction style, misleading the users about who they are talking to, or using unsuitable language and tone.

Following user experience design best practices and avoiding the 10 most common mistakes listed in this article will help you make the process easier and create a truly successful chatbot.

Article written by Patrycja Hala Sacan and Luis Nagel

Related blog posts