6 Ways to Enhance Your Chatbot UX

Designing the human side of the experience

Not-so-breaking news: The idea of conversing with a robot has evolved from science fiction (2001: A Space Odyssey’s HAL, Star Wars’ C3PO) to everyday reality (Alexa, Siri). For years now, countless industries have implemented AI-powered solutions as responses to the increasing customer demand for immediate, round-the-clock customer service.

As the COVID-19 pandemic exponentially speeds up this digital evolution, more and more companies are looking to adopt technology that better fits this model of instant communication. Chatbots undoubtedly answer this call: Immediate responses to questions, 24/7 assistance, reduced phone support volume, faster facilitation toward resources… I don’t think I need to convince you.

What I do want to convince you of is the importance of putting your users at the heart of your chatbot design. Efficient automation can’t replace human connection, but we can definitely learn from it. Focusing on the human side of the screen, and capturing the simplicity, familiarity, and delight reminiscent of messaging a real person, can bring life to your conversations and further strengthen the brand/audience bond.

I’ve narrowed in on 6 user experience considerations that can help elevate your customer’s perception of your chatbot — and therefore your brand overall — from “meh” to “oooh!”

1. First Things First: Plan for Imperfection

Machine learning takes time. Just like we can’t expect a child to understand every sentence in a book, we can’t expect a brand-new bot to recognize 100% of user input. It’s part of the learning process, and bots need to be exposed to as much input as possible to improve responses in the future. Take a look at how even large companies can miss the mark at first:

From left: 1. GEICO provided irrelevant suggestions, even after rephrasing. 2. Levi’s “Indigo” didn’t plan for unlikely questions, providing a completely random message. 3. Capital One’s “Eno” recognized the keyword “damaged” but didn’t understand the grammatical context.

Instead of hoping for flawless AI from the start, plan for the inevitable mistakes. There are a few ways you can smooth out the experience:

• Set expectations at the beginning. Tell the customer the intended conversation topics (“I can help set up your account”) and confirm the possibility of real human interaction (“Or I’ll put you in touch with someone”). This can help clarify purpose and avoid assumptions that the bot has replaced interpersonal customer service.
• When responding to unrecognized inputs, provide next steps to avoid a dead end. You can reframe the question, ask to rephrase in a simpler way, provide suggested replies, or ask if they’d like to talk to a human.
• When necessary, disable open text altogether, and instead ask users to choose from pre-selected responses. This is a viable “phase 1” approach for many clients unfamiliar with AI, as it can be a sort of foot-in-the-door technique to evaluate the success of your chatbot before taking the leap to natural language processing.

From left: 1. “Resistbot” clarifies acceptable input with a fun emoji to lighten the mood. 2. The Chopra Foundation’s mental wellness bot explains that it’s still learning, asks the user to try again, and even tries reframing the question to prompt a new, understandable response. 3. Amazon’s Messaging Assistant restricts input to pre-selected buttons to avoid misunderstandings.

2. Accommodate Your Error-Prone Customers

Bots aren’t the only ones who make mistakes. Humans are, well … human. We get distracted, press incorrect buttons, we’re bad at spelling, we can be easily stressed or confused.

A range of solutions can accommodate human error, as there’s quite a range of potential mishaps. For starters:

• “Crap, I hit the wrong suggested message.” A simple undo, or a re-selection of the correct button, would suffice. But many bots either disable previous suggestions or hide them altogether, forcing the user to continue on the incorrect path, decide whether typing “go back” or the desired term might work, or even try refreshing the page.
• “Ugh, I spelled financial wrong again.” Not all browsers/devices/users enable autocomplete. Make sure your bot can recognize misspellings, and either assume the correct word and move on, or clarify when needed (“Did you mean financial assistance?”).
• “Um … I’m … lost.” Especially for chatbots that restrict input to pre-selected options, it’s important to provide options to get back to a familiar place. One simple way to do this is a “Start over” option, to get back to the welcome message and try again.

From left: 1. Dominos’ “Dom” keeps chat options enabled even after selection, allowing you to switch if you chose incorrectly or changed your mind. 2. Dulcolax’s assistant has a Start Over option, to go to the beginning of the chat at any time. 3. Planned Parenthood’s “Roo” seamlessly provides the user what they’re looking for without getting confused by the spelling mistake.

3. Craft a Seamless Transition From Bot to Human Agent

If your bot includes live chat integration, there are a couple of ground rules. Think of an in-store experience: just like the store clerk asking unwanted questions after you already said “Nope, just browsing,” make sure live service agents aren’t jumping in and invading users’ privacy. In the same vein, don’t be the store clerk in the back checking your phone when someone needs a different shoe size: Make sure that when the customer wants help, there’s an easy way to get connected.

There are a few things you can do to smooth the bot/human transition:

• Only initiate live chat if the user requests or agrees to it.
• Send a goodbye message from the bot, so the customer knows a switch is happening (“One second while I transfer you to an associate”).
• Make sure the service agent can see the user’s chat history with the bot, so they know what questions already have and have not been answered.
• Provide an ever-present way to request a live person: Giving an “out” if the user is lost. An icon, button, or menu item can do the trick. You can initiate the same transition if a user types “person,” “representative,” or a similar term.

From left: 1. Drift connected me with an agent before I could decline. Plus, using the VPN to detect the customer’s name or affiliation … can you say creepy? 2/3. Amazon’s Messaging Assistant consistently displays an agent icon. After confirming the customer’s intention, it immediately connects you

4. Tailor Conversations to Unique User Needs

Your users are individuals with distinct goals. They’re also used to the evolving landscape of personalized ads and recommendations. We may not know them personally, but there are some assumptions we can make from what we do know. For instance, a user searching your website for pricing information is in a much different mindset than a logged-in customer checking out your support FAQs.

One way to start personalizing chat content is by mapping what you know about customers — page, channel, search term, previous engagements, etc. — to safe assumptions about them such as journey stages, barriers, and needs. Based on that, greet the various customer groups with messaging and suggestions tailored to that setting.

This pharmaceutical example tailors messages and suggestive prompts based on the user’s channel and content section, or offers a generic message when that information is irrelevant. Additional ways to tailor conversations could be by previous page/channel visits, referring URL, demographic or target segmentation, and more. This can help customers think “Hey, nice, this is just what I needed!”

Approaches like this can make the customer feel like the brand is anticipating their goals and making support as easy as possible. But keeping in mind that assumed intentions aren’t always correct, make sure you always provide an open text field or another way to change topics.

5. Talk Like Your Customer’s Friend (But Maybe Not Best Friend)

With our short attention spans and love of laughter, humans like to be entertained — we send emojis, memes and gifs, react to messages, fire off quick tangents and share our streams of consciousness. Bringing life to your bot’s messaging through these familiar methods can undoubtedly spark joy and a stronger brand-audience connection.

While the level of personality will vary greatly for bots serving different purposes and audiences, one thing to keep in mind is to balance flair, fun and the task at hand. Users likely didn’t engage with your bot for pure entertainment — they have a goal or question in mind, and they’d like to accomplish it quickly. While you and your best friend may have 3 meme-based conversations at once, when chatting with a brand, make sure any amusing messages come at just the right time, enhancing rather than distracting.

From left: 1. Dulcolax’s assistant has tons of fun personality, but requiring the user to choose a tangential message before moving forward with a new question or topic slows them down and may distract from the task at hand. 2/3. Resistbot sends a native iOS confetti animation after the user signed a petition. Since the customer is still waiting for confirmation that the petition has been sent to officials, the animation serves as both success reinforcement and loading entertainment simultaneously.

6. Last But Far From Least: Sweat the Small Stuff

Let’s face it, chatbots are complicated. Once you’ve been in the weeds on what to recommend to a customer who just selected button 1.4.2 of flow 1.4, dialog 1, conversation A, it’s easy to overlook the fact that the customer can also get to that button from dialog 2, conversation B, and that the recommendation needs to make sense in both contexts, or that you need to decide to separate the recommendations in order to tailor them more appropriately. Whew. It’s important to balance the desire to customize every single message for your customer with the reality check of how big of a conversation tree you can manage. Take a look at how crazy just one can get:

A zoomed-out view of a conversation diagram. What can start as a single task or topic can quickly spiral into infinite branches and custom conversations.

Take time to imagine the experience of each possible conversation flow for the first time (your users definitely are). Does getting that recommendation from button 1.4.2 still make sense after conversations A and B? Does the language flow with similar tone, emotion and context if you skip past flow 2.3 and go directly to 2.4? The nitty-gritty of the flows may be a bit daunting, but spending time with as many use cases and journeys as you can count can ensure each customer receives that same level of simplicity, familiarity and delight as the next.

From planning for unrecognized text, human error, and live agent transitions, to personalizing content and poring over the amusing additions and details of each flow’s messaging, I hope you can take a couple of these pointers and enhance your users’ experiences with your chatbot. While many more nuances contribute to the implementation of a chatbot, keeping the above in mind can help you focus on the humanity of your users, and spark the so-great-I-have-to-tell-my-friend-about-it experience we all crave.

Thanks for reading! This piece was originally posted as a two-part series on intouchsol.com. You can check out those posts here: Part One and Part Two.