Last week, in Part One of this series, we touched on the ever-evolving era of chatbots amid COVID-19, with some tips on how to smooth out any hiccups between the key players: bot, customer and live agent. Now that you’re familiar with the lay of the land, let’s talk about how to elevate your customers’ experience even further, with personalized dialog, entertainment at the right time, and the utmost attention to details.
Tailor Conversations to Unique User Needs
Your patients, caregivers and healthcare professionals 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 patient searching a drug’s website for how much it costs is in a much different mindset than an on-script patient checking out the drug’s support-focused Facebook page. A nurse practitioner perusing the insurance and access pages doesn’t need the same conversation as a specialist with a product question.
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 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.
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 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.
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.
That concludes this two-part series. From planning for unrecognized text, human error and live agent transitions in Part One, to today’s discussion about personalizing content and poring over the amusing additions and details of each flow’s messaging, I hope you can take a couple of the pointers and enhance your users’ experiences with your chatbot. While many more nuances can go into a launch, especially depending on the channel at hand (SMS or voice assistants deserve a dedicated series of their own), 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.
Looking for chatbot 101? 10 Things Pharma Needs for a Successful Chatbot and Chatbots Are About to Transform Facebook are great places to start.
For more UX-pertise to inform your next project, reach out to Paul Kim (NY), email@example.com, Amy Toft (CHI) firstname.lastname@example.org, or Liz Corbin (KC) email@example.com
For more information on Cognitive Core, please contact Abidur Rahman (Innovation) firstname.lastname@example.org