<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
    <channel>
        <title><![CDATA[Stories by Katie Johnson on Medium]]></title>
        <description><![CDATA[Stories by Katie Johnson on Medium]]></description>
        <link>https://medium.com/@katiejohnson_3234?source=rss-3a33fa4b1bb6------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/1*V8gsOvjz3QeDzyoFRkZffw@2x.jpeg</url>
            <title>Stories by Katie Johnson on Medium</title>
            <link>https://medium.com/@katiejohnson_3234?source=rss-3a33fa4b1bb6------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Fri, 20 Nov 2026 21:16:17 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@katiejohnson_3234/feed" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[Golidlocks & the 3 bots - Using Storytelling to Build Bots that Span Generations]]></title>
            <link>https://medium.com/@katiejohnson_3234/golidlocks-the-3-bots-using-storytelling-to-build-bots-that-span-generations-2b1784cd36fe?source=rss-3a33fa4b1bb6------2</link>
            <guid isPermaLink="false">https://medium.com/p/2b1784cd36fe</guid>
            <category><![CDATA[design-thinking]]></category>
            <category><![CDATA[bots]]></category>
            <category><![CDATA[ai]]></category>
            <category><![CDATA[chatbot-design]]></category>
            <category><![CDATA[design]]></category>
            <dc:creator><![CDATA[Katie Johnson]]></dc:creator>
            <pubDate>Mon, 23 Apr 2018 12:59:00 GMT</pubDate>
            <atom:updated>2018-04-23T14:15:59.707Z</atom:updated>
            <content:encoded><![CDATA[<p>Missed my presentation at the MoNage Conference? The following is a modified version of my presentation on building bots using storytelling techniques. Enjoy!</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/936/1*XXzXQrX0L4HBtCheahfgxA.png" /></figure><p>Over the past few years, storytelling has proven to be an important technique in designing engaging user experiences. Today, we are seeing it used more and more in our designs of bots. But what is storytelling in bot form and why is it important? Storytelling in bot form tends to revolve around the experience and journey that the user is taken on while interacting with your bot. Whether it’s a chat or voice bot, storytelling is a great way to enhance the user experience and keep your users engaged in the conversation until the very end. It’s also a great way to accommodate for a wide range of user personas. Companies often time have a number of different user personas that they need to design their bots for while still making the experience personalized and tailored to the user. It’s very common for companies to have between 3 and 5 different user personas that they want to focus on when designing and building out their bots. I use storytelling techniques that will help meet the needs of many different types of users while improving NPS scores and customer engagement and retention rates.</p><p>There are a number of different techniques that you can use to enhance your bot and make them more enjoyable, but before we can even think about storytelling techniques, we must first understand our user’s needs and desires through design thinking. We can use design thinking workshops and methodologies to uncover the needs of users. It’s helpful to break down our user’s needs and focus on these categories while asking questions about our user’s needs so we can design bots that provide great experiences.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/936/1*AzJHdkyT1zrU50n2gNrfpg.png" /></figure><ul><li>Understanding the User’s Journey — How is the user interacting with technology along their journey with your brand? What is the end goal of the user?</li><li>Digital Experience (Native vs. Naïve) — How comfortable is your user with interacting with technology? How comfortable are they interacting with a bot? Can we predict how confident they will be using our bot?</li><li>Preferred Channel (Smart Home Devices, SMS, Chat, Voice, Social Media Platforms, Slack, etc.) — What channel does your user interact with most frequently? Do we need to build a bot that can cross over multiple channels? Uncovering preferences and identifying how your user wants to be engaged on their preferred platform is important for engagement.</li><li>Design Elements for Each Channel — How do you want to tell your story? Not all channels are created equal and shouldn’t be designed for as equals. For example, using visuals, buttons, streaming videos, and image swiping and scrolling can be powerful storytelling techniques for chat channels whereas voice channel conversations will need to break down more complex steps and make information such as credit cards and phone numbers at a more consumable rate for your users. Playing with tone of voice to express excitement or disappointment can also enhance the user experience for voice solutions.</li></ul><p>It’s important to realize that not all techniques are applicable for each industry or use case. For example, we may not need all of these design elements for the use case or we may not focus on one of these preferred channels if the user group doesn’t spend much time on it. In a tech support use case, we may want to primarily focus on building out streaming instructional video content or image recognition to recognize products. Understanding the needs of your users will be important for designing your story.</p><p>Now that we understand who the user is and what their needs are, we can explore different storytelling techniques to use to build our your bot. You’ll want to consider all of the following elements that can be used to enhance your bot and help tell your brand’s story.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/928/1*Qsq1Ko3WdbFObObjzyaKqg.png" /></figure><ul><li>Tone — Consider a formal vs. informal bot depending on your targeted user. For an informal bot, you may consider including and capturing emojis as sentiment, which may be a great addition for our millennial and gen z user persona. Although most financial institutions take a more formal approach to tone, some banks and mortgage companies have taken a more casual language and tone approach to targeting millennials.</li><li>Personality — Creating a bot that is engaging, encouraging, gives the user confirmation and affirmation will have huge effects on the success of your bot. With a bot, you have the unique ability to have a direct conversation with your end user that consistently represents the brand of your company.</li><li>Visuals (Maps, Graphics, Buttons, Videos) — These are great for storytelling and bringing your experience to life. It helps to break up a monotonous dialog experience and give some points of interaction with your end users that increases user sentiment scores.</li><li>Variations — Giving your bot multiple response variations will make the conversation flow more smoothly giving human like qualities to your bot. If one step of your conversation proves to be more challenging, add a variation that gives more explanation or if one step continues to get repeated, consider having an alternative response that breaks down the dialog and guides the users through more complex steps.</li><li>Personalization — In bot building, context is key for personalization. The more information we know and can leverage to create a simple and seamless experience, the better. Knowing your customer and having the ability to pull information into your conversation when you can will create a more personalized experience that will be sure to impress your end user.</li><li>Fallbacks/Repeats — It’s always important to have a fallback and repeat option in your design allowing users to get the necessary help when they need it most. You can use command options for repeats or getting in touch with a live agent when necessary.</li></ul><p>It’s possible to incorporate all of these elements into the design of your bot and as a designer, you should consider all of these techniques to improve the user experience but remember that some of these may not be necessary for your users so before you start to build, get to know your user and what their needs are in order to design a superb user experience. As we learn more about the user as they are going through the experience we pick up context and their needs and we can tailor their experience using context and logic that will allow the user to have an experience that fits their needs.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/936/1*jJkGj0aE1NTzLEYXWO6GUQ.png" /></figure><p>Designing a great user experience for your bot can have really positive effects for your business including higher net promoter scores, increased user engagement rates, reduced handle time, and increased brand awareness just to name a few. From the initial design and build phases until the launch of your bot, it is important to continue to iterate and redesign based on user interactions. Learning how users interact with your bot is essential to growing your bot into maturity. Remember that each user interaction is a chance to get to know your end user so continue to evolve with your users to constantly improve your experience. Feedback is a gift and a great way to get design ideas and make changes that will improve the overall experience.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/936/1*LIgM--Eo9AWbwYxyMAUu2g.png" /></figure><p>This article is a reflection of my own thoughts and experiences as a bot designer, and are not necessarily an IBM point of view.</p><p>Have a questions or want to talk bots? Reach out out to me on LinkedIn in or via email!</p><p>Want to learn more about the MoNage Conference? Check it out here: <a href="https://www.monage.io/">https://www.monage.io/</a></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=2b1784cd36fe" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[My best practices for designing and building great customer service chatbots]]></title>
            <link>https://blog.chatbotslife.com/my-best-practices-for-designing-and-building-great-customer-service-chatbots-55ffda43ab63?source=rss-3a33fa4b1bb6------2</link>
            <guid isPermaLink="false">https://medium.com/p/55ffda43ab63</guid>
            <category><![CDATA[ai]]></category>
            <category><![CDATA[bots]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[chatbots]]></category>
            <category><![CDATA[technology]]></category>
            <dc:creator><![CDATA[Katie Johnson]]></dc:creator>
            <pubDate>Thu, 22 Jun 2017 13:45:34 GMT</pubDate>
            <atom:updated>2017-06-22T16:50:18.037Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/752/1*IGCuCe8odD5qF_Q8fA47QA.jpeg" /><figcaption>Photo source: <a href="http://suggestive.com/5-predictions-future-human-race/">http://suggestive.com/5-predictions-future-human-race/</a></figcaption></figure><p>Conversational interfaces focusing on customer service or task oriented virtual agents have become an entry point for many companies into the world of AI. When it comes to customer service, you may have thought of the hours wasted dialing into a customer support line taking minutes to be routed to the correct person and finally having to explain your issues after you’ve just had a tumultuous experience getting someone on the phone. This mind-numbing experiencing is ripe for AI injection.</p><p>Companies are now starting to take the first step in initiating their AI journey by taking this experience and turning it into one of ease, self-service and proactive care guiding the customer through a journey and answering questions before they knew they had the question rather than the more traditional reactive customer support methodologies.</p><p><a href="https://www.eventbrite.com/e/the-chatbot-conference-tickets-34868758395?aff=CBL">The Chatbot Conference</a></p><p>Over the past two years I’ve been building bots. I’ve built virtual agents focused on customer services and virtual assistants focused on helping people accomplish certain tasks. Here are some of the things that I have found most helpful in building bots in addition to some of my best lessons learned:</p><p><strong>Keep it simple</strong></p><p>The truth is, people are busy. We value when things are done for us and when things get done without a lot of headaches, especially in customer support. This is a great lesson when building a customer service bot. Keep it as simple as possible. From the process to the conversation itself, keep it simple. Try to minimize the number of steps a user must go through in order to reach their end goal. There is nothing more frustrating than having an end goal and having to take an exorbitant amount of steps to get there. Always think less is more- fewer clicks, less typing and more interface features. This includes keeping users engaged on one interface. If you have external content, embed the experience within the chat eliminating the need to switch browsers or open additional apps. This may require additional work in terms of reformatting, revising or even writing new content completely, but will keep users engaged and lead to a better experience. Within your bot, allow users to interact with buttons, images, carousel cycle options and even a countdown of steps to the end goal, keeping them engaged and task oriented. Your interface and interaction with your end user is just as important as the backend process you’re building it for, maybe even more so.</p><p><strong>Technology and infrastructure are critical, but not to your user</strong></p><p>Having the technology and infrastructure to support your bot should be a no brainer from a user’s perspective. Although this is most likely where the bulk of your time building your bot will be, the end user doesn’t care what’s going on behind the scenes, they care about getting their work done and doing so quickly. When you’re creating a bot, focus on your end user and build a strong technological foundation and secure NLP service to support it. Your chatbot should be able to not only handle simple Q&amp;A, but also more complex dialog flows incorporating conversation context, personalization, and a wide range of responses chosen at random that make your bot appear more human. As a user, I always want my life to be made simpler by the use of technology, not more difficult (read technical). Having a great experience with a brand’s bot is the best way to create loyalty. I recommend starting off your project with a Design Thinking workshop focusing on identifying your user personas and the journey they will set out on. This will help to identify feasible short term design elements as well as long term visionary moonshots that may take more effort, or may not be feasible at all. The idea is to not only think about the current challenges users face, but to start thinking about the ideal pathway to get there, even if it includes hitching a ride on a spaceship.</p><p><strong>Take users on a journey</strong></p><p>When building your bot, you have an end goal in mind, a process you’re trying to accomplish with the user flow you are creating. Remember though that every step of the way is important. Having a clear purpose in what your end goal is will help build trust with users when engaging with your bot. It’s critical to keep your end user engaged, because it’s very easy for a user to bail out of a conversation and never come back. Don’t let users get stuck in a never ending looping conversation. It will lead to a frustrating user experience and you’ll risk losing that customer or cause them to not want to interact with your bot again. You only get one shot at this. If you fail the first time, they rarely come back. When users get frustrated, I like to have a fall back and way to exit the conversation for additional help. This obviously isn’t the ideal scenario for accomplishing your goal, but make sure you’re taking care of your end user providing an experience that will get the them help while creating brand loyalty due to a great customer experience.</p><p><strong>Customer service should be a concierge service</strong></p><p>One simple thing to keep in mind: no one wants to sit on the phone for hours or press 0 until you get a human. This is frustrating, I know. As a developer, you want to change human behavior. You want to take a user through a dialog to solve their problem without intervention. Your bot should have a fallback plan. Sometimes you can’t solve every problem so you need to defer to a human agent for assistance. This is normal, but when it comes to getting that person the help they need, make it a concierge service. Provide a simple way to set up a time to call the customer back or schedule a visit. If chat is your preferred platform, enable your chatbot to seamlessly transfer to a live chat agent in times of escalation. Don’t make your customer jump through more hoops to get in touch with someone.</p><p><strong>Customer service tends to be a battle</strong></p><p>How many times have you gone into a customer service scenario expecting to get something for free or wanting to win some kind of battle. Rather than preparing for a battle scene out of <em>Gladiator</em>, build in options that will delight your customer and make them feel like they are winning at the end of the experience. We all want to walk out of a customer service experience feeling light, happy and a winner. Building out these options will create a sense of relief that is very much needed in customer service and will keep users coming back for additional products. Set parameters for at risk users and build in the opportunity to offer “a promotion” for their poor experience with your product to reduce turnover of favorable customers.</p><p><strong>Be proactive when you can</strong></p><p>When you’re given the ability to create a personalized experience, use context to create a proactive experience rather than reactive. If you know your user is asking about their warranty and you see they are currently within their warranty period, present potential options of next actions for the user to take. Are they wanting to extend their warranty? Are they wanting to get service for their product? Be proactive and think about what the user really wants to do next. It’s important to guide your user down a path of action items and executions but stay to their script, not yours.</p><p>Above all, learn from your failures, iterate from your initial design to fit how people are interacting with your bot and don’t be afraid to pivot. Analyze how your users are interacting with your bot and how they are asking questions then make changes to fit their needs. There are infinite uses of chatbots and since it is relatively new in the industry, treat your bot like an experiment where you can learn how users interact and ask questions then continue to improve your design.</p><p><em>This article is from my own personal viewpoint and experience building bots. It does not reflect the views of IBM or the Watson Cognitive &amp; Analytics practice. If you’d like to discuss AI, chatbots or industry trends further, shoot me an email or connect with me on LinkedIn!</em></p><p><a href="https://www.linkedin.com/in/katherinegjohnson/">Katie Johnson (Greater New York City Area) on LinkedIn | LinkedIn</a></p><p><em>Author Note: Bots can be deployed on various channels including web, mobile, voice, phone, SMS, etc. My primary experiences has been focused on deploying bots via web, text and voice channels.</em></p><iframe src="https://cdn.embedly.com/widgets/media.html?src=https%3A%2F%2Fupscri.be%2F3e59ef%3Fas_embed%3Dtrue&amp;dntp=1&amp;url=https%3A%2F%2Fupscri.be%2F3e59ef&amp;image=http%3A%2F%2Fapi.screenshotlayer.com%2Fapi%2Fcapture%3Faccess_key%3Dfe59908dad3baab69ffab249a2224b03%26viewport%3D1024x612%26width%3D1000%26url%3Dhttps%253A%252F%252Fupscri.be%252F3e59ef%253Fscreenshot&amp;key=a19fcc184b9711e1b4764040d3dc5c07&amp;type=text%2Fhtml&amp;schema=upscri" width="800" height="400" frameborder="0" scrolling="no"><a href="https://medium.com/media/7078d8ad19192c4c53d3bf199468e4ab/href">https://medium.com/media/7078d8ad19192c4c53d3bf199468e4ab/href</a></iframe><figure><a href="https://chatbotslife.com/bot-communities-mastermind-group-d2dae9876709#.53x0py6ou"><img alt="" src="https://cdn-images-1.medium.com/max/255/1*6XUspT9JOSq0w0Fi35HIaA.png" /></a></figure><figure><a href="https://m.me/ChatbotsLife"><img alt="" src="https://cdn-images-1.medium.com/max/255/1*c1LDMH5vbnIz9rmAka8Hwg.png" /></a></figure><figure><a href="https://chatbotslife.com/how-to-get-a-free-chatbot-b1fb9dfe109#.z9dtp2sy0"><img alt="" src="https://cdn-images-1.medium.com/max/255/1*D0Jf3dI6ZThtqcfwDYY7mg.png" /></a></figure><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=55ffda43ab63" width="1" height="1" alt=""><hr><p><a href="https://blog.chatbotslife.com/my-best-practices-for-designing-and-building-great-customer-service-chatbots-55ffda43ab63">My best practices for designing and building great customer service chatbots</a> was originally published in <a href="https://blog.chatbotslife.com/">Chatbots Life</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
    </channel>
</rss>