{"id":934,"date":"2017-08-07T18:54:05","date_gmt":"2017-08-07T16:54:05","guid":{"rendered":"https:\/\/capturly.com\/blog\/?p=934"},"modified":"2020-06-09T11:53:08","modified_gmt":"2020-06-09T09:53:08","slug":"how-to-design-less-annoying-bots","status":"publish","type":"post","link":"https:\/\/capturly.com\/blog\/how-to-design-less-annoying-bots\/","title":{"rendered":"How to Build Trust for Chatbots With UX"},"content":{"rendered":"<p class=\"graf graf--p\"><em class=\"markup--em markup--p-em\">This article is a follow-up of the previous: <\/em><a href=\"https:\/\/capturly.com\/blog\/the-next-big-bang-in-ux\/\"><strong class=\"markup--strong markup--p-strong\"><em class=\"markup--em markup--p-em\">Why Bots are the next Big Bang in UX<\/em><\/strong><\/a><strong class=\"markup--strong markup--p-strong\"><em class=\"markup--em markup--p-em\">. <\/em><\/strong><em class=\"markup--em markup--p-em\">I closed the article with the introduction of the onboarding process, to be more specific, the importance of tutorials, which can be summarized this way:<\/em><\/p>\n<blockquote class=\"graf graf--pullquote graf--startsWithDoubleQuote\"><p><em class=\"markup--em markup--pullquote-em\">\u201cSo next time the user talks to the bot, it should be more like a conversation between friends who know each\u00a0other.\u201d<\/em><\/p><\/blockquote>\n<p class=\"graf graf--p\">So the bot in my example \u2014 poncho, the funny weather bot \u2014 ensures this by creating \u201chooks\u201d based on the preferences of the user. However, there\u2019s no guarantee that the person who is using it the first time will give precise information.<\/p>\n<blockquote class=\"graf graf--blockquote\"><p>That\u2019s why a good designer needs to think one step ahead.<\/p><\/blockquote>\n<p class=\"graf graf--p\">In this article, we\u2019re going to answer the following questions:<\/p>\n<ul class=\"postList\">\n<li class=\"graf graf--li\">What is a conversational funnel?<\/li>\n<li class=\"graf graf--li\">How to build trust and why is it\u00a0important?<\/li>\n<li class=\"graf graf--li\">What are the best practices that deliver a smooth user experience?<\/li>\n<\/ul>\n<blockquote class=\"graf graf--pullquote\"><p>Let\u2019s begin.<\/p><\/blockquote>\n<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_53 counter-hierarchy ez-toc-counter ez-toc-grey ez-toc-container-direction\">\n<div class=\"ez-toc-title-container\">\n<p class=\"ez-toc-title \" >Table of Contents<\/p>\n<span class=\"ez-toc-title-toggle\"><\/span><\/div>\n<nav><ul class='ez-toc-list ez-toc-list-level-1 ' ><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/capturly.com\/blog\/how-to-design-less-annoying-bots\/#Conversation_types_and_conversation_flow\" title=\"Conversation types and conversation flow\">Conversation types and conversation flow<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/capturly.com\/blog\/how-to-design-less-annoying-bots\/#How_to_build_trust\" title=\"How to build\u00a0trust?\">How to build\u00a0trust?<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/capturly.com\/blog\/how-to-design-less-annoying-bots\/#Implementing_Artificial_Intelligence\" title=\"Implementing Artificial Intelligence:\">Implementing Artificial Intelligence:<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/capturly.com\/blog\/how-to-design-less-annoying-bots\/#Conversation_best_practices\" title=\"Conversation best practices:\">Conversation best practices:<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/capturly.com\/blog\/how-to-design-less-annoying-bots\/#Conclusion\" title=\"Conclusion:\">Conclusion:<\/a><\/li><\/ul><\/nav><\/div>\n<h2 class=\"graf graf--h4\"><span class=\"ez-toc-section\" id=\"Conversation_types_and_conversation_flow\"><\/span>Conversation types and conversation flow<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p class=\"graf graf--p\">One of the hardest parts is to <a href=\"https:\/\/chatbotslife.com\/designing-chatbot-conversations-7fd94b2a78d8\">design the conversation flow<\/a>. There are two main types of conversations. The first is <strong class=\"markup--strong markup--p-strong\"><em class=\"markup--em markup--p-em\">task-led,\u00a0<\/em><\/strong>where the aim\u00a0is to accomplish certain goals while going through the conversational funnel. The second will be a <strong class=\"markup--strong markup--p-strong\"><em class=\"markup--em markup--p-em\">topic-led<\/em><\/strong> conversation; this type is different because it\u2019s more about entertainment.<\/p>\n<p class=\"graf graf--p\"><strong class=\"markup--strong markup--p-strong\">Task-led conversations:<\/strong><\/p>\n<p class=\"graf graf--p\">A good example could be when someone is buying lunch. It starts with a single task definition. Once we have a task, the process needs to be initialized.<\/p>\n<figure class=\"graf graf--figure\"><img decoding=\"async\" loading=\"lazy\" class=\"graf-image aligncenter\" src=\"https:\/\/cdn-images-1.medium.com\/max\/800\/1*V_Sdt_SLOdDEFHNNygetPQ.jpeg\" alt=\"Task-led conversations\" width=\"600\" height=\"200\" data-image-id=\"1*V_Sdt_SLOdDEFHNNygetPQ.jpeg\" data-width=\"600\" data-height=\"200\" \/><\/figure>\n<p style=\"text-align: center;\">Figure 1.<\/p>\n<p class=\"graf graf--p\">The initialization process can be divided into multiple subtasks. In our example, it could be something like this:<\/p>\n<figure class=\"graf graf--figure\"><img decoding=\"async\" loading=\"lazy\" class=\"graf-image aligncenter\" src=\"https:\/\/cdn-images-1.medium.com\/max\/800\/1*7rsyKVbiYA9ifzGYzepuqw.jpeg\" alt=\"initialization process\" width=\"800\" height=\"800\" data-image-id=\"1*7rsyKVbiYA9ifzGYzepuqw.jpeg\" data-width=\"800\" data-height=\"800\" \/><\/figure>\n<p style=\"text-align: center;\">Figure 2.<\/p>\n<p class=\"graf graf--p\">The same goes for the actual buying process:<\/p>\n<figure class=\"graf graf--figure\"><img decoding=\"async\" loading=\"lazy\" class=\"graf-image aligncenter\" src=\"https:\/\/cdn-images-1.medium.com\/max\/800\/1*NGKZjsHRzIsVssaBok-Ezg.jpeg\" alt=\"buying process \" width=\"600\" height=\"200\" data-image-id=\"1*NGKZjsHRzIsVssaBok-Ezg.jpeg\" data-width=\"600\" data-height=\"200\" \/><\/figure>\n<p style=\"text-align: center;\">Figure 3.<\/p>\n<p class=\"graf graf--p\">If everything goes according to the plan, the task is completed. However, as I mentioned before, we think and talk like humans and this is where it gets tricky.<\/p>\n<p class=\"graf graf--p\"><strong class=\"markup--strong markup--p-strong\">The conversation funnel<\/strong><\/p>\n<p class=\"graf graf--p\">When it comes to task-led conversations, I like to mention the conversation funnel. You might have heard about <strong><a href=\"https:\/\/blog.kissmetrics.com\/how-marketing-funnels-work\/\">the funnel term used in marketing<\/a><\/strong>. If we think about webshops, these describe the desired path that the visitors should go through in order to count as a customer. Needless to say, companies need to focus on <a class=\"markup--anchor markup--p-anchor\" href=\"https:\/\/capturly.com\/\" rel=\"noopener\" data-href=\"https:\/\/capturly.com\/\"><strong class=\"markup--strong markup--p-strong\">website optimization<\/strong><\/a> if they want to bring out the most of the funnel.<\/p>\n<p><button style=\"background-color: #25b2fa; color: #ffffff; width: 290px; height: 60px; border-radius: 50px; outline: transparent; padding: 8px; border: none; font-size: 0.9em; font-family: Quicksand, Arial, sans-serif; cursor: pointer; display: block; margin: 0px auto; text-align: center;\" type=\"button\"><strong>I WANT TO CONVERT<\/strong><\/button><\/p>\n<p class=\"graf graf--p\">During the design process, optimizing the different stages of the funnel is also important.<\/p>\n<figure class=\"graf graf--figure\"><img decoding=\"async\" loading=\"lazy\" class=\"graf-image aligncenter\" src=\"https:\/\/cdn-images-1.medium.com\/max\/800\/1*aVJcx7xE4sRXACYhnNVs0w.jpeg\" alt=\"optimizing the different stages of the conversion funnel\" width=\"622\" height=\"547\" data-image-id=\"1*aVJcx7xE4sRXACYhnNVs0w.jpeg\" data-width=\"622\" data-height=\"547\" \/><\/figure>\n<p style=\"text-align: center;\">Figure 4.<\/p>\n<p class=\"graf graf--p\">In the example shown in Figure 4, the goal of the task-led conversation is to guide the users through the funnel and optimize the conversion rate.<\/p>\n<p class=\"graf graf--p\"><strong class=\"markup--strong markup--p-strong\">Topic-led discussions:<\/strong><\/p>\n<p class=\"graf graf--p\">The biggest difference between task and topic-led conversations is\u00a0a number of steps. Unlike before, the main goal is to entertain\u00a0or, in other words, \u00a0to kill time. Instead of a certain path, the designer needs to define a set of topics. The topics are large datasets and the user is free to explore them\u00a0during the conversation. However, this doesn\u2019t mean that the user is thrown into the ocean. A good topic-led conversation has some sort of \u201canchor\u201d points. So it also has a structure that can look something like this:<img decoding=\"async\" loading=\"lazy\" class=\"graf-image aligncenter\" src=\"https:\/\/cdn-images-1.medium.com\/max\/800\/1*Le0QoZtAlWFsHgisc7Rzvw.jpeg\" alt=\"Topic-led discussions\" width=\"600\" height=\"200\" data-image-id=\"1*Le0QoZtAlWFsHgisc7Rzvw.jpeg\" data-width=\"600\" data-height=\"200\" \/><\/p>\n<p class=\"graf graf--p\" style=\"text-align: center;\">Figure 5.<\/p>\n<p class=\"graf graf--p\"><strong class=\"markup--strong markup--p-strong\"><em class=\"markup--em markup--p-em\">User: <\/em><\/strong>Which is your favorite transport vehicle in Star Wars?<\/p>\n<p class=\"graf graf--p\"><strong class=\"markup--strong markup--p-strong\"><em class=\"markup--em markup--p-em\">Bot: <\/em><\/strong>Bantha.. obviously.<\/p>\n<p class=\"graf graf--p\"><strong class=\"markup--strong markup--p-strong\"><em class=\"markup--em markup--p-em\">User:<\/em><\/strong> Lol, I kinda like the Sith Speeder, it\u2019s pretty fast and funny-looking at the same time. Remember when Darth Maul got on it?<\/p>\n<p class=\"graf graf--p\"><strong class=\"markup--strong markup--p-strong\"><em class=\"markup--em markup--p-em\">Bot:<\/em><\/strong> Darth Maul is a really cool character, not as cool as BB-8 though. Would you like to see some cool dual lightsaber designs?<\/p>\n<p class=\"graf graf--p\">When it comes to topic-led conversations, keeping up the interest can be easier because there is more room to navigate. In the example above, the conversation started around a dataset of vehicles then moved on to characters.<\/p>\n<h2 class=\"graf graf--h4\"><span class=\"ez-toc-section\" id=\"How_to_build_trust\"><\/span>How to build\u00a0trust?<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p class=\"graf graf--p graf--hasDropCapModel graf--hasDropCap\"><span class=\"graf-dropCap\">We<\/span> are humans, we think and talk as humans. For us,\u00a0<a href=\"http:\/\/www.virtualspirits.com\/how-to-build-chatbot-for-website-building-trust.aspx\">building trust is essential<\/a>. We can make decisions, change subjects without following a particular logical order. So the main problem with the human-bot interaction is that humans like to test bots in order to get to know\u00a0how \u201csmart\u201d it is. When the user starts this \u201cgame\u201d there\u2019s a high chance that the bot will fail at some point \u2014 even if it deals with huge datasets such as Amazon\u2019s inventory like Kip \u2014.<\/p>\n<figure class=\"graf graf--figure\"><img decoding=\"async\" loading=\"lazy\" class=\"graf-image aligncenter\" src=\"https:\/\/cdn-images-1.medium.com\/max\/800\/1*mq57VEyn-Yg7cCjCLfbyFA.jpeg\" alt=\"how to build trust with chatbots\" width=\"796\" height=\"510\" data-image-id=\"1*mq57VEyn-Yg7cCjCLfbyFA.jpeg\" data-width=\"796\" data-height=\"510\" \/><\/figure>\n<p style=\"text-align: center;\">Figure 6.<\/p>\n<p class=\"graf graf--p\">Going off topic is always a challenge and a designer has to face this sooner or later. However, this \u201cconflict\u201d isn\u2019t always a bad thing. Maintaining the \u201chuman-like\u201d factor in a conversation is expected and not impossible. A good practice can be decoration. This means that the designer adds sentences that have no direct influence on the conversation, but<\/p>\n<blockquote class=\"graf graf--pullquote\"><p>it adds characteristic to the bot or, in other words, more depth. This way the user can \u201cforget\u201d that he\/she\u2019s talking to a pile of\u00a0code.<\/p><\/blockquote>\n<p class=\"graf graf--p\"><strong class=\"markup--strong markup--p-strong\">Managing User exceptions:<\/strong><\/p>\n<p class=\"graf graf--p\">For humans, changing course in a conversation is not a big deal. Let\u2019s say the user goes through the initialization process without any problems and then suddenly wishes to revert back his\/her decision and pick something else.<\/p>\n<p class=\"graf graf--p\">The designer can handle these multiple ways:<\/p>\n<p class=\"graf graf--p\"><em class=\"markup--em markup--p-em\"><a href=\"https:\/\/ankitbko.github.io\/2017\/03\/human-handover-bot\/\">Routing the conversation to a human<\/a> <\/em>is<em class=\"markup--em markup--p-em\">\u00a0<\/em>probably the easiest and most transparent way. It can be a good alternative to course correction. A person who is in charge can suggest solutions to more complex questions. But there&#8217;s\u00a0the possibility that users will eventually \u201cexploit\u201d this feature by asking for human assistance in the future.<\/p>\n<p class=\"graf graf--p\"><em class=\"markup--em markup--p-em\">Course correction <\/em>is about how the bot can\u00a0climb out of awkward situations by taking the conversation back on track. Let&#8217;s say the user wants something else instead of the options available. Then an indirect course correction can save the outcome. These types of conversations are very common. For example, if you go to a restaurant and ask for\u00a0something that is not on the menu.<\/p>\n<p class=\"graf graf--p\"><strong class=\"markup--strong markup--p-strong\"><em class=\"markup--em markup--p-em\">User:<\/em><\/strong> Hi, I wanna eat something.<\/p>\n<p class=\"graf graf--p\"><strong class=\"markup--strong markup--p-strong\"><em class=\"markup--em markup--p-em\">Bot:<\/em><\/strong> Hello! What can I get you? Would you like to see the menu?<\/p>\n<p class=\"graf graf--p\"><strong class=\"markup--strong markup--p-strong\"><em class=\"markup--em markup--p-em\">User<\/em><\/strong>: Do you have Lasagne?<\/p>\n<p class=\"graf graf--p\"><strong class=\"markup--strong markup--p-strong\"><em class=\"markup--em markup--p-em\">Bot<\/em><\/strong>: We can\u2019t serve you Lasagne at the moment (our Chicken Enchilada is super delicious by the way), but I\u2019ll let the chef know about your wish and will notify you as soon as we have it on our menu!<\/p>\n<p class=\"graf graf--p\">This is much more appealing than simply repeating the same offer all over again.<\/p>\n<p class=\"graf graf--p\"><strong class=\"markup--strong markup--p-strong\">Extracting information<\/strong><\/p>\n<p class=\"graf graf--p\">Even a simple conversation can <a href=\"http:\/\/www.uxbooth.com\/articles\/chatbox-ux-crafting-a-valuable-conversation\/\">hold plenty of valuable, rich data<\/a>. We can define entities in multiple dimensions, for example, level of complexity or sensitivity.<\/p>\n<blockquote class=\"graf graf--blockquote\"><p>Let\u2019s say the user doesn\u2019t wait for the bot to even make the offer.<\/p><\/blockquote>\n<p class=\"graf graf--p\"><strong class=\"markup--strong markup--p-strong\"><em class=\"markup--em markup--p-em\">User: <\/em><\/strong>Hi, I wanna have some Lasagne!<\/p>\n<p class=\"graf graf--p\">It would be confusing to ask what the user wants and offer the menu just because of the sake of bot-logic. This is a great opportunity to extract entities. In this example, we have a simple and not sensitive information provided in the order. There could also be multiple entities present at the same time.<\/p>\n<p class=\"graf graf--p\"><strong class=\"markup--strong markup--p-strong\"><em class=\"markup--em markup--p-em\">User:<\/em><\/strong> Hi, I would like to have some Lasagne for dinner and delivered home.<\/p>\n<p class=\"graf graf--p\">If we look at the statement it holds the following entities:<\/p>\n<ul class=\"postList\">\n<li class=\"graf graf--li\">the exact type of food<\/li>\n<li class=\"graf graf--li\">a non-specified time<\/li>\n<li class=\"graf graf--li\">a non-specified location<\/li>\n<\/ul>\n<p class=\"graf graf--p\">The first two are simple and not sensitive, but the last entity is the exact opposite. It defines an address which is backed up with a large database that contains personal information about the user. For the user, this is nothing but ordering some food.<\/p>\n<blockquote class=\"graf graf--pullquote\"><p>However, for the bot this is a great opportunity to gather more data in order to provide a more personal user experience in the\u00a0future.<\/p><\/blockquote>\n<p class=\"graf graf--p\">On mobile and web interfaces, there are form-samples where the user has to fill out the required fields in a given structure and also there\u2019s a validation process involved. In conversations, validation is still a requirement, but the order of input doesn\u2019t always follow a certain pattern. Artificial intelligence frameworks usually have sophisticated entity extraction solutions that can handle validation.<\/p>\n<h2 class=\"graf graf--p\"><span class=\"ez-toc-section\" id=\"Implementing_Artificial_Intelligence\"><\/span><strong class=\"markup--strong markup--p-strong\">Implementing Artificial Intelligence:<\/strong><span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p class=\"graf graf--p\">It\u2019s a common misconception that Artificial Intelligence (AI) is the very core of bots. AI at its current state can be considered a set of tools that designers and developers can use while building all kinds of applications. In certain types of conversations, it is advised to use Artificial intelligence (AI). It helps to deal with complex conversations. However, it also adds some complexity.<\/p>\n<p class=\"graf graf--p\"><img decoding=\"async\" loading=\"lazy\" class=\" wp-image-939 aligncenter\" src=\"\/blog\/wp-content\/uploads\/2017\/08\/ai_1x-300x225.png\" alt=\"image_of_AI\" width=\"430\" height=\"323\" srcset=\"https:\/\/capturly.com\/blog\/wp-content\/uploads\/2017\/08\/ai_1x-300x225.png 300w, https:\/\/capturly.com\/blog\/wp-content\/uploads\/2017\/08\/ai_1x.png 400w\" sizes=\"(max-width: 430px) 100vw, 430px\" \/><\/p>\n<p class=\"graf graf--p\" style=\"text-align: center;\">Figure 7.\u00a0<span class=\"attribution \"><span class=\"shot-byline-user\">by\u00a0<a class=\"url hoverable\" href=\"https:\/\/dribbble.com\/Selimov\" rel=\"contact\">Andy Selimov<\/a><\/span><\/span><\/p>\n<p class=\"graf graf--p\"><strong>Example situations where AI can be useful:<\/strong><\/p>\n<ol class=\"postList\">\n<li class=\"graf graf--li\"><em class=\"markup--em markup--li-em\">Image recognition<\/em> \u2014 Probably the most common out there. It has proven itself in the past couple of years. It allows the recognition and analyzation of objects, faces, look for certain patterns in people\u2019s emotions, read the text and so on.<\/li>\n<li class=\"graf graf--li\"><a href=\"https:\/\/dzone.com\/articles\/bots-and-artificial-intelligence\"><em class=\"markup--em markup--li-em\">Natural language processing (NLP)<\/em><\/a>\u2014 this is especially effective when designing building a conversational environment. It helps to understand the\u00a0intents and extracting information from the conversation.<\/li>\n<li class=\"graf graf--li\"><em class=\"markup--em markup--li-em\">Conversation management<\/em> \u2014 this high-level AI not only is capable of extracting entities but also sees through the whole contexts.<\/li>\n<li class=\"graf graf--li\"><em class=\"markup--em markup--li-em\">Predicting the outcome <\/em>\u2014 This ability is essential to humans. We are able to tell what\u2019s right and wrong or the next move in a situation just by predicting the future outcome. Prediction APIs can analyze and learn certain patterns.<\/li>\n<\/ol>\n<p class=\"graf graf--p\"><strong class=\"markup--strong markup--p-strong\">Drawbacks of AI:<\/strong><\/p>\n<p class=\"graf graf--p\">Unless the situation really requires it \u2014 like managing pure text conversations \u2014 it can be an \u201coverkill\u201d. AI can be complex and, of course, expensive. Due to its complexity, it\u2019s hard to implement in a bot. Also, it needs a lot of time to learn and <a href=\"https:\/\/www.fastcodesign.com\/3054934\/the-next-phase-of-ux-designing-chatbot-personalities\">build up its\u00a0personality <\/a>before it can be productive.<\/p>\n<blockquote class=\"graf graf--pullquote\"><p>Most bots today don\u2019t use AI; instead, they guide the user with the help of rich interactions.<\/p><\/blockquote>\n<h2 class=\"graf graf--h4\"><span class=\"ez-toc-section\" id=\"Conversation_best_practices\"><\/span>Conversation best practices:<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<ol class=\"postList\">\n<li class=\"graf graf--li\"><em class=\"markup--em markup--li-em\">Shorthanding:<\/em>\u00a0it comes handy <a href=\"https:\/\/signalvnoise.com\/posts\/1926-a-shorthand-for-designing-ui-flows\">when designing UI flows<\/a>. If the user and the bot already \u201cknow\u201d each other, there is no reason not to use the extracted entities from before to build up a preference list that is unique to the user. Imagine yourself ordering your favorite pizza while not having to go through the whole process over and over again. Instead, all you have to say is: \u201cHi, I want the usual today!\u201d<\/li>\n<li class=\"graf graf--li\"><em class=\"markup--em markup--li-em\">Learning from the mistakes: <\/em>making mistakes is part of the game called life. Instead of making up excuses, a designer should analyze and prevent it from occurring in the future. Going through all the weak spots where the bot failed to satisfy the user\u2019s expectations is a great opportunity to learn more about the user and extract additional information for a more future-proof engagement.<\/li>\n<li class=\"graf graf--li\"><em class=\"markup--em markup--li-em\">Rich elements and expecting feedback: <\/em>additional pictures, GIFs, emojis, navigation buttons are additional elements that can make a conversation more interesting. In some cases, a single picture can express more information than multiple lines of text. A decent can provide this hybrid communication experience.<\/li>\n<\/ol>\n<blockquote class=\"graf graf--pullquote\"><p>But a bot really shines when it expects these rich interactions and feedback from the user and can react in the same\u00a0way!<\/p><\/blockquote>\n<h2 class=\"graf graf--h4\"><span class=\"ez-toc-section\" id=\"Conclusion\"><\/span>Conclusion:<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p class=\"graf graf--p\">A conversation between human beings can be task or topic-led. This applies to human-bot relations also. However, humans often go off-topic, change the logical order of the conversation and so on. Sometimes they do this just to test the \u201cpartner\u201d. If the bot fails to correct the course and pull the conversation back on track, the user might just end up leaving the conversation funnel. This means that building up trust is one of the main priorities and should be performed in an early stage. Managing user exceptions and building up a personalized experience from extracted information can be very effective when building trust. Many think that Artificial Intelligence is simply the essence of bots, but that\u2019s not true. AI can be considered as a set of tools for designers and developers and is mostly required in specific situations only.<\/p>\n<h5 class=\"graf graf--p\" style=\"text-align: center;\" data-trid=\"367\">What\u2019s your opinion on the topic? What would you like to read next? Please leave your thoughts and ideas in the comment section below. Also sharing is caring and keeps us motivated!<\/h5>\n","protected":false},"excerpt":{"rendered":"<p>This article is a follow-up of the previous: Why Bots are the next Big Bang in UX. I closed the article with the introduction of the onboarding process, to be more specific, the importance of tutorials, which can be summarized this way: \u201cSo next time the user talks to the bot, it should be more<\/p>\n","protected":false},"author":5,"featured_media":941,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[6],"tags":[21,81,80,87,40,85,88,42,39,10,13,86,11,9],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v20.13 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>How to Build Trust for Chatbots With UX - Capturly Blog<\/title>\n<meta name=\"description\" content=\"Managing user exceptions and building up a personalized experience from extracted information is effective when building trust with bots on your e-commerce website.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/capturly.com\/blog\/how-to-design-less-annoying-bots\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"How to Build Trust for Chatbots With UX - Capturly Blog\" \/>\n<meta property=\"og:description\" content=\"Managing user exceptions and building up a personalized experience from extracted information is effective when building trust with bots on your e-commerce website.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/capturly.com\/blog\/how-to-design-less-annoying-bots\/\" \/>\n<meta property=\"og:site_name\" content=\"Capturly Blog\" \/>\n<meta property=\"article:published_time\" content=\"2017-08-07T16:54:05+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2020-06-09T09:53:08+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/capturly.com\/blog\/wp-content\/uploads\/2017\/08\/cm_ct_illustration_1x.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"800\" \/>\n\t<meta property=\"og:image:height\" content=\"600\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Sophie\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Sophie\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"10 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/capturly.com\/blog\/how-to-design-less-annoying-bots\/\",\"url\":\"https:\/\/capturly.com\/blog\/how-to-design-less-annoying-bots\/\",\"name\":\"How to Build Trust for Chatbots With UX - Capturly Blog\",\"isPartOf\":{\"@id\":\"https:\/\/capturly.com\/blog\/#website\"},\"datePublished\":\"2017-08-07T16:54:05+00:00\",\"dateModified\":\"2020-06-09T09:53:08+00:00\",\"author\":{\"@id\":\"https:\/\/capturly.com\/blog\/#\/schema\/person\/d2fa9a6984d3c94b27710eb3307d4cdc\"},\"description\":\"Managing user exceptions and building up a personalized experience from extracted information is effective when building trust with bots on your e-commerce website.\",\"breadcrumb\":{\"@id\":\"https:\/\/capturly.com\/blog\/how-to-design-less-annoying-bots\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/capturly.com\/blog\/how-to-design-less-annoying-bots\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/capturly.com\/blog\/how-to-design-less-annoying-bots\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/capturly.com\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"How to Build Trust for Chatbots With UX\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/capturly.com\/blog\/#website\",\"url\":\"https:\/\/capturly.com\/blog\/\",\"name\":\"Capturly Blog\",\"description\":\"Optimize your website\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/capturly.com\/blog\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/capturly.com\/blog\/#\/schema\/person\/d2fa9a6984d3c94b27710eb3307d4cdc\",\"name\":\"Sophie\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/capturly.com\/blog\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/211636dc42cdb9c80a0ea48309f82b5e?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/211636dc42cdb9c80a0ea48309f82b5e?s=96&d=mm&r=g\",\"caption\":\"Sophie\"},\"url\":\"https:\/\/capturly.com\/blog\/author\/sophie\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"How to Build Trust for Chatbots With UX - Capturly Blog","description":"Managing user exceptions and building up a personalized experience from extracted information is effective when building trust with bots on your e-commerce website.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/capturly.com\/blog\/how-to-design-less-annoying-bots\/","og_locale":"en_US","og_type":"article","og_title":"How to Build Trust for Chatbots With UX - Capturly Blog","og_description":"Managing user exceptions and building up a personalized experience from extracted information is effective when building trust with bots on your e-commerce website.","og_url":"https:\/\/capturly.com\/blog\/how-to-design-less-annoying-bots\/","og_site_name":"Capturly Blog","article_published_time":"2017-08-07T16:54:05+00:00","article_modified_time":"2020-06-09T09:53:08+00:00","og_image":[{"width":800,"height":600,"url":"https:\/\/capturly.com\/blog\/wp-content\/uploads\/2017\/08\/cm_ct_illustration_1x.jpg","type":"image\/jpeg"}],"author":"Sophie","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Sophie","Est. reading time":"10 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/capturly.com\/blog\/how-to-design-less-annoying-bots\/","url":"https:\/\/capturly.com\/blog\/how-to-design-less-annoying-bots\/","name":"How to Build Trust for Chatbots With UX - Capturly Blog","isPartOf":{"@id":"https:\/\/capturly.com\/blog\/#website"},"datePublished":"2017-08-07T16:54:05+00:00","dateModified":"2020-06-09T09:53:08+00:00","author":{"@id":"https:\/\/capturly.com\/blog\/#\/schema\/person\/d2fa9a6984d3c94b27710eb3307d4cdc"},"description":"Managing user exceptions and building up a personalized experience from extracted information is effective when building trust with bots on your e-commerce website.","breadcrumb":{"@id":"https:\/\/capturly.com\/blog\/how-to-design-less-annoying-bots\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/capturly.com\/blog\/how-to-design-less-annoying-bots\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/capturly.com\/blog\/how-to-design-less-annoying-bots\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/capturly.com\/blog\/"},{"@type":"ListItem","position":2,"name":"How to Build Trust for Chatbots With UX"}]},{"@type":"WebSite","@id":"https:\/\/capturly.com\/blog\/#website","url":"https:\/\/capturly.com\/blog\/","name":"Capturly Blog","description":"Optimize your website","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/capturly.com\/blog\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/capturly.com\/blog\/#\/schema\/person\/d2fa9a6984d3c94b27710eb3307d4cdc","name":"Sophie","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/capturly.com\/blog\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/211636dc42cdb9c80a0ea48309f82b5e?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/211636dc42cdb9c80a0ea48309f82b5e?s=96&d=mm&r=g","caption":"Sophie"},"url":"https:\/\/capturly.com\/blog\/author\/sophie\/"}]}},"_links":{"self":[{"href":"https:\/\/capturly.com\/blog\/wp-json\/wp\/v2\/posts\/934"}],"collection":[{"href":"https:\/\/capturly.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/capturly.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/capturly.com\/blog\/wp-json\/wp\/v2\/users\/5"}],"replies":[{"embeddable":true,"href":"https:\/\/capturly.com\/blog\/wp-json\/wp\/v2\/comments?post=934"}],"version-history":[{"count":22,"href":"https:\/\/capturly.com\/blog\/wp-json\/wp\/v2\/posts\/934\/revisions"}],"predecessor-version":[{"id":3894,"href":"https:\/\/capturly.com\/blog\/wp-json\/wp\/v2\/posts\/934\/revisions\/3894"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/capturly.com\/blog\/wp-json\/wp\/v2\/media\/941"}],"wp:attachment":[{"href":"https:\/\/capturly.com\/blog\/wp-json\/wp\/v2\/media?parent=934"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/capturly.com\/blog\/wp-json\/wp\/v2\/categories?post=934"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/capturly.com\/blog\/wp-json\/wp\/v2\/tags?post=934"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}