Amazon provides bot support via its messaging channel, which is accessed via its website or on the Amazon mobile app. When seeking support, customers must first submit a query within Amazon\u2019s knowledge base. An option to \u2018contact us\u2019 is then provided on the knowledge base search results page, which directs to options for messaging or phone-based support.<\/p>\n\n\n\n
Amazon\u2019s messaging experience isn\u2019t quite asynchronous. At Helpshift, we consider an asynchronous messaging experience to be one where you can leave and come back to the conversation at your leisure \u2014 so you can do a grocery run while you wait for an agent and jump back into the conversation when you get back.<\/p>\n\n\n\n
With Amazon\u2019s messaging experience, you can leave and come back and still see all of the previous interactions you\u2019ve had with chatbots (although we did encounter some issues getting older messages to load and display). However, if you need help from an agent, the experience becomes session based. You have to stay in the messaging environment and complete the conversation then and there. Additionally, on the mobile app, responses from an agent don\u2019t result in a push notification, reinforcing the need to keep the messaging session open.<\/p>\n\n\n\n
To get the most out of chatbots and other forms of automation, we recommend using an asynchronous messaging environment.<\/p>\n\n\n\n
The sections that follow will provide a summary of features within three broad categories and provide a score for each. Scores are out of 5, so a perfect score is 15. Here\u2019s a scoring rubric for your reference:<\/p>\n\n\n\n
<\/p>\n\n\n\n For chatbots to be helpful, they need to first understand the context of the customer\u2019s issue and then proactively provide the customer with a path to resolution \u2014 whether that be by providing self-help resources or transferring to the right bot or agent that can help resolve the issue.<\/p>\n\n\n\n When first entering Amazon\u2019s messaging experience, a bot immediately greets you and explains a bit about how you can interact with it. It also provides several options for the customer to tell it what their issue is about. Additionally, the customer can free-type to describe their issue, which is then analyzed by an AI to route their issue to the appropriate bot or agent.<\/p>\n\n\n\n We took the time to test out both options to see how Amazon\u2019s bot performed.<\/p>\n\n\n\n The chatbot provided us with the following options upfront:<\/p>\n\n\n\n These options seem to cover the most common questions that customers ask. We selected \u2018Kindle, Fire, and Alexa devices\u2019. This brought us into a workflow that asked us about common issues and surfaced text that appeared to be from Amazon\u2019s knowledge base to troubleshoot. The bot then escalates to an agent when we chose the option that we were still experiencing connection issues.<\/p>\n\n\n We also wanted to test Amazon\u2019s AI capabilities by free-typing a few queries. These surfaced a few interesting results:<\/p>\n\n\n\n Query 1 – Where are my earplugs?<\/strong><\/p>\n\n\n\n Asking this question, the bot immediately recognizes that this is a query related to a specific item previously ordered. In this case, a pair of reusable ear plugs (San Francisco can be noisy!). The bot immediately presents the earplugs order as a single option to select and then, once selected, the bot advises that the item was delivered on the 21st of August and then offers additional options to select. We also tested the query \u2018where is my order?\u2019 and were taken down the same path, although we were presented with more order options.<\/p>\n\n\n\n The fact that we were presented only with the earplugs order when specifically asking about them suggests that Amazon\u2019s AI is smart enough to return specific orders based on the customer\u2019s query.<\/p>\n\n\n\n Query 2 – I didn\u2019t receive my order<\/strong><\/p>\n\n\n\n While this query seems like it\u2019s similar to \u2018where is my order?\u2019 Amazon\u2019s AI actually treated the query slightly differently, apparently understanding the slight nuance of asking \u2018where\u2019 to saying something wasn\u2019t received. In this case, the bot returns options based on missing or damaged items. Ostensibly, this is because Amazon often packages different items together, so if a customer didn\u2019t \u2018receive\u2019 an item it may be that it wasn\u2019t in the box with other items.<\/p>\n\n\n Query 3 – I need a Christmas card for my cousin<\/strong><\/p>\n\n\n\n We tested this query to see if Amazon\u2019s bot would help with product suggestions. The short answer to this is no. Asking about Christmas cards surfaced options for gift cards. Similarly, asking about a beach umbrella immediately resulted in a transfer to an agent. Apparently, Amazon\u2019s bot isn\u2019t a fan of sun and sand. <\/p>\n\n\n\n Helpshift score: 5.0 <\/strong><\/p>\n\n\n\n Overall Amazon\u2019s chatbot quickly understood our issue and proactively surfaced resources and options towards resolution. Typed queries were generally well understood, although not programmed to give product suggestions.<\/p>\n\n\n\n Ultimately, chatbots are only useful if they\u2019re easy for customers to use and can offer a more efficient experience compared to speaking directly with an agent. Beyond contextual understanding and proactivity, chatbots need to take a customer down a logical and seamless path to resolution \u2014 avoiding bottlenecks, delays or the dreaded frustration loop of \u2018sorry, I don\u2019t understand, can you rephrase your question?\u2019 over and over again with no escape. In terms of efficiency, a good bot should waste as little of the customer\u2019s time as possible by providing pertinent information up front without the customer having to dig around.<\/p>\n\n\n\n Luckily, a member of our team recently ordered a sheet set on Amazon but received the wrong color \u2014 a perfect opportunity to throw another test at Amazon\u2019s chatbots.<\/p>\n\n\n\n We followed the same process as before with the earplugs and selected the option for \u2018return or replace item\u2019. This triggered the returns self-help page to open in a new tab. However, when we attempted to request an exchange we ran into a hiccup where we weren\u2019t given an option to choose a different color \u2014 instead we were given the option to exchange for completely unrelated items.<\/p>\n\n\n\n This was not ideal, so we then went back to the messaging environment and selected the agent option, which was a nondescript icon at the bottom of the thread of a person wearing a headset. An agent came on-line within less than a minute and quickly let us know that, for reasons unknown, the item was not eligible for exchange. We were sent a return label via email and the team member was able to re-order the correct color sheets.<\/p>\n\n\n Overall, with both this and preceding examples, Amazon\u2019s chatbot experience followed a logical flow that ultimately got us to a resolution. The bot and messaging environment also offer a few options for easy escalation to an agent, either by asking if more help is needed and providing corresponding options (No, that\u2019s all; Yes, I have a different question), an agent icon at the bottom of the chatbox (although it comes and goes depending on the interaction) or by simply replying \u2018agent\u2019 to the bot.<\/p>\n\n\n\n Despite the overall ease of use, we did find it interesting that Amazon\u2019s chatbot wasn\u2019t able to retrieve information related to a specific product\u2019s return or exchange restrictions. Had the chatbot known that the sheet set wasn\u2019t eligible for exchange, it could have automatically provided this information along with a return label without the need for us to speak with an agent. This would have lead to a much more efficient support experience overall.<\/p>\n\n\n\n Other features that add to ease of use and efficiency include the aforementioned features, such as the ability (in most cases) to leave the chat and come back to it later, the ability to switch from desktop to mobile, and the ability to free-type queries.<\/p>\n\n\n\n One major feature that is important for improving ease of use and efficiency, but that was missing from Amazon\u2019s chatbot experience, is feedback collection at the end of every interaction. Implementing this is as simple as programming a bot to collect feedback before a ticket is closed (How would you rate your support experience?). <\/p>\n\n\n\n Helpshift score: 4.0<\/strong><\/p>\n\n\n\n The chatbot experience is generally easy and intuitive for customers to use. However, the bot could have provided additional information about returns and exchanges. Also, there was no option to provide feedback.<\/p>\n\n\n\n One aspect of chatbots that can make a big impact on the customer experience is their persona and ability to empathize with customers. Of course, chatbots are pre-programmed by human beings, so customer service teams need to make sure that they translate the brand voice and tone over to their chatbots in order to create a consistent experience for customers.<\/p>\n\n\n\n Chatbot personas can range from bland to silly \u2014 with some brands employing a mascot as their chatbot, such as an animal. Others try to pass their bot off as a real person, which we don’t recommend. Likewise, how a chatbot responds to customers can also vary, with some brands opting for witty replies while others prefer drier responses. Regardless of the persona and voice a brand chooses for its chatbots, at the very least they should be friendly and employ a helpful and empathetic tone of voice.<\/p>\n\n\n\n Amazon certainly opted for pragmatism here. Their chatbot doesn\u2019t have a specific persona or name and simply refers to itself as a \u2018messaging assistant\u2019. Likewise, responses are plain but helpful with a conversational tone (\u201cok,\u201d \u201cso,\u201d \u201csure,\u201d \u201clet\u2019s see\u201d). In terms of empathy, the chatbot did offer a light apology when we indicated items were missing or otherwise not what we expected. <\/p>\n\n\n\n Helpshift score – 5.0<\/strong><\/p>\n\n\n\n While not cracking Dad jokes, Amazon\u2019s chatbot is friendly, helpful and empathetic.<\/p>\n\n\n\n Overall score – 14\/15<\/strong><\/p>\n\n\n\n We gave Amazon\u2019s chatbot an overall score of 14 out of 15, which is outstanding when you consider that chatbot technology is still relatively new and many brands have struggled to implement them properly.<\/p>\n\n\n\n Here\u2019s a quick breakdown:<\/p>\n\n\n\n <\/p>\n\n\n\n <\/p>\n\n\n\n Strengths<\/strong> – Amazon\u2019s chatbot is ultimately a net positive to Amazon\u2019s overall customer experience. If the point of a chatbot is to provide a better experience than a person for routine issues, than Amazon\u2019s chatbot does just that. Options that were provided throughout the experience followed a logical flow towards resolution and the bot was generally proactive in providing pertinent information as well as an easy escalation path to an agent if needed.<\/p>\n\n\n\n Weaknesses <\/strong>– Currently, Amazon\u2019s chatbots don\u2019t provide product suggestions based on a customer\u2019s query, which may be a missed opportunity. The chatbot also wasn\u2019t able to retrieve information specific to a product that would have saved us time on our particular issue. The chatbot also doesn\u2019t ask customers to provide feedback on their experiences.<\/p>\n\n\n\n We hope you\u2019ve found this first Bot Wars battle useful in understanding what a great chatbot experience should look like. Stay tuned for the next installment of Bot Wars coming next month! <\/p>\n","protected":false},"excerpt":{"rendered":" In a messaging experience not far away\u2026 …and actually as close as your pocket, there\u2019s a chatbot ready to help you with any issue that you might be having with…<\/p>\n","protected":false},"author":2,"featured_media":23339,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"content-type":"","inline_featured_image":false,"_kad_blocks_custom_css":"","_kad_blocks_head_custom_js":"","_kad_blocks_body_custom_js":"","_kad_blocks_footer_custom_js":"","_kad_post_transparent":"","_kad_post_title":"","_kad_post_layout":"","_kad_post_sidebar_id":"","_kad_post_content_style":"","_kad_post_vertical_padding":"","_kad_post_feature":"","_kad_post_feature_position":"","_kad_post_header":false,"_kad_post_footer":false,"footnotes":"","_links_to":"","_links_to_target":""},"categories":[178],"tags":[201,254],"table_tags":[],"acf":[],"taxonomy_info":{"category":[{"value":178,"label":"Chatbots"}],"post_tag":[{"value":201,"label":"automation"},{"value":254,"label":"chatbots for customer service"}]},"featured_image_src_large":["https:\/\/www.helpshift.com\/wp-content\/uploads\/2022\/04\/HELP_Bot_Wars_Blog_Image_800x600_L1R1.png",800,600,false],"author_info":{"display_name":"Brandan","author_link":"https:\/\/www.helpshift.com\/author\/brandond\/"},"comment_info":0,"category_info":[{"term_id":178,"name":"Chatbots","slug":"chatbots","term_group":0,"term_taxonomy_id":178,"taxonomy":"category","description":"","parent":0,"count":17,"filter":"raw","cat_ID":178,"category_count":17,"category_description":"","cat_name":"Chatbots","category_nicename":"chatbots","category_parent":0}],"tag_info":[{"term_id":201,"name":"automation","slug":"automation","term_group":0,"term_taxonomy_id":201,"taxonomy":"post_tag","description":"","parent":0,"count":9,"filter":"raw"},{"term_id":254,"name":"chatbots for customer service","slug":"chatbots-for-customer-service","term_group":0,"term_taxonomy_id":254,"taxonomy":"post_tag","description":"","parent":0,"count":5,"filter":"raw"}],"_links":{"self":[{"href":"https:\/\/www.helpshift.com\/wp-json\/wp\/v2\/posts\/23335"}],"collection":[{"href":"https:\/\/www.helpshift.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.helpshift.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.helpshift.com\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.helpshift.com\/wp-json\/wp\/v2\/comments?post=23335"}],"version-history":[{"count":3,"href":"https:\/\/www.helpshift.com\/wp-json\/wp\/v2\/posts\/23335\/revisions"}],"predecessor-version":[{"id":30279,"href":"https:\/\/www.helpshift.com\/wp-json\/wp\/v2\/posts\/23335\/revisions\/30279"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.helpshift.com\/wp-json\/wp\/v2\/media\/23339"}],"wp:attachment":[{"href":"https:\/\/www.helpshift.com\/wp-json\/wp\/v2\/media?parent=23335"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.helpshift.com\/wp-json\/wp\/v2\/categories?post=23335"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.helpshift.com\/wp-json\/wp\/v2\/tags?post=23335"},{"taxonomy":"table_tags","embeddable":true,"href":"https:\/\/www.helpshift.com\/wp-json\/wp\/v2\/table_tags?post=23335"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}Scoring Rubric<\/td><\/tr> Criteria <\/td> Points <\/td><\/tr> Awareness of context & proactivity<\/td> 5<\/td><\/tr> Ease of use & efficiency<\/td> 5<\/td><\/tr> Persona & Empathy<\/td> 5<\/td><\/tr> Total<\/td> 15<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n 2. Awareness of context and proactivity<\/h3>\n\n\n\n
\n
![\"\"](\"https:\/\/www.helpshift.com\/wp-content\/uploads\/2022\/04\/Screen-Shot-2019-09-11-at-11.20.55-AM.png\")
<\/figure><\/div>\n\n\n![\"\"](\"https:\/\/www.helpshift.com\/wp-content\/uploads\/2022\/04\/Screen-Shot-2019-09-13-at-4.21.29-PM.png\")
3. Ease of use & efficiency<\/h3>\n\n\n\n
![\"\"](\"https:\/\/www.helpshift.com\/wp-content\/uploads\/2022\/04\/Screen-Shot-2019-09-17-at-5.06.53-PM.png\")
4. Persona & empathy<\/h3>\n\n\n\n
5. The verdict<\/h3>\n\n\n\n
Score Breakdown<\/td><\/tr> Criteria <\/td> Score <\/td><\/tr> Awareness of context & proactivity<\/td> 5<\/td><\/tr> Ease of use & efficiency<\/td> 4<\/td><\/tr> Persona & Empathy<\/td> 5<\/td><\/tr> Total<\/td> 14\/15<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n