{"id":59701,"date":"2025-03-27T18:06:49","date_gmt":"2025-03-27T18:06:49","guid":{"rendered":"https:\/\/www.bloomreach.com\/?post_type=library&#038;p=59701"},"modified":"2025-03-27T18:06:50","modified_gmt":"2025-03-27T18:06:50","slug":"balancing-search-tradition-and-transformation-with-bloomreach-clarity","status":"publish","type":"library","link":"https:\/\/www.bloomreach.com\/en\/blog\/balancing-search-tradition-and-transformation-with-bloomreach-clarity","title":{"rendered":"Balancing Search Tradition and Transformation With Bloomreach Clarity"},"content":{"rendered":"\n<p>It\u2019s clear that people want conversational experiences when shopping \u2014 after all, we\u2019ve already been seeing some <a href=\"https:\/\/www.bloomreach.com\/en\/case-studies\/tfg-boosts-online-conversion-rate-with-bloomreach-clarity\">incredible results<\/a> with <a href=\"https:\/\/www.bloomreach.com\/en\/products\/clarity\">Bloomreach Clarity<\/a>, our conversational AI shopping agent.&nbsp;<\/p>\n\n\n\n<p>But the path to Clarity wasn\u2019t always a straightforward one. When dealing with transformative technology, there\u2019s always a fine balance to handle the evolution of user behaviors from what they are used to and where we want to take them. In this post, I\u2019ll explore some of the challenges we tackled when developing Clarity and how we\u2019re now reshaping the traditional product discovery experience on ecommerce sites.&nbsp;<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">The Challenges With Bringing Conversational AI to Product Discovery<\/h2>\n\n\n\n<p>In its initial state, we originally designed Bloomreach Clarity to be a product expert. This meant deploying it on product detail pages (PDPs) and product listing pages (PLPs) to answer questions. This was an easy-to-understand concept for brands \u2014 we were simply adding value with an agent that complemented the product discovery experience.&nbsp;<\/p>\n\n\n\n<p>However, we always envisioned integrating Clarity within the traditional search experience as well. To do this, we first had to address a couple of obstacles in our path:&nbsp;<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>We have customers using our highly tuned Discovery solution for their search engine as well as customers still using their existing search engine. While they want to leverage the GenAI conversational experience offered by Clarity, they also still want to keep the traditional search bar experience on their sites.\u00a0<\/li>\n\n\n\n<li>We also wanted to avoid bifurcating the experience \u2014 if you have both a search bar and a separate chat window, people will naturally gravitate toward the search bar because that\u2019s what they\u2019re used to. How can we get people to use a conversational shopping agent without it feeling intrusive or out of place?\u00a0<\/li>\n<\/ul>\n\n\n\n<h2 class=\"wp-block-heading\">Integrating Search With Conversational AI&nbsp;<\/h2>\n\n\n\n<p>To tackle these challenges, we integrated Clarity with our search API to create an optimal experience for product discovery. In particular, we wanted to ensure that Clarity could leverage all of the benefits configured into the search engine (e.g., allowing the merchandiser to <a href=\"https:\/\/www.bloomreach.com\/en\/blog\/giving-merchandisers-unprecedented-control-with-ai-studio\">override our search algorithm<\/a> to unload a specific product) and the analytics-driven ML algorithms that power RPV lift.\u00a0<\/p>\n\n\n\n<p>Clarity has a built-in understanding of the advanced properties in search that most users don\u2019t typically use (such as using quotation marks for an exact search). Additionally, the LLM will extract categories (e.g., \u201cdining chair\u201d vs. \u201caccent stool\u201d), filter attributes (e.g., color, price, size), and sort attributes (e.g., a shopper sets a maximum price, so the LLM sorts results in ascending order).&nbsp;<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Creating a Conversational Shopping Experience<\/h2>\n\n\n\n<p>We also needed to address the conversational user experience for search. If a shopper is speaking directly with Clarity (either via a chat window or through an embedded module), then Clarity will run a series of LLM calls to ensure its responses are accurate and relevant:&nbsp;<\/p>\n\n\n\n<p><strong>Pre-search:<\/strong> If the search query is too broad, Clarity will ask clarifying questions and provide some quick response buttons to get more information. For example, if a user simply types in \u201ctable,\u201d Clarity can ask what kind of table the customer is looking for to better serve them.&nbsp;<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" width=\"1024\" height=\"794\" src=\"https:\/\/www.bloomreach.com\/wp-content\/uploads\/2025\/03\/Clarity-Xun_search-follow-up-1024x794.png\" alt=\"Conversational shopping agent Bloomreach Clarity asking follow-up questions on a search query\" class=\"wp-image-59702\" srcset=\"https:\/\/www.bloomreach.com\/wp-content\/uploads\/2025\/03\/Clarity-Xun_search-follow-up-1024x794.png 1024w, https:\/\/www.bloomreach.com\/wp-content\/uploads\/2025\/03\/Clarity-Xun_search-follow-up-300x233.png 300w, https:\/\/www.bloomreach.com\/wp-content\/uploads\/2025\/03\/Clarity-Xun_search-follow-up-768x596.png 768w, https:\/\/www.bloomreach.com\/wp-content\/uploads\/2025\/03\/Clarity-Xun_search-follow-up.png 1462w\" sizes=\"(max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n\n<p><strong>Search: <\/strong>Once Clarity determines that there is enough specificity in the query, it\u2019ll generate a search API call to retrieve relevant products, using the advanced search properties and filters.&nbsp;<\/p>\n\n\n\n<p><strong>Post-search: <\/strong>Before showing products to the customer, Clarity will then perform a relevancy check to ensure the products are actually relevant to the query. For example, if the search query was for \u201cbrown cherry dining table under $400,\u201d then Clarity will check that the products it retrieved match the color, material, type of table, and price range.&nbsp;<\/p>\n\n\n\n<p>If the relevancy filter doesn\u2019t return any results, we\u2019ll make another LLM call to find results that are as close to those filters as possible. The LLM will then generate text to explain the results, ask follow-up questions, or make further suggestions.\u00a0<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" width=\"1024\" height=\"610\" src=\"https:\/\/www.bloomreach.com\/wp-content\/uploads\/2025\/03\/Clarity-Xun_table-size-follow-up-1024x610.png\" alt=\"Bloomreach Clarity having a conversation with a shopper asking for more details on a search query for a brown cherry dining table\" class=\"wp-image-59705\" srcset=\"https:\/\/www.bloomreach.com\/wp-content\/uploads\/2025\/03\/Clarity-Xun_table-size-follow-up-1024x610.png 1024w, https:\/\/www.bloomreach.com\/wp-content\/uploads\/2025\/03\/Clarity-Xun_table-size-follow-up-300x179.png 300w, https:\/\/www.bloomreach.com\/wp-content\/uploads\/2025\/03\/Clarity-Xun_table-size-follow-up-768x458.png 768w, https:\/\/www.bloomreach.com\/wp-content\/uploads\/2025\/03\/Clarity-Xun_table-size-follow-up.png 1462w\" sizes=\"(max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n\n<p>But what about shoppers who want to keep using the traditional search bar experience? We wanted to avoid having an intrusive chat window pop up too early while they were using the search bar, as that would break up the experience in an unintuitive way.&nbsp;<\/p>\n\n\n\n<p>To address this, we created an integration where Clarity will generate questions as the user searches \u2014 kind of like an advanced autosuggest. So, if a shopper searches for \u201csofa,\u201d in addition to the standard keyword autosuggestions (e.g., \u201csofa for living room,\u201d \u201csofa cover,\u201d etc.), Clarity will also generate relevant questions (e.g., \u201cWhat type of sofa is most comfortable?\u201d or \u201cWhat sofa size is best for a 2-bedroom apartment?\u201d).&nbsp;<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" width=\"1024\" height=\"709\" src=\"https:\/\/www.bloomreach.com\/wp-content\/uploads\/2025\/03\/Clarity-Xun_search-autosuggest-1024x709.png\" alt=\"Bloomreach Clarity connecting to a search bar to autogenerate common questions in addition to autosuggestions\" class=\"wp-image-59708\" srcset=\"https:\/\/www.bloomreach.com\/wp-content\/uploads\/2025\/03\/Clarity-Xun_search-autosuggest-1024x709.png 1024w, https:\/\/www.bloomreach.com\/wp-content\/uploads\/2025\/03\/Clarity-Xun_search-autosuggest-300x208.png 300w, https:\/\/www.bloomreach.com\/wp-content\/uploads\/2025\/03\/Clarity-Xun_search-autosuggest-768x532.png 768w, https:\/\/www.bloomreach.com\/wp-content\/uploads\/2025\/03\/Clarity-Xun_search-autosuggest.png 1462w\" sizes=\"(max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n\n<p>We are able to generate relevant questions by giving the query and product descriptions to an LLM to generate questions based on the following rules:&nbsp;<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Questions must relate to what a user might ask a shopping assistant when looking for the product specified in the search query\u00a0<\/li>\n\n\n\n<li>Questions must contain the search query or its most significant part<\/li>\n\n\n\n<li>Questions cannot be related to discounts or promotions\u00a0<\/li>\n<\/ul>\n\n\n\n<p>Furthermore, Clarity will round the user\u2019s input to the first query brought up by the search query suggester since this has the highest probability of matching their intended search. If a set of questions exists for the query, then Clarity will show them. This ensures that relevant questions will appear as soon as the user starts typing (even if it\u2019s just a single character).&nbsp;<\/p>\n\n\n\n<p>Once a person clicks on an auto-generated question, Clarity uses an LLM evaluator to determine if the retrieved answers are accurate before displaying them. From there, the shopper can either continue using the traditional search experience by filtering and browsing, or they can continue chatting with Clarity and asking follow-up questions.\u00a0<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Give Your Shoppers a Conversational Experience With Bloomreach<\/h2>\n\n\n\n<p>Consumers may not be quite ready yet to completely abandon the search bar, but that doesn\u2019t mean you can\u2019t give them a better experience with conversational shopping. With Clarity, you can bring conversational shopping to your shoppers when it makes sense for their habits, whether that\u2019s a dedicated module for them to interact with or a subtle prompt within the search bar itself.\u00a0<\/p>\n\n\n\n<p>Ultimately, shoppers are already evolving the way they search and discover products, and you\u2019ll need to evolve to match their preferences. Learn more about how a conversational shopping agent like <a href=\"https:\/\/www.bloomreach.com\/en\/products\/clarity\">Clarity<\/a> can help you drive greater engagement and conversions across your site.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>It\u2019s clear that people want conversational experiences when shopping \u2014 after all, we\u2019ve already been seeing some incredible results with Bloomreach Clarity, our conversational AI shopping agent.&nbsp; But the path to Clarity wasn\u2019t always a straightforward one. When dealing with transformative technology, there\u2019s always a fine balance to handle the evolution of user behaviors from [&hellip;]<\/p>\n","protected":false},"author":127,"featured_media":59711,"template":"","ew-regions":[],"ew-solutions":[],"library_type":[513],"library_blog_tag":[362,368,359],"industry":[],"channel":[],"topic":[283,285,546],"class_list":["post-59701","library","type-library","status-publish","has-post-thumbnail","hentry","library_type-blog","library_blog_tag-ai-and-innovation","library_blog_tag-conversational-shopping","library_blog_tag-executive-insights","topic-ai","topic-grow-aov","topic-personalization"],"acf":{"library_blog_banner_content":"","library_blog_banner_cta1_text":"","library_blog_banner_cta1_href":"","library_blog_banner_cta1_new_tab":false,"library_blog_banner_cta2_text":"","library_blog_banner_cta2_href":"","library_blog_banner_cta2_new_tab":false,"library_blog_banner_bg_color":"#EAF7FE","library_blog_banner_cta_text_color":"#FFF","library_blog_banner_cta_bg_color":"#019ACE","library_blog_banner_cta2_text_color":"#000","library_blog_banner_cta2_bg_color":"#FFF","library_blog_chatgpt_content":"","library_blog_chatgpt_cta_href":"","library_blog_chatgpt_cta_text":"Ask ChatGPT"},"_links":{"self":[{"href":"https:\/\/www.bloomreach.com\/en\/wp-json\/wp\/v2\/library\/59701","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.bloomreach.com\/en\/wp-json\/wp\/v2\/library"}],"about":[{"href":"https:\/\/www.bloomreach.com\/en\/wp-json\/wp\/v2\/types\/library"}],"author":[{"embeddable":true,"href":"https:\/\/www.bloomreach.com\/en\/wp-json\/wp\/v2\/users\/127"}],"version-history":[{"count":1,"href":"https:\/\/www.bloomreach.com\/en\/wp-json\/wp\/v2\/library\/59701\/revisions"}],"predecessor-version":[{"id":59717,"href":"https:\/\/www.bloomreach.com\/en\/wp-json\/wp\/v2\/library\/59701\/revisions\/59717"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.bloomreach.com\/en\/wp-json\/wp\/v2\/media\/59711"}],"wp:attachment":[{"href":"https:\/\/www.bloomreach.com\/en\/wp-json\/wp\/v2\/media?parent=59701"}],"wp:term":[{"taxonomy":"ew_regions","embeddable":true,"href":"https:\/\/www.bloomreach.com\/en\/wp-json\/wp\/v2\/ew-regions?post=59701"},{"taxonomy":"ew_solutions","embeddable":true,"href":"https:\/\/www.bloomreach.com\/en\/wp-json\/wp\/v2\/ew-solutions?post=59701"},{"taxonomy":"library_type","embeddable":true,"href":"https:\/\/www.bloomreach.com\/en\/wp-json\/wp\/v2\/library_type?post=59701"},{"taxonomy":"library_blog_tag","embeddable":true,"href":"https:\/\/www.bloomreach.com\/en\/wp-json\/wp\/v2\/library_blog_tag?post=59701"},{"taxonomy":"industry","embeddable":true,"href":"https:\/\/www.bloomreach.com\/en\/wp-json\/wp\/v2\/industry?post=59701"},{"taxonomy":"channel","embeddable":true,"href":"https:\/\/www.bloomreach.com\/en\/wp-json\/wp\/v2\/channel?post=59701"},{"taxonomy":"topic","embeddable":true,"href":"https:\/\/www.bloomreach.com\/en\/wp-json\/wp\/v2\/topic?post=59701"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}