{"id":12348,"date":"2025-07-28T18:22:24","date_gmt":"2025-07-28T18:22:24","guid":{"rendered":"https:\/\/rax-stg-wp-aws.com\/case_study\/j-crew\/"},"modified":"2026-06-22T15:54:59","modified_gmt":"2026-06-22T15:54:59","slug":"jcrew","status":"publish","type":"case_study","link":"https:\/\/rax-prod-wp-aws.com\/es\/case_study\/jcrew\/","title":{"rendered":"J.Crew"},"content":{"rendered":"<p><a href=\"https:\/\/www.jcrew.com\/\">J.Crew Group<\/a>&nbsp;is an internationally recognized omnichannel retailer and family of legacy American brands;&nbsp; J.Crew, J.Crew Factory and Madewell. Famous for building iconic, beloved brands,&nbsp; J.Crew Group is the ultimate destination for personal style that is timeless, classic and high quality. As of July 7th, 2025, the Company operates over 100 J.Crew retail stores, over 150 Madewell stores and over 330 J.Crew Factory stores in the United States, and maintains a robust ecommerce presence.&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>J.Crew Group&nbsp;is an internationally recognized omnichannel retailer and family of legacy American brands;&nbsp; J.Crew, J.Crew Factory and Madewell. Famous for building iconic, beloved brands,&nbsp; J.Crew Group is the ultimate destination for personal style that is timeless, classic and high quality. As of July 7th, 2025, the Company operates over 100 J.Crew retail stores, over 150 [&hellip;]<\/p>\n","protected":false},"author":2,"featured_media":0,"menu_order":0,"comment_status":"open","ping_status":"open","template":"","format":"standard","meta":{"content-type":"","seo_title":"J.Crew | Rackspace AI","seo_description":"See how J.Crew Group partnered with Rackspace to build custom AWS-native AI agents that streamlined IT, vendor and customer support while reducing workloads.","banner_text":"This iconic clothing and accessories retailer chose to partner with Rackspace AI to create three AI agents for internal process improvement on AWS.","banner_image":"\/wp-content\/uploads\/2026\/case_study_images\/jcrew\/Interior-Page-Banner.jpg","banner_cta_link":"","header":"J.Crew Group streamlines IT, vendor and customer support with custom AI agents","customer_overview":"Customer","challenge":"J.Crew Group set out to transform its internal support systems by adopting innovative AI-driven solutions for its IT help desk, supply chain vendor communications and customer service center. ","outcome":"Using AWS-native tools, Rackspace built three AI agents that helped J.Crew Group reduce support workloads and laid the foundation for future AI innovation.","mian_quote":"<p>\u201cRackspace provides a robust AI feature set. The team approaches development with a product mindset, which allows us to go to market quickly and confidently.\u201d<\/p>\r\n","mian_quote_attribution_name":"Harsh Gupta","mian_quote_attribution_title":"Senior Director, IT Systems","mian_quote_attribution_company":"J.Crew Group","second_quote":"<p>\u201cWe rely on proven experts, like our Rackspace team members, to share their deep expertise, give us leading-edge guidance and be our trusted development partner.\u201d<\/p>\r\n","second_quote_attribution_name":"Harsh Gupta","second_quote_attribution_title":"Senior Director, IT Systems","second_quote_attribution_company":"J.Crew Group","second_quote_attribution_image":"\/wp-content\/uploads\/2026\/case_study_images\/jcrew\/Quote-Background-1-12918.jpg","tertiary_quote":"<p>J.Crew Group projects a 15% drop in IT help desk call volume and up to three hours saved daily for vendor support teams with its new AI agents.<\/p>\r\n","tertiary_quote_attribution_name":"","tertiary_quote_attribution_title":"","tertiary_quote_attribution_company":"","tertiary_quote_image":"\/wp-content\/uploads\/2026\/case_study_images\/jcrew\/Quote-Background-2-12918.jpg","text_river_1_headline":"Situation","text_river_1_text":"<p>Driven by the need to provide timely support and accurate answers quickly to questions from employees, vendors and customers, J.Crew Group began exploring AI agents options in early 2024<a>.&nbsp;<\/a>With limited in-house AI capabilities, the company looked for a trusted partner to help design robust, innovative solutions that could:<\/p>\r\n\r\n<ul>\r\n\t<li>Reduce the support burden on developers and leadership by automating responses to routine questions<\/li>\r\n\t<li>Integrate seamlessly with analytics platforms for data-driven insights<\/li>\r\n\t<li>Adapt quickly to evolving documentation, data formats and business requirements<\/li>\r\n<\/ul>\r\n\r\n<p>To deliver real value, these AI agents also had to meet a complex set of technical requirements. They needed to:<\/p>\r\n\r\n<ul>\r\n\t<li>Operate within J.Crew Group\u2019s AWS cloud environment<\/li>\r\n\t<li>Process and understand a wide range of file types, including PDFs, images, PowerPoint, Excel files and web pages<\/li>\r\n\t<li>Search selectively across internal knowledge sources, such as SharePoint<\/li>\r\n\t<li>Tailor responses based on the user\u2019s department or role<\/li>\r\n\t<li>Retrieve answers only from pre-approved websites, such as jcrew.com<\/li>\r\n\t<li>Support multiple languages for broader usability<\/li>\r\n<\/ul>\r\n\r\n<p>Harsh Gupta, Senior Director, IT Systems, at J.Crew Group, said, \u201cOur philosophy has always been to choose the best products in every technical area, then learn to maintain them within our internal teams. Whether it\u2019s order management or supply chain applications, we are always using the best-in-breed products.\u201d<\/p>\r\n\r\n<p>To deepen that trust, Rackspace played a key role in aligning J.Crew Group\u2019s cloud foundation with advanced AI capabilities, ensuring the solution was scalable, secure and production-ready from day one.<\/p>\r\n\r\n<p>\u201cThis engagement with J.Crew Group highlights the power of combining deep cloud expertise with practical, results-driven AI innovation,\u201d said D K Sinha, President of Public Cloud at Rackspace Technology. \u201cBy building directly on their AWS environment, we helped unlock business value quickly \u2014 all while staying rooted in operational excellence and technical precision.\u201d<\/p>\r\n\r\n<p>\u201cWe asked Rackspace and another vendor to propose AI chatbot solutions,\u201d said Gupta. \u201cOnce we saw what Rackspace could accomplish within our existing AWS environment, the choice became clear. Rackspace was already a trusted partner for hosting and infrastructure management, so we had confidence it could also deliver strong results in the AI space.\u201d<\/p>\r\n","text_river_1_image":"\/wp-content\/uploads\/2026\/case_study_images\/jcrew\/Text-and-Video-Image-2.jpg","text_river_1_video":"","text_river_2_headline":"Solution","text_river_2_text":"<p>To meet its goals, the J.Crew Group and Rackspace teams began by identifying three AI agents to pilot: one for IT help desk support, one for supply chain vendors and one for the customer service center.<\/p>\r\n\r\n<p>J.Crew Group (JCG) Buddy is designed to ease the IT help desk workload by enabling employee self-service. J.Crew Group targeted a 15% reduction in call volume with this agent.<\/p>\r\n\r\n<p>JCIConnect, the vendor agent, supports the supply chain team by answering role-specific vendor questions in multiple languages \u2014 saving an estimated two to three hours per day for employees.<\/p>\r\n\r\n<p>JCG Ally, the Contact Center agent helps customer service representatives resolve questions more efficiently by reducing the number of issues escalated to managers.<\/p>\r\n\r\n<p>To bring these bots to life, Rackspace employed a range of technologies across clouds, including LangGraph, Microsoft Azure Entra, the AWS Cloud Development Kit (CDK), AWS Lambda and Google\u2019s Vertex AI API.<\/p>\r\n\r\n<p>\u201cWe rely on Rackspace to make the best recommendations in our toolset,\u201d said Gupta. \u201cEach time they made a suggestion, our internal teams validated the recommendation and agreed it was the best approach.\u201d<\/p>\r\n\r\n<p>Rackspace worked closely with J.Crew Group to tailor every element \u2014 from authentication to user experience \u2014 to fit internal requirements. For example, the team customized prompt engineering with AWS large language models (LLMs) to ensure the AI agents delivered precise, context-aware answers aligned to J.Crew Group\u2019s needs.<\/p>\r\n\r\n<p>To meet multilingual and role-specific demands, Rackspace built the agents on LangGraph, an open-source, multi-agent orchestration framework. \u201cIt allows an AI agent to decide whether to answer the question based on internal documents, go to the internet or ask a follow-up question,\u201d explained Subrahmanyam Arunachalam, Data Science Engineer at Rackspace. \u201cLangGraph is one of the most intelligent frameworks available.\u201d<\/p>\r\n\r\n<p>One key challenge was integrating Microsoft Azure Entra for authentication \u2014 even though the application was hosted on AWS. Rackspace built a seamless SSO experience that authenticates users through Microsoft Azure\u00ae, synchronized logins and applied proper access controls back in the AWS-hosted agent interface.<\/p>\r\n\r\n<p>\u201cThe Rackspace team has always been agile,\u201d said Gupta. \u201cThey created an on-the-fly solution to help us identify bad documentation. This team has been phenomenal \u2014 always going above and beyond.\u201d<\/p>\r\n\r\n<p>To minimize manual upkeep, Rackspace also automated the agent\u2019s knowledge base refresh cycle. Every seven days, it scans for changes and updates automatically, eliminating the need for dedicated document management workflows.<\/p>\r\n\r\n<p>As development progressed, the solution evolved into a multi-cloud architecture. Rackspace used Vertex AI API on Google Cloud to give the AI agent secure internet access, with strict controls to limit source data to J.Crew Group-approved domains such as jcrew.com and wikipedia.com.<\/p>\r\n\r\n<p>The backend architecture leverages AWS Lambda for compute, OpenSearch for vector document storage, Amazon Bedrock for LLM hosting, and Amazon Simple Storage Service (Amazon S3) for document storage. All components were consolidated using AWS Cloud Development Kit (CDK), which streamlined deployment and simplified maintenance.<\/p>\r\n\r\n<p>\u201cThe CDK allowed us to create infrastructure templates and reuse them across chatbot projects,\u201d said Arunachalam. \u201cIt brought our development timeline down from months to weeks and helped us scale from one bot to three.\u201d<\/p>\r\n","text_river_2_image":"\/wp-content\/uploads\/2026\/case_study_images\/jcrew\/Text-and-Video-Image-3.jpg","text_river_2_video":"","text_river_3_headline":"Outcome","text_river_3_text":"<p>JCG Buddy was the first agent ready for testing, with JCIConnect and the JCG Ally Agent following closely behind. \u201cOur hope with introducing JCG Buddy first was to put something in front of our internal associates to build excitement,\u201d said Gupta. \u201cWe wanted to demonstrate how the agent could support efficiency in their day-to-day tasks. Their feedback helped us take all three AI agents to the next level in AI development.\u201d<\/p>\r\n\r\n<p>Early outcomes included a 15% projected reduction in help desk call volume from JCG Buddy and an estimated savings of two to three hours per day for employees handling vendor queries through JCIConnect. The project also gave J.Crew Group\u2019s internal teams an opportunity to gain hands-on experience with AI development and move toward greater self-sufficiency.<\/p>\r\n\r\n<p>Gupta credited Rackspace AI team with playing a critical advisory role throughout the engagement. \u201cWe relied on our partnership to bring in AI expertise, provide guidance and act as our development advisor,\u201d he said.<\/p>\r\n\r\n<p>Rackspace AI team supported J.Crew Group in evaluating technical options, refining prompt engineering and training internal teams to manage and maintain the applications.<\/p>\r\n\r\n<p>Looking ahead, J.Crew Group views this initiative as just the beginning. \u201cWe\u2019re now exploring ways to expand chatbot functionality into our analytics platforms,\u201d said Gupta. \u201cOur goal is to answer data-driven questions \u2014 not just static ones.\u201d<\/p>\r\n","text_river_3_pull_quote":"","case_study_image":"\/wp-content\/uploads\/2026\/case_study_images\/jcrew\/Text-and-Video-Image-1.jpg","customer_logo":"\/wp-content\/uploads\/2026\/case_study_images\/jcrew\/Customer-Logo-12918.png","case_study_video":"","insights_image":"\/wp-content\/uploads\/2026\/case_study_images\/jcrew\/Related-Stories_2.jpg","og_image":"\/wp-content\/uploads\/2026\/case_study_images\/jcrew\/OpenGraph_2.jpg","twitter_image":"\/wp-content\/uploads\/2026\/case_study_images\/jcrew\/Twitter_Card.jpg","rxt_industry":"Consumer Goods","region":"North America","rxt_platforms":"Amazon Web Services (AWS)","rxt_solutions":"AI","rxt_professional_managed_service":"","business_size":"Mid-market","bu_categories":"Public Cloud","details_url":"https:\/\/www.jcrew.com\/","teaser_title":"J.Crew ","teaser_flag":"Case Study","teaser_read_more":"Learn More","teaser_logo":"","related_headline":"","content_type":"case_study","nid":"","drupal_nid":"27711","drupal_path":"\/case-studies\/jcrew","related_case_studies":"","tab_items":"General contact case study L2, Contact Tab 2, Combained Contact Us - Careers","view_all_case_studies":"{\"uri\":\"entity:node\\\/23443\",\"title\":\"View all Case Studies\",\"options\":[]}","breadcrumb_top":"{\"uri\":\"entity:node\\\/23443\",\"title\":\"Case Studies\",\"options\":[]}","breadcrumb_title":"J.Crew ","display_quote":"1","form_headline":"Let\u2019s Talk Strategy","form_subtext":"<p>Tell us a little about your challenges and we\u2019ll contact you.<\/p>\r\n","metatag":"","primary_cta_url_target":"","footnotes":""},"categories":[209],"tags":[],"class_list":["post-12348","case_study","type-case_study","status-publish","format-standard","hentry","category-case-study"],"_links":{"self":[{"href":"https:\/\/rax-prod-wp-aws.com\/es\/wp-json\/wp\/v2\/case_study\/12348","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/rax-prod-wp-aws.com\/es\/wp-json\/wp\/v2\/case_study"}],"about":[{"href":"https:\/\/rax-prod-wp-aws.com\/es\/wp-json\/wp\/v2\/types\/case_study"}],"author":[{"embeddable":true,"href":"https:\/\/rax-prod-wp-aws.com\/es\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/rax-prod-wp-aws.com\/es\/wp-json\/wp\/v2\/comments?post=12348"}],"version-history":[{"count":1,"href":"https:\/\/rax-prod-wp-aws.com\/es\/wp-json\/wp\/v2\/case_study\/12348\/revisions"}],"predecessor-version":[{"id":12349,"href":"https:\/\/rax-prod-wp-aws.com\/es\/wp-json\/wp\/v2\/case_study\/12348\/revisions\/12349"}],"wp:attachment":[{"href":"https:\/\/rax-prod-wp-aws.com\/es\/wp-json\/wp\/v2\/media?parent=12348"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/rax-prod-wp-aws.com\/es\/wp-json\/wp\/v2\/categories?post=12348"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/rax-prod-wp-aws.com\/es\/wp-json\/wp\/v2\/tags?post=12348"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}