{"id":2610,"date":"2026-07-02T20:44:00","date_gmt":"2026-07-03T00:44:00","guid":{"rendered":"https:\/\/blog2wrkdev.wpenginepowered.com\/ux-research-ai\/"},"modified":"2026-09-30T08:35:55","modified_gmt":"2026-09-30T12:35:55","slug":"ux-research-ai","status":"publish","type":"post","link":"https:\/\/blog2workato.wpengine.com\/ux-research-ai\/","title":{"rendered":"UX Research in the Age of AI: Challenges and Best Practices"},"content":{"rendered":"\n<h2 id=\"1\" class=\"wp-block-heading\"><strong>Introduction: A Unique Challenge for AI Development<\/strong><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Artificial intelligence is rapidly transforming how we work, making effective integration crucial for organizations. Incorporating new AI tools and features poses a new set of challenges for AI product development. One specific challenge arises from the variability of user interactions with unreleased AI models. <\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Traditionally, research has been tied to design, but with chatbots, copilots, and other AI-driven experiences, AI systems must exist first to observe meaningful user interactions. This shift requires teams to develop new processes and methods to empower product development in the age of AI.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">This paper presents one such novel methodology that integrates real user interactions into GPT-driven simulations to foster an adaptive and user-driven approach to AI design and development. It also outlines considerations for utilizing this method within the product development process and the potential for AI agents to act as simulated users to create more robust AI products.<\/p>\n\n\n\n<h2 id=\"2\" class=\"wp-block-heading\"><strong>Background: Why UX Process Must Adapt<\/strong><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Unlike traditional UX research, which focuses on measuring user behaviors, UX research for AI requires an additional layer\u2014ensuring the AI itself can accurately interpret and execute user queries. <\/p>\n\n\n\n<p class=\"wp-block-paragraph\">User experience hinges on both understanding what an AI can do and knowing how to prompt it effectively. Historically, research has either led or followed design, with development occurring afterward.\u00a0<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">However, AI research presents a unique challenge: the AI system must exist before meaningful user interactions can be studied, making it difficult to anticipate user behavior. This requires a fundamental shift\u2014AI model development can benefit by preceding research and design. <\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Recent research from Google DeepMind (<a href=\"https:\/\/research.google\/people\/meredithringelmorris\/\" target=\"_blank\" rel=\"noreferrer noopener\">Morris<\/a>, 2025) highlights similar challenges in human-computer interaction (HCI) for AI, emphasizing the difficulties of bridging the &#8220;gulf of execution&#8221; and &#8220;gulf of evaluation&#8221;\u2014ensuring users can properly communicate their intent to AI and validate the AI\u2019s responses. <\/p>\n\n\n\n<p class=\"wp-block-paragraph\">As AI and copilots become integral to business automation, enabling users to perform complex tasks with ease, understanding user interactions with these products before release is essential.\u00a0<\/p>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-full\"><a href=\"https:\/\/blog2workato.wpengine.com\/wp-content\/uploads\/2026\/09\/Workato-2-1-7.png\"><img decoding=\"async\" src=\"https:\/\/blog2workato.wpengine.com\/wp-content\/uploads\/2026\/09\/Workato-2-1-7.png\" alt=\"Unlike traditional UX research, which focuses on measuring user behaviors, UX research for AI requires an additional layer\u2014ensuring the AI itself can accurately interpret and execute user queries. \" class=\"wp-image-45281\"\/><\/a><\/figure>\n<\/div>\n\n\n<h2 id=\"3\" class=\"wp-block-heading\"><strong>A Copilot Learning Experience<\/strong><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">In 2024, Workato introduced <a href=\"https:\/\/docs.workato.com\/en\/recipes\/recipe-copilot.html\">Recipe Copilot<\/a>, leveraging AI to assist users in writing and editing recipes. While adoption was high, a usability study of user interactions revealed that certain input styles yielded accurate outputs, whereas others led to errors, frustrating users.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Despite strong promise for enhanced productivity and above-average performance, the Copilot experience required greater stability and accuracy to convert user inputs into meaningful recipes. I sought to help the team explore how research could assist QA in improving Copilot reliability.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Through a qualitative study of user interactions with our Copilot, three distinct user input styles had emerged:<\/p>\n\n\n\n<ol class=\"wp-block-list\">\n<li><strong>Directive Prompting<\/strong> \u2013 Users provided explicit, step-by-step instructions in a single input.<\/li>\n\n\n\n<li><strong>Goal-Oriented Prompting<\/strong> \u2013 Users described the desired outcome without specifying implementation details.<\/li>\n\n\n\n<li><strong>Exploratory Prompting<\/strong> \u2013 Users refined their requests iteratively based on AI responses.<\/li>\n<\/ol>\n\n\n\n<p class=\"wp-block-paragraph\">Using these insights, I reverse-engineered a structured framework that QA and engineering could utilize to enhance AI-generated outputs based on real-world use cases. This methodology enables AI systems to adapt to user behavior, improving automation <a href=\"https:\/\/www.workato.com\/the-connector\/orchestrate-ai-workflows\/\">workflows<\/a> and overall satisfaction.<\/p>\n\n\n\n<h2 id=\"4\" class=\"wp-block-heading\"><strong>Simulating Prompt Styles for Research and QA<\/strong><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Training an AI model requires robust QA testing that mirrors real-world user interactions\u2014many of which may be incomplete, ambiguous, or exploratory. For instance, we often see users turn to AI for guidance when they lack full understanding of a task themselves.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">To simulate this variability, I developed a methodology using ChatGPT to generate simulated conversations for development testing. The goal was to produce idealized recipe outputs for the top recipe use cases and to provide varied, user-driven conversations that lead to that idealized result.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>Methodology Steps:<\/strong><\/h3>\n\n\n\n<ol class=\"wp-block-list\">\n<li><strong>Defining Top Recipe Types<\/strong> \u2013 Identifying key automation use cases in Snowflake, categorized by unique recipes, triggers\/actions, and apps used.<\/li>\n\n\n\n<li><strong>Training GPT on Prompting Styles<\/strong> \u2013 Generating simulated conversations for each identified use case from the Copilot research (above).<\/li>\n\n\n\n<li><strong>Generating Expected Outputs<\/strong> \u2013 Creating three output types to guide QA:\n<ul class=\"wp-block-list\">\n<li><strong>Idealized Workato Recipe Outputs<\/strong> \u2013 Benchmarks for expected automation workflows.<\/li>\n\n\n\n<li><strong>Simulated User Conversations<\/strong> \u2013 Demonstrating how different input styles influence Copilot interactions.<\/li>\n\n\n\n<li><strong>Stage-wise Copilot Outputs<\/strong> \u2013 Analyzing AI behavior at each stage of user engagement.<\/li>\n<\/ul>\n<\/li>\n<\/ol>\n\n\n\n<p class=\"wp-block-paragraph\">These structured outputs provided QA with both user input patterns and expected AI responses, helping refine system performance and accuracy. For instance, with these outputs, QA could test whether or not the AI outputs match the intended ideal path across top use-cases without having to hypothesize <em>how<\/em> a user might act.<\/p>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter size-full\"><a href=\"https:\/\/blog2workato.wpengine.com\/wp-content\/uploads\/2026\/09\/Workato-3-20.png\"><img decoding=\"async\" src=\"https:\/\/blog2workato.wpengine.com\/wp-content\/uploads\/2026\/09\/Workato-3-20.png\" alt=\"Reorienting AI development toward an earlier Proof-of-Concept (PoC) phase enables iterative learning from real user interactions.\" class=\"wp-image-45282\"\/><\/a><\/figure>\n<\/div>\n\n\n<h2 id=\"5\" class=\"wp-block-heading\"><strong>The Expanding Role of Research in AI Development<\/strong><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Traditional UX research follows an iterative cycle between research and design before final product development. However, with AI, evaluating performance only after launch is too late. Instead, reorienting AI development toward an earlier Proof-of-Concept (PoC) phase enables iterative learning from real user interactions.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>The Simulated Engagement Method:<\/strong><\/h3>\n\n\n\n<ol class=\"wp-block-list\">\n<li><strong>AI PoC Development<\/strong> \u2013 Engineers develop an interactive prototype based on an initial framework.<\/li>\n\n\n\n<li><strong>Observing User Interactions<\/strong> \u2013 Users engage with the PoC, prompting the AI based on real-world needs.<\/li>\n\n\n\n<li><strong>Identifying Interaction Styles<\/strong> \u2013 Categorizing user prompting\/engagement strategies.<\/li>\n\n\n\n<li><strong>Use-Case Analysis<\/strong> \u2013 Aggregating behavioral data to identify the most common automation use cases.<\/li>\n\n\n\n<li><strong>Simulated Interactions<\/strong> \u2013 GPT-generated outputs model idealized AI responses across different prompting styles.<\/li>\n<\/ol>\n\n\n\n<p class=\"wp-block-paragraph\">This methodology allows research to influence<a href=\"https:\/\/docs.workato.com\/en\/connectors\/ai-by-workato\"> AI development <\/a>earlier in the process, ensuring user-driven refinements rather than retrospective design modifications. By restructuring research and QA workflows, product teams can shorten feedback loops and <strong>accelerate development timelines<\/strong> while maintaining AI quality.<\/p>\n\n\n\n<h2 id=\"6\" class=\"wp-block-heading\"><strong>Future-Proofing AI with Agents<\/strong><\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Observing real-world user interactions with a <a href=\"https:\/\/www.workato.com\/product-hub\/from-poc-to-production-running-mcp-in-the-enterprise\/?timezone=us\">Proof-of-Concept<\/a> (PoC) AI provides a foundation for understanding how users engage with the system. However, once interaction patterns are identified, AI agents can further contribute by assisting in quality assurance testing.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Rather than relying solely on predefined test cases, AI agents trained on observed user prompting styles could systematically probe AI systems, identifying weak points in responses and inconsistencies across different input patterns. <\/p>\n\n\n\n<p class=\"wp-block-paragraph\">This would allow for a <strong>continuous research-driven QA loop<\/strong>\u2014where simulated agents replicate real-world interaction patterns to surface potential improvements before deployment.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">By incorporating <a href=\"https:\/\/www.workato.com\/the-connector\/what-are-ai-agents\/\">AI agents<\/a> into QA workflows after research has established user input trends, companies can ensure AI models remain adaptable to evolving user behaviors. This additional layer of AI-assisted validation could help refine not only response accuracy but also interaction fluidity, ultimately improving AI copilots\u2019 effectiveness in production environments.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Future work will explore how AI agents can autonomously identify edge cases and prompt refinements based on large-scale user behavior patterns, further extending the impact of research-driven AI development.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>References<\/strong><\/h3>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Morris, M.R. (2025). <em>HCI for AGI<\/em>. Interactions Magazine.<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>Introduction: A Unique Challenge for AI Development Artificial intelligence is rapidly transforming how we work, making effective integration crucial for organizations. Incorporating new AI tools and features poses a new set of challenges for AI product development. One specific challenge arises from the variability of user interactions with unreleased AI models. Traditionally, research has been [&hellip;]<\/p>\n","protected":false},"author":99,"featured_media":12581,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[60],"tags":[],"class_list":["post-2610","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai-agents-orchestration"],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v28.8 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>UX Research in the Age of AI: Challenges and Best Practices<\/title>\n<meta name=\"description\" content=\"Explore how UX research is evolving for AI, from user interactions and simulated prompts to AI-powered QA and agent-driven testing.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/blog2workato.wpengine.com\/ux-research-ai\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"UX Research in the Age of AI: Challenges and Best Practices\" \/>\n<meta property=\"og:description\" content=\"Explore how UX research is evolving for AI, from user interactions and simulated prompts to AI-powered QA and agent-driven testing.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/blog2workato.wpengine.com\/ux-research-ai\/\" \/>\n<meta property=\"og:site_name\" content=\"Workato\" \/>\n<meta property=\"article:published_time\" content=\"2026-07-03T00:44:00+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2026-09-30T12:35:55+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/workato.com\/the-connector\/wp-content\/uploads\/2026\/09\/Rethinking-UX-in-the-Age-of-AI-1024x448.png\" \/>\n\t<meta property=\"og:image:width\" content=\"1024\" \/>\n\t<meta property=\"og:image:height\" content=\"448\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"Brian Hayes\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Brian Hayes\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"5 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/blog2workato.wpengine.com\\\/ux-research-ai\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/blog2workato.wpengine.com\\\/ux-research-ai\\\/\"},\"author\":{\"name\":\"Brad Griffith\",\"@id\":\"https:\\\/\\\/www.workato.com\\\/the-connector\\\/#\\\/schema\\\/person\\\/744993c23062654520299fbc1307ebb3\"},\"headline\":\"UX Research in the Age of AI: Challenges and Best Practices\",\"datePublished\":\"2026-07-03T00:44:00+00:00\",\"dateModified\":\"2026-09-30T12:35:55+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/blog2workato.wpengine.com\\\/ux-research-ai\\\/\"},\"wordCount\":1076,\"image\":{\"@id\":\"https:\\\/\\\/blog2workato.wpengine.com\\\/ux-research-ai\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/blog2workato.wpengine.com\\\/wp-content\\\/uploads\\\/2026\\\/09\\\/Rethinking-UX-in-the-Age-of-AI.png\",\"articleSection\":[\"AI Agents &amp; Orchestration\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/blog2workato.wpengine.com\\\/ux-research-ai\\\/\",\"url\":\"https:\\\/\\\/blog2workato.wpengine.com\\\/ux-research-ai\\\/\",\"name\":\"UX Research in the Age of AI: Challenges and Best Practices\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.workato.com\\\/the-connector\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/blog2workato.wpengine.com\\\/ux-research-ai\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/blog2workato.wpengine.com\\\/ux-research-ai\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/blog2workato.wpengine.com\\\/wp-content\\\/uploads\\\/2026\\\/09\\\/Rethinking-UX-in-the-Age-of-AI.png\",\"datePublished\":\"2026-07-03T00:44:00+00:00\",\"dateModified\":\"2026-09-30T12:35:55+00:00\",\"author\":{\"@id\":\"https:\\\/\\\/www.workato.com\\\/the-connector\\\/#\\\/schema\\\/person\\\/744993c23062654520299fbc1307ebb3\"},\"description\":\"Explore how UX research is evolving for AI, from user interactions and simulated prompts to AI-powered QA and agent-driven testing.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/blog2workato.wpengine.com\\\/ux-research-ai\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/blog2workato.wpengine.com\\\/ux-research-ai\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/blog2workato.wpengine.com\\\/ux-research-ai\\\/#primaryimage\",\"url\":\"https:\\\/\\\/blog2workato.wpengine.com\\\/wp-content\\\/uploads\\\/2026\\\/09\\\/Rethinking-UX-in-the-Age-of-AI.png\",\"contentUrl\":\"https:\\\/\\\/blog2workato.wpengine.com\\\/wp-content\\\/uploads\\\/2026\\\/09\\\/Rethinking-UX-in-the-Age-of-AI.png\",\"width\":2560,\"height\":1120},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/blog2workato.wpengine.com\\\/ux-research-ai\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/blog2workato.wpengine.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"UX Research in the Age of AI: Challenges and Best Practices\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/www.workato.com\\\/the-connector\\\/#website\",\"url\":\"https:\\\/\\\/www.workato.com\\\/the-connector\\\/\",\"name\":\"Workato\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/www.workato.com\\\/the-connector\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/www.workato.com\\\/the-connector\\\/#\\\/schema\\\/person\\\/744993c23062654520299fbc1307ebb3\",\"name\":\"Brian Hayes\",\"url\":\"https:\\\/\\\/blog2workato.wpengine.com\\\/author\\\/brad-griffithworkato-com\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"UX Research in the Age of AI: Challenges and Best Practices","description":"Explore how UX research is evolving for AI, from user interactions and simulated prompts to AI-powered QA and agent-driven testing.","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:\/\/blog2workato.wpengine.com\/ux-research-ai\/","og_locale":"en_US","og_type":"article","og_title":"UX Research in the Age of AI: Challenges and Best Practices","og_description":"Explore how UX research is evolving for AI, from user interactions and simulated prompts to AI-powered QA and agent-driven testing.","og_url":"https:\/\/blog2workato.wpengine.com\/ux-research-ai\/","og_site_name":"Workato","article_published_time":"2026-07-03T00:44:00+00:00","article_modified_time":"2026-09-30T12:35:55+00:00","og_image":[{"width":1024,"height":448,"url":"https:\/\/workato.com\/the-connector\/wp-content\/uploads\/2026\/09\/Rethinking-UX-in-the-Age-of-AI-1024x448.png","type":"image\/png"}],"author":"Brian Hayes","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Brian Hayes","Est. reading time":"5 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/blog2workato.wpengine.com\/ux-research-ai\/#article","isPartOf":{"@id":"https:\/\/blog2workato.wpengine.com\/ux-research-ai\/"},"author":{"name":"Brad Griffith","@id":"https:\/\/www.workato.com\/the-connector\/#\/schema\/person\/744993c23062654520299fbc1307ebb3"},"headline":"UX Research in the Age of AI: Challenges and Best Practices","datePublished":"2026-07-03T00:44:00+00:00","dateModified":"2026-09-30T12:35:55+00:00","mainEntityOfPage":{"@id":"https:\/\/blog2workato.wpengine.com\/ux-research-ai\/"},"wordCount":1076,"image":{"@id":"https:\/\/blog2workato.wpengine.com\/ux-research-ai\/#primaryimage"},"thumbnailUrl":"https:\/\/blog2workato.wpengine.com\/wp-content\/uploads\/2026\/09\/Rethinking-UX-in-the-Age-of-AI.png","articleSection":["AI Agents &amp; Orchestration"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/blog2workato.wpengine.com\/ux-research-ai\/","url":"https:\/\/blog2workato.wpengine.com\/ux-research-ai\/","name":"UX Research in the Age of AI: Challenges and Best Practices","isPartOf":{"@id":"https:\/\/www.workato.com\/the-connector\/#website"},"primaryImageOfPage":{"@id":"https:\/\/blog2workato.wpengine.com\/ux-research-ai\/#primaryimage"},"image":{"@id":"https:\/\/blog2workato.wpengine.com\/ux-research-ai\/#primaryimage"},"thumbnailUrl":"https:\/\/blog2workato.wpengine.com\/wp-content\/uploads\/2026\/09\/Rethinking-UX-in-the-Age-of-AI.png","datePublished":"2026-07-03T00:44:00+00:00","dateModified":"2026-09-30T12:35:55+00:00","author":{"@id":"https:\/\/www.workato.com\/the-connector\/#\/schema\/person\/744993c23062654520299fbc1307ebb3"},"description":"Explore how UX research is evolving for AI, from user interactions and simulated prompts to AI-powered QA and agent-driven testing.","breadcrumb":{"@id":"https:\/\/blog2workato.wpengine.com\/ux-research-ai\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/blog2workato.wpengine.com\/ux-research-ai\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/blog2workato.wpengine.com\/ux-research-ai\/#primaryimage","url":"https:\/\/blog2workato.wpengine.com\/wp-content\/uploads\/2026\/09\/Rethinking-UX-in-the-Age-of-AI.png","contentUrl":"https:\/\/blog2workato.wpengine.com\/wp-content\/uploads\/2026\/09\/Rethinking-UX-in-the-Age-of-AI.png","width":2560,"height":1120},{"@type":"BreadcrumbList","@id":"https:\/\/blog2workato.wpengine.com\/ux-research-ai\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/blog2workato.wpengine.com\/"},{"@type":"ListItem","position":2,"name":"UX Research in the Age of AI: Challenges and Best Practices"}]},{"@type":"WebSite","@id":"https:\/\/www.workato.com\/the-connector\/#website","url":"https:\/\/www.workato.com\/the-connector\/","name":"Workato","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.workato.com\/the-connector\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/www.workato.com\/the-connector\/#\/schema\/person\/744993c23062654520299fbc1307ebb3","name":"Brian Hayes","url":"https:\/\/blog2workato.wpengine.com\/author\/brad-griffithworkato-com\/"}]}},"_links":{"self":[{"href":"https:\/\/blog2workato.wpengine.com\/wp-json\/wp\/v2\/posts\/2610","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blog2workato.wpengine.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blog2workato.wpengine.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blog2workato.wpengine.com\/wp-json\/wp\/v2\/users\/99"}],"replies":[{"embeddable":true,"href":"https:\/\/blog2workato.wpengine.com\/wp-json\/wp\/v2\/comments?post=2610"}],"version-history":[{"count":2,"href":"https:\/\/blog2workato.wpengine.com\/wp-json\/wp\/v2\/posts\/2610\/revisions"}],"predecessor-version":[{"id":14738,"href":"https:\/\/blog2workato.wpengine.com\/wp-json\/wp\/v2\/posts\/2610\/revisions\/14738"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/blog2workato.wpengine.com\/wp-json\/wp\/v2\/media\/12581"}],"wp:attachment":[{"href":"https:\/\/blog2workato.wpengine.com\/wp-json\/wp\/v2\/media?parent=2610"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blog2workato.wpengine.com\/wp-json\/wp\/v2\/categories?post=2610"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blog2workato.wpengine.com\/wp-json\/wp\/v2\/tags?post=2610"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}