{"id":26203,"date":"2025-08-01T11:43:48","date_gmt":"2025-08-01T11:43:48","guid":{"rendered":"https:\/\/www.refrens.com\/grow\/?p=26203"},"modified":"2025-08-01T11:56:30","modified_gmt":"2025-08-01T11:56:30","slug":"ai-for-quality-assurance","status":"publish","type":"post","link":"https:\/\/www.refrens.com\/grow\/ai-for-quality-assurance\/","title":{"rendered":"A Comprehensive Guide to Automating QA Workflow"},"content":{"rendered":"\n<h1 id=\"a-founder-s-intern-tale-of-integrating-ai-for-quality-assurance\" style=\"font-size:24px\">A founder&#8217;s intern tale of integrating AI for Quality Assurance <\/h1>\n\n\n\n<div style=\"height:20px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<h1 id=\"hi-i-m-shreya-lakhera-a-founder-s-office-intern-at-refrens\" style=\"font-size:15px\">Hi, I\u2019m Shreya Lakhera, a founder\u2019s office intern at Refrens.&nbsp;<\/h1>\n\n\n\n<p>In a series of automating our workflows for different teams, I was tasked with a wild one: <em>\u201cSee if we can use AI to improve our QA process.\u201d<\/em>&nbsp;<\/p>\n\n\n\n<p>As someone obsessed with AI, I was thrilled. The QA team? Not so much.<\/p>\n\n\n\n<p><em>\u201cIf it doesn\u2019t reduce our workload, it\u2019s not worth it.\u201d<\/em><strong> \u2013 Shivam, our QA lead, day one of the project.<\/strong><\/p>\n\n\n\n<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_62 ez-toc-wrap-center counter-hierarchy ez-toc-counter ez-toc-custom 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\"><a href=\"#\" class=\"ez-toc-pull-right ez-toc-btn ez-toc-btn-xs ez-toc-btn-default ez-toc-toggle\" aria-label=\"Toggle Table of Content\"><span class=\"ez-toc-js-icon-con\"><span class=\"\"><span class=\"eztoc-hide\" style=\"display:none;\">Toggle<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #161c26;color:#161c26\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewBox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #161c26;color:#161c26\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewBox=\"0 0 24 24\" version=\"1.2\" baseProfile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/span><\/a><\/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:\/\/www.refrens.com\/grow\/ai-for-quality-assurance\/#The_Problem_QA_Was_Becoming_the_Bottleneck\" title=\"The Problem: QA Was Becoming the Bottleneck\">The Problem: QA Was Becoming the Bottleneck<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/www.refrens.com\/grow\/ai-for-quality-assurance\/#The_Exploration_40_AI_Tools_2_Months_1_Spreadsheet\" title=\"The Exploration: 40+ AI Tools, 2 Months, 1 Spreadsheet\">The Exploration: 40+ AI Tools, 2 Months, 1 Spreadsheet<\/a><ul class='ez-toc-list-level-4' ><li class='ez-toc-heading-level-4'><ul class='ez-toc-list-level-4' ><li class='ez-toc-heading-level-4'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/www.refrens.com\/grow\/ai-for-quality-assurance\/#Step_1_Make_the_Team_Part_of_the_Process\" title=\"Step 1: Make the Team Part of the Process\">Step 1: Make the Team Part of the Process<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-4'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/www.refrens.com\/grow\/ai-for-quality-assurance\/#Step_2_Drowning_in_Tools\" title=\"Step 2: Drowning in Tools&nbsp;\">Step 2: Drowning in Tools&nbsp;<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-4'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/www.refrens.com\/grow\/ai-for-quality-assurance\/#Step_3_Acknowledge_the_Resistance\" title=\"Step 3: Acknowledge the Resistance\">Step 3: Acknowledge the Resistance<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-4'><a class=\"ez-toc-link ez-toc-heading-6\" href=\"https:\/\/www.refrens.com\/grow\/ai-for-quality-assurance\/#Step_4_Evaluate_with_Real-World_Criteria\" title=\"Step 4: Evaluate with Real-World Criteria\">Step 4: Evaluate with Real-World Criteria<\/a><\/li><\/ul><\/li><\/ul><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-7\" href=\"https:\/\/www.refrens.com\/grow\/ai-for-quality-assurance\/#The_Hardest_Part_Convincing_the_Team\" title=\"The Hardest Part: Convincing the Team\">The Hardest Part: Convincing the Team<\/a><ul class='ez-toc-list-level-4' ><li class='ez-toc-heading-level-4'><ul class='ez-toc-list-level-4' ><li class='ez-toc-heading-level-4'><a class=\"ez-toc-link ez-toc-heading-8\" href=\"https:\/\/www.refrens.com\/grow\/ai-for-quality-assurance\/#What_We_Did_Differently_%E2%80%93\" title=\"What We Did Differently &#8211; \">What We Did Differently &#8211; <\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-4'><a class=\"ez-toc-link ez-toc-heading-9\" href=\"https:\/\/www.refrens.com\/grow\/ai-for-quality-assurance\/#Results_So_Far\" title=\"Results (So Far)\">Results (So Far)<\/a><\/li><\/ul><\/li><\/ul><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-10\" href=\"https:\/\/www.refrens.com\/grow\/ai-for-quality-assurance\/#TLDR\" title=\"TL;DR\">TL;DR<\/a><\/li><\/ul><\/nav><\/div>\n<h2 id=\"the-problem-qa-was-becoming-the-bottleneck\"><span class=\"ez-toc-section\" id=\"The_Problem_QA_Was_Becoming_the_Bottleneck\"><\/span>The Problem: QA Was Becoming the Bottleneck<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>As our product scaled, so did our bugs. Regression cycles stretched into weekends. Sanity checks turned into repetitive manual loops, and the team was buried under test reruns and flaky scripts.&nbsp;<\/p>\n\n\n\n<p>QA wasn\u2019t broken; it was exhausted.<\/p>\n\n\n\n<p>So, I dug deep into the world of <strong>AI QA automation tools<\/strong>, and along with Shivam, dove headfirst into a two-month long game of AI-hunt.<\/p>\n\n\n\n<div style=\"height:20px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<h2 id=\"the-exploration-40-ai-tools-2-months-1-spreadsheet\"><span class=\"ez-toc-section\" id=\"The_Exploration_40_AI_Tools_2_Months_1_Spreadsheet\"><\/span>The Exploration: 40+ AI Tools, 2 Months, 1 Spreadsheet<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>We tested over 40 tools: demos, trials, waitlists, crashes, you name it.<\/p>\n\n\n\n<p>Some tools were brilliant (@DevAssure, @<a href=\"http:\/\/kusho.ai\" target=\"_blank\" rel=\"noopener\">Kusho.ai<\/a>, @Reflect.run). Some were heavy, overpriced, or just mislabeled automation as AI. Some didn\u2019t work in India. And many looked great until you actually tried using them.&nbsp;<\/p>\n\n\n\n<p><em>\u201cWe didn\u2019t need another fancy dashboard; we needed time back.\u201d<\/em><\/p>\n\n\n\n<p>Here\u2019s the <strong>how-to<\/strong> that worked for me (and might for you):<\/p>\n\n\n\n<div style=\"height:10px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<h4 id=\"step-1-make-the-team-part-of-the-process\"><span class=\"ez-toc-section\" id=\"Step_1_Make_the_Team_Part_of_the_Process\"><\/span><strong>Step 1: Make the Team Part of the Process<\/strong><span class=\"ez-toc-section-end\"><\/span><\/h4>\n\n\n\n<p>I made sure to involve the QA team in demos. Let them crash the tools. Let them veto bad ones. Ownership builds buy-in.<\/p>\n\n\n\n<div style=\"height:10px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<h4 id=\"step-2-drowning-in-tools\"><span class=\"ez-toc-section\" id=\"Step_2_Drowning_in_Tools\"><\/span><strong>Step 2: Drowning in Tools&nbsp;<\/strong><span class=\"ez-toc-section-end\"><\/span><\/h4>\n\n\n\n<p>We built a monster spreadsheet. Every tool that claimed \u201cAI-powered QA\u201d made the list.<\/p>\n\n\n\n<p>We tested:<\/p>\n\n\n\n<figure class=\"wp-block-table is-style-stripes\"><table class=\"has-ast-global-color-5-background-color has-background\"><tbody><tr><td><strong><em>Tool<\/em><\/strong><\/td><td><strong><em>Why It\u2019s Good<\/em><\/strong><\/td><\/tr><tr><td><strong><em>Kusho.ai<\/em><\/strong><\/td><td><em>Generates Cypress scripts, strong UI\/API testing<\/em><\/td><\/tr><tr><td><strong><em>Qodex<\/em><\/strong><\/td><td><em>Great for API testing, lightweight alternative to Postman<\/em><\/td><\/tr><tr><td><strong><em>Keploy<\/em><\/strong><\/td><td><em>GitHub-integrated backend API testing with low entry cost<\/em><\/td><\/tr><tr><td><strong><em>LambdaTest<\/em><\/strong><\/td><td><em>UI testing + basic AI script generation<\/em><\/td><\/tr><tr><td><strong><em>Perfecto<\/em><\/strong><\/td><td><em>Mobile + web testing, codeless AI-based test creation<\/em><\/td><\/tr><tr><td><strong><em>Reflect.run<\/em><\/strong><\/td><td><em>Accurate no-code UI test creation with AI steps<\/em><\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n<p>Some tools were genuinely smart. Others just slapped &#8220;AI&#8221; on basic record-and-playback features. A few were beautiful but broke in India. Some charged over $20,000 a year for &#8220;enterprise&#8221; features we\u2019d never use.<\/p>\n\n\n\n<p>We crashed more tools than I care to admit.&nbsp;<\/p>\n\n\n\n<p>But every demo, every failed integration, every frustrated Slack message added to our learning.&nbsp;<\/p>\n\n\n\n<div style=\"height:10px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<h4 id=\"step-3-acknowledge-the-resistance\"><span class=\"ez-toc-section\" id=\"Step_3_Acknowledge_the_Resistance\"><\/span><strong>Step 3: Acknowledge the Resistance<\/strong><span class=\"ez-toc-section-end\"><\/span><\/h4>\n\n\n\n<p>Don\u2019t force the change. Our QA team wasn\u2019t anti-AI; they were anti-wasted-effort.&nbsp;<\/p>\n\n\n\n<p>They had valid concerns:<\/p>\n\n\n\n<ul><li>New tools take time to learn<br><\/li><li>Early-stage AI still needs guardrails<br><\/li><li>The last thing they wanted was another flaky system<\/li><\/ul>\n\n\n\n<p>So we picked <strong>just one workflow <\/strong>&#8211; sanity checks, and automated that first.<\/p>\n\n\n\n<div style=\"height:10px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<h4 id=\"step-4-evaluate-with-real-world-criteria\"><span class=\"ez-toc-section\" id=\"Step_4_Evaluate_with_Real-World_Criteria\"><\/span><strong>Step 4: Evaluate with Real-World Criteria<\/strong><span class=\"ez-toc-section-end\"><\/span><\/h4>\n\n\n\n<p>Before we even opened the first demo, we defined what &#8220;success&#8221; would look like.&nbsp;<\/p>\n\n\n\n<p>Our north star wasn\u2019t just AI for AI\u2019s sake, we needed tools that could make our testers less frustrated.<\/p>\n\n\n\n<p>Here\u2019s what we were really hoping a tool could do:<\/p>\n\n\n\n<ul><li>Run a pre-configured test&nbsp;<\/li><li>Generate test cases&nbsp;<\/li><li>Run new test cases&nbsp;<\/li><li>Check for visual change. &#8211; from previous version&nbsp;<\/li><li>Check for visual bugs and inconsistency&nbsp;<\/li><li>API testing&nbsp;<\/li><\/ul>\n\n\n\n<p>To keep things grounded, we created a scoring checklist that helped us objectively assess each tool:<\/p>\n\n\n\n<ul><li>Does it integrate smoothly with our pipelines and work?<\/li><li>Can it auto-generate or self-heal test cases as things evolve?<\/li><li>Is the onboarding process fast enough for a dev sprint?<\/li><li>Do the results make sense to both devs and testers?<\/li><li>Is the pricing realistic for an early-stage startup?<\/li><\/ul>\n\n\n\n<p>Spoiler: most tools failed on more than one front.<\/p>\n\n\n\n<div style=\"height:20px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<h2 id=\"the-hardest-part-convincing-the-team\"><span class=\"ez-toc-section\" id=\"The_Hardest_Part_Convincing_the_Team\"><\/span>The Hardest Part: Convincing the Team<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>\u201cOnce we had our tool shortlist, the next challenge was bigger, how do we actually get the team to trust them?\u201d<\/p>\n\n\n\n<p>Our QA team was sharp, overworked, and justifiably skeptical. The mood was clear:<\/p>\n\n\n\n<p><em>&nbsp;\u201cWhy fix what isn\u2019t broken?\u201d<\/em><em><br><\/em> <em>\u201cThis will only slow us down.\u201d<\/em><\/p>\n\n\n\n<p>And at first, they were right.<\/p>\n\n\n\n<p>Early tests were flaky. Onboarding felt like onboarding a new team member. Instead of saving time, we were analyzing more documentation just to understand the tool.<\/p>\n\n\n\n<p>I had moments where I questioned the entire idea.<\/p>\n\n\n\n<p>But we didn\u2019t give up.<\/p>\n\n\n\n<h4 id=\"what-we-did-differently\"><span class=\"ez-toc-section\" id=\"What_We_Did_Differently_%E2%80%93\"><\/span><strong>What We Did Differently<\/strong> &#8211; <span class=\"ez-toc-section-end\"><\/span><\/h4>\n\n\n\n<p>Instead of replacing existing processes, we made AI a quiet assistant:<\/p>\n\n\n\n<ul><li>Automated repetitive sanity checks<\/li><li>Let QA engineers focus on exploratory and edge cases<\/li><li>Started with <em>one<\/em> reliable suite, not the whole test pyramid<\/li><li>Avoided pushing AI into unstable flows<\/li><\/ul>\n\n\n\n<p class=\"has-medium-font-size\"><strong>The final choice: Devassure.<\/strong><\/p>\n\n\n\n<p>After weeks of experimentation, <strong>DevAssure<\/strong> stood out, not for being flashy, but for being practical:<\/p>\n\n\n\n<ul><li>Balanced UI + API testing<\/li><li>Stable test generation, didn\u2019t break on complex flows<\/li><li>Friendly pricing for startups<\/li><li>Incremental adoption with an amazing online support team<\/li><\/ul>\n\n\n\n<p>The team trusts the results. That\u2019s the win.<\/p>\n\n\n\n<h4 id=\"results-so-far\"><span class=\"ez-toc-section\" id=\"Results_So_Far\"><\/span><strong>Results (So Far)<\/strong><span class=\"ez-toc-section-end\"><\/span><\/h4>\n\n\n\n<ul><li>We adopted <strong>DevAssure<\/strong> for regression and sanity checks.<\/li><li>Fewer manual QA hours<\/li><li>Faster sanity checks<\/li><li>Happier testers and no more weekend regressions<\/li><li>And yes, I earned a few more \u201ccrazy project\u201d credits&nbsp;<\/li><\/ul>\n\n\n\n<div style=\"height:20px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<h2 id=\"tl-dr\"><span class=\"ez-toc-section\" id=\"TLDR\"><\/span>TL;DR<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<ul><li>QA was becoming a bottleneck due to growing bugs and lengthy regression cycles.<\/li><li>Over 40 AI tools were evaluated, including @DevAssure, @Kusho.ai, and @Reflect.run.<br><\/li><li><strong>Process:<br><\/strong><ul><li>Involved the QA team from the start through demos and hands-on testing.<br><\/li><li>Created a spreadsheet to track and compare features, pricing, and performance.<br><\/li><li>Focused on automating a single workflow (sanity checks) before scaling.<br><\/li><\/ul><\/li><li>After rigorous testing, DevAssure was chosen for its practical features and stable test generation.<br><\/li><li><strong>Outcome:<\/strong> Reduced manual QA hours, faster sanity checks, and increased trust in the automated results.<\/li><\/ul>\n\n\n\n<div style=\"height:12px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<p>For me, this wasn\u2019t just a crash course in tools, it was a masterclass in patience, persuasion, and the power of small wins.<\/p>\n\n\n\n<p>If you\u2019re in the middle of your own QA transformation or just starting out,&nbsp; feel free to reach out. I\u2019ll happily share our notes, lessons, and probably a rant or two about tools that almost made it.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>A founder&#8217;s intern tale of integrating AI for Quality Assurance Hi, I\u2019m Shreya Lakhera, a founder\u2019s office intern at Refrens.&nbsp; In a series of automating our workflows for different teams, I was tasked with a wild one: \u201cSee if we can use AI to improve our QA process.\u201d&nbsp; As someone obsessed with AI, I was &hellip;<\/p>\n<p class=\"read-more\"> <a class=\"\" href=\"https:\/\/www.refrens.com\/grow\/ai-for-quality-assurance\/\"> <span class=\"screen-reader-text\">A Comprehensive Guide to Automating QA Workflow<\/span> Read More &raquo;<\/a><\/p>\n","protected":false},"author":17,"featured_media":26204,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_uag_custom_page_level_css":"","site-sidebar-layout":"default","site-content-layout":"default","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","spay_email":""},"categories":[3],"tags":[],"jetpack_featured_media_url":"https:\/\/www.refrens.com\/grow\/wp-content\/uploads\/2025\/08\/Feature-Images-7.png","uagb_featured_image_src":{"full":["https:\/\/www.refrens.com\/grow\/wp-content\/uploads\/2025\/08\/Feature-Images-7.png",1280,720,false],"thumbnail":["https:\/\/www.refrens.com\/grow\/wp-content\/uploads\/2025\/08\/Feature-Images-7-150x84.png",150,84,true],"medium":["https:\/\/www.refrens.com\/grow\/wp-content\/uploads\/2025\/08\/Feature-Images-7-300x169.png",300,169,true],"medium_large":["https:\/\/www.refrens.com\/grow\/wp-content\/uploads\/2025\/08\/Feature-Images-7-768x432.png",768,432,true],"large":["https:\/\/www.refrens.com\/grow\/wp-content\/uploads\/2025\/08\/Feature-Images-7-1024x576.png",1024,576,true],"1536x1536":["https:\/\/www.refrens.com\/grow\/wp-content\/uploads\/2025\/08\/Feature-Images-7.png",1280,720,false],"2048x2048":["https:\/\/www.refrens.com\/grow\/wp-content\/uploads\/2025\/08\/Feature-Images-7.png",1280,720,false],"refrens-yarpp-thumbnail-w200":["https:\/\/www.refrens.com\/grow\/wp-content\/uploads\/2025\/08\/Feature-Images-7-200x112.png",200,112,true],"newspack-article-block-landscape-large":["https:\/\/www.refrens.com\/grow\/wp-content\/uploads\/2025\/08\/Feature-Images-7-1200x720.png",1200,720,true],"newspack-article-block-portrait-large":["https:\/\/www.refrens.com\/grow\/wp-content\/uploads\/2025\/08\/Feature-Images-7-900x720.png",900,720,true],"newspack-article-block-square-large":["https:\/\/www.refrens.com\/grow\/wp-content\/uploads\/2025\/08\/Feature-Images-7-1200x720.png",1200,720,true],"newspack-article-block-landscape-medium":["https:\/\/www.refrens.com\/grow\/wp-content\/uploads\/2025\/08\/Feature-Images-7-800x600.png",800,600,true],"newspack-article-block-portrait-medium":["https:\/\/www.refrens.com\/grow\/wp-content\/uploads\/2025\/08\/Feature-Images-7-600x720.png",600,720,true],"newspack-article-block-square-medium":["https:\/\/www.refrens.com\/grow\/wp-content\/uploads\/2025\/08\/Feature-Images-7-800x720.png",800,720,true],"newspack-article-block-landscape-small":["https:\/\/www.refrens.com\/grow\/wp-content\/uploads\/2025\/08\/Feature-Images-7-400x300.png",400,300,true],"newspack-article-block-portrait-small":["https:\/\/www.refrens.com\/grow\/wp-content\/uploads\/2025\/08\/Feature-Images-7-300x400.png",300,400,true],"newspack-article-block-square-small":["https:\/\/www.refrens.com\/grow\/wp-content\/uploads\/2025\/08\/Feature-Images-7-400x400.png",400,400,true],"newspack-article-block-landscape-tiny":["https:\/\/www.refrens.com\/grow\/wp-content\/uploads\/2025\/08\/Feature-Images-7-200x150.png",200,150,true],"newspack-article-block-portrait-tiny":["https:\/\/www.refrens.com\/grow\/wp-content\/uploads\/2025\/08\/Feature-Images-7-150x200.png",150,200,true],"newspack-article-block-square-tiny":["https:\/\/www.refrens.com\/grow\/wp-content\/uploads\/2025\/08\/Feature-Images-7-200x200.png",200,200,true],"newspack-article-block-uncropped":["https:\/\/www.refrens.com\/grow\/wp-content\/uploads\/2025\/08\/Feature-Images-7-1200x675.png",1200,675,true],"yarpp-thumbnail":["https:\/\/www.refrens.com\/grow\/wp-content\/uploads\/2025\/08\/Feature-Images-7-120x120.png",120,120,true],"web-stories-poster-portrait":["https:\/\/www.refrens.com\/grow\/wp-content\/uploads\/2025\/08\/Feature-Images-7-640x720.png",640,720,true],"web-stories-publisher-logo":["https:\/\/www.refrens.com\/grow\/wp-content\/uploads\/2025\/08\/Feature-Images-7-96x96.png",96,96,true],"web-stories-thumbnail":["https:\/\/www.refrens.com\/grow\/wp-content\/uploads\/2025\/08\/Feature-Images-7-150x84.png",150,84,true]},"uagb_author_info":{"display_name":"Shreya Lakhera","author_link":"https:\/\/www.refrens.com\/grow\/author\/sanjivni\/"},"uagb_comment_info":0,"uagb_excerpt":"A founder&#8217;s intern tale of integrating AI for Quality Assurance Hi, I\u2019m Shreya Lakhera, a founder\u2019s office intern at Refrens.&nbsp; In a series of automating our workflows for different teams, I was tasked with a wild one: \u201cSee if we can use AI to improve our QA process.\u201d&nbsp; As someone obsessed with AI, I was&hellip;","_links":{"self":[{"href":"https:\/\/www.refrens.com\/grow\/wp-json\/wp\/v2\/posts\/26203"}],"collection":[{"href":"https:\/\/www.refrens.com\/grow\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.refrens.com\/grow\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.refrens.com\/grow\/wp-json\/wp\/v2\/users\/17"}],"replies":[{"embeddable":true,"href":"https:\/\/www.refrens.com\/grow\/wp-json\/wp\/v2\/comments?post=26203"}],"version-history":[{"count":6,"href":"https:\/\/www.refrens.com\/grow\/wp-json\/wp\/v2\/posts\/26203\/revisions"}],"predecessor-version":[{"id":26214,"href":"https:\/\/www.refrens.com\/grow\/wp-json\/wp\/v2\/posts\/26203\/revisions\/26214"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.refrens.com\/grow\/wp-json\/wp\/v2\/media\/26204"}],"wp:attachment":[{"href":"https:\/\/www.refrens.com\/grow\/wp-json\/wp\/v2\/media?parent=26203"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.refrens.com\/grow\/wp-json\/wp\/v2\/categories?post=26203"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.refrens.com\/grow\/wp-json\/wp\/v2\/tags?post=26203"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}