{"id":23173,"date":"2026-04-16T08:15:00","date_gmt":"2026-04-16T15:15:00","guid":{"rendered":"https:\/\/www.microsoft.com\/insidetrack\/blog\/?p=23173"},"modified":"2026-04-20T08:24:59","modified_gmt":"2026-04-20T15:24:59","slug":"microsoft-ciso-advice-how-to-build-trustworthy-agentic-ai","status":"publish","type":"post","link":"https:\/\/www.microsoft.com\/insidetrack\/blog\/microsoft-ciso-advice-how-to-build-trustworthy-agentic-ai\/","title":{"rendered":"Microsoft CISO advice: How to build trustworthy agentic AI"},"content":{"rendered":"\n<p class=\"wp-block-paragraph\">Building production-ready solutions with agentic AI comes with inherent risks. When agents make mistakes or hallucinate, the potential impacts can multiply rapidly.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u201cIt turns out that it&#8217;s very easy to write AI-powered software, but it&#8217;s very hard to write AI-powered software that works right in real-world cases,\u201d says Yonatan Zunger, CVP and deputy CISO for Microsoft.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Yunger explains how important it is to test if you want to build trustworthy agentic AI.<\/p>\n\n\n\n<div class=\"wp-block-columns is-layout-flex wp-container-core-columns-is-layout-28f84493 wp-block-columns-is-layout-flex has-2-columns\">\n<div class=\"wp-block-column is-vertically-aligned-center is-layout-flow wp-block-column-is-layout-flow\" style=\"flex-basis:65px\">\n<figure class=\"wp-block-image aligncenter size-full is-resized\"><img loading=\"lazy\" decoding=\"async\" width=\"95\" height=\"96\" src=\"https:\/\/www.microsoft.com\/insidetrack\/blog\/uploads\/prod\/2025\/07\/Learn-how-p-g.png\" alt=\"\" class=\"wp-image-19668\" style=\"width:48px\"\/><\/figure>\n<\/div>\n\n\n\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\">\n<p class=\"wp-block-paragraph\" style=\"margin-top:var(--wp--preset--spacing--spacing-4);margin-bottom:var(--wp--preset--spacing--spacing-4)\"><strong><strong>Learn from our experience&nbsp;<\/strong><\/strong><\/p>\n\n\n\n<p class=\"wp-block-paragraph\" style=\"margin-top:var(--wp--preset--spacing--spacing-4);margin-bottom:var(--wp--preset--spacing--spacing-4)\"><a href=\"https:\/\/www.microsoft.com\/en-us\/security\/blog\/2026\/03\/31\/applying-security-fundamentals-to-ai-practical-advice-for-cisos\/\" target=\"_blank\" rel=\"noreferrer noopener\">Read our practical advice about applying security fundamentals to AI.<\/a><\/p>\n<\/div>\n<\/div>\n\n\n\n<figure class=\"wp-block-embed is-type-video is-provider-youtube wp-block-embed-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"wp-block-embed__wrapper\">\n <span class=\"embed-youtube\" style=\"text-align:center; display: block;\"><iframe loading=\"lazy\" class=\"youtube-player\" width=\"640\" height=\"360\" src=\"https:\/\/www.youtube.com\/embed\/eNU7c48541M?version=3&#038;rel=1&#038;showsearch=0&#038;showinfo=1&#038;iv_load_policy=1&#038;fs=1&#038;hl=en-US&#038;autohide=2&#038;wmode=transparent\" allowfullscreen=\"true\" style=\"border:0;\" sandbox=\"allow-scripts allow-same-origin allow-popups allow-presentation allow-popups-to-escape-sandbox\"><\/iframe><\/span>\n<\/div><figcaption class=\"wp-element-caption\"><em>Watch this video to see Yonatan Zunger explain how to build trustworthy agentic AI. (For a transcript, please view the video on YouTube: <\/em><a href=\"https:\/\/www.youtube.com\/watch?v=eNU7c48541M\" target=\"_blank\" rel=\"noreferrer noopener\"><em>https:\/\/www.youtube.com\/watch?v=eNU7c48541M<\/em><\/a>)<\/figcaption><\/figure>\n\n\n\n<div class=\"wp-block-group has-global-padding is-content-justification-left is-layout-constrained wp-container-core-group-is-layout-c0392459 wp-block-group-is-layout-constrained\" style=\"padding-right:0;padding-left:0\">\n<div class=\"wp-block-group has-global-padding is-layout-constrained wp-container-core-group-is-layout-7db9d80f wp-block-group-is-layout-constrained\" style=\"padding-right:0;padding-left:0\">\n<figure class=\"wp-block-image alignleft size-full is-resized\"><img loading=\"lazy\" decoding=\"async\" width=\"190\" height=\"190\" src=\"https:\/\/www.microsoft.com\/insidetrack\/blog\/uploads\/prod\/2025\/07\/Key-takeaways-badge.png\" alt=\"\" class=\"wp-image-19493\" style=\"object-fit:cover;width:75px;height:75px\" srcset=\"https:\/\/www.microsoft.com\/insidetrack\/blog\/uploads\/prod\/2025\/07\/Key-takeaways-badge.png 190w, https:\/\/www.microsoft.com\/insidetrack\/blog\/uploads\/prod\/2025\/07\/Key-takeaways-badge-150x150.png 150w\" sizes=\"auto, (max-width: 190px) 100vw, 190px\" \/><\/figure>\n\n\n\n<p class=\"has-body-xl-font-size wp-block-paragraph\" style=\"margin-top:var(--wp--preset--spacing--spacing-24);margin-bottom:0;padding-top:var(--wp--preset--spacing--spacing-24)\">Key takeaways<\/p>\n<\/div>\n\n\n\n<p class=\"wp-block-paragraph\">Here are best practices to apply while building trustworthy agentic AI:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li class=\"wp-block-list-item\"><strong>Prototype. Test. Iterate.<\/strong> Think of and try prompts your real users might give your agentic AI. Use real data. From those trials, build a set of test cases and keep testing.<\/li>\n\n\n\n<li class=\"wp-block-list-item\"><strong>Use AI tools to amplify testing.<\/strong> Evaluating agents requires a \u201ctry it and repeat it\u201d mindset. Using AI Foundry with such tools as Python Risk Identification Tool amplifies these assessment capabilities.<\/li>\n\n\n\n<li class=\"wp-block-list-item\"><strong>Record your tests<\/strong>. Applying this practice, as you would with unit testing, enables you to repeat evaluations as your data models and agents evolve.<\/li>\n\n\n\n<li class=\"wp-block-list-item\"><strong>Don\u2019t skimp on testing.<\/strong> Test early, test often, test with real data. This is the best way to understand what your agent might do when it encounters the unexpected.<\/li>\n<\/ul>\n<\/div>\n\n\n\n<div class=\"wp-block-group has-global-padding is-content-justification-left is-layout-constrained wp-container-core-group-is-layout-c0392459 wp-block-group-is-layout-constrained\" style=\"padding-right:0;padding-left:0\">\n<div class=\"wp-block-group has-global-padding is-layout-constrained wp-container-core-group-is-layout-7db9d80f wp-block-group-is-layout-constrained\" style=\"padding-right:0;padding-left:0\">\n<figure class=\"wp-block-image alignleft size-full is-resized\"><img loading=\"lazy\" decoding=\"async\" width=\"190\" height=\"190\" src=\"https:\/\/www.microsoft.com\/insidetrack\/blog\/uploads\/prod\/2025\/07\/Try-it-out-badge.png\" alt=\"\" class=\"wp-image-19492\" style=\"object-fit:cover;width:75px;height:75px\" srcset=\"https:\/\/www.microsoft.com\/insidetrack\/blog\/uploads\/prod\/2025\/07\/Try-it-out-badge.png 190w, https:\/\/www.microsoft.com\/insidetrack\/blog\/uploads\/prod\/2025\/07\/Try-it-out-badge-150x150.png 150w\" sizes=\"auto, (max-width: 190px) 100vw, 190px\" \/><\/figure>\n\n\n\n<p class=\"has-body-xl-font-size wp-block-paragraph\" style=\"margin-top:var(--wp--preset--spacing--spacing-24);margin-bottom:0;padding-top:var(--wp--preset--spacing--spacing-24)\">Try it out<\/p>\n<\/div>\n\n\n\n<ul class=\"wp-block-list is-style-list-no-bullets\">\n<li class=\"wp-block-list-item\"><a href=\"https:\/\/microsoft.github.io\/PyRIT\/?OCID=InsideTrack_Product_10871\" target=\"_blank\" rel=\"noreferrer noopener\">Find out how to deploy Python Risk Identification Tool (PyRIT).<\/a><\/li>\n\n\n\n<li class=\"wp-block-list-item\"><a href=\"https:\/\/learn.microsoft.com\/en-us\/azure\/foundry\/concepts\/concept-playgrounds?OCID=InsideTrack_Product_10871\" target=\"_blank\" rel=\"noreferrer noopener\">Explore how to use Microsoft Foundry Playgrounds to test your AI solutions.<\/a><\/li>\n<\/ul>\n<\/div>\n\n\n\n<div class=\"wp-block-group has-global-padding is-content-justification-left is-layout-constrained wp-container-core-group-is-layout-c0392459 wp-block-group-is-layout-constrained\" style=\"padding-right:0;padding-left:0\">\n<div class=\"wp-block-group has-global-padding is-layout-constrained wp-container-core-group-is-layout-7db9d80f wp-block-group-is-layout-constrained\" style=\"padding-right:0;padding-left:0\">\n<figure class=\"wp-block-image alignleft size-full is-resized\"><img loading=\"lazy\" decoding=\"async\" width=\"190\" height=\"190\" src=\"https:\/\/www.microsoft.com\/insidetrack\/blog\/uploads\/prod\/2025\/07\/Related-links-badge.png\" alt=\"\" class=\"wp-image-19491\" style=\"object-fit:cover;width:75px;height:75px\" srcset=\"https:\/\/www.microsoft.com\/insidetrack\/blog\/uploads\/prod\/2025\/07\/Related-links-badge.png 190w, https:\/\/www.microsoft.com\/insidetrack\/blog\/uploads\/prod\/2025\/07\/Related-links-badge-150x150.png 150w\" sizes=\"auto, (max-width: 190px) 100vw, 190px\" \/><\/figure>\n\n\n\n<p class=\"has-body-xl-font-size wp-block-paragraph\" style=\"margin-top:var(--wp--preset--spacing--spacing-24);margin-bottom:0;padding-top:var(--wp--preset--spacing--spacing-24)\">Related links<\/p>\n<\/div>\n\n\n\n<ul style=\"margin-top:var(--wp--preset--spacing--spacing-20)\" class=\"wp-block-list\">\n<li class=\"wp-block-list-item\"><a href=\"https:\/\/www.microsoft.com\/insidetrack\/blog\/microsoft-ciso-advice-the-importance-of-a-written-ai-safety-plan\/\">Read more about how to secure agentic AI.<\/a><\/li>\n\n\n\n<li class=\"wp-block-list-item\"><a href=\"https:\/\/www.microsoft.com\/en-us\/security\/blog\/2025\/05\/29\/how-to-deploy-ai-safely\/\" target=\"_blank\" rel=\"noreferrer noopener\">Learn more from Zunger about how to deploy AI safely.<\/a><\/li>\n\n\n\n<li class=\"wp-block-list-item\"><a href=\"https:\/\/www.microsoft.com\/en-us\/security\/blog\/2025\/08\/26\/securing-and-governing-the-rise-of-autonomous-agents\/\" target=\"_blank\" rel=\"noreferrer noopener\">Discover what you need to know about governing autonomous agents.<\/a><\/li>\n\n\n\n<li class=\"wp-block-list-item\"><a href=\"https:\/\/www.microsoft.com\/en-us\/security\/blog\/2025\/03\/04\/securing-generative-ai-models-on-azure-ai-foundry\/\" target=\"_blank\" rel=\"noreferrer noopener\">Explore how to use Azure AI Foundry to secure generative AI models.<\/a><\/li>\n\n\n\n<li class=\"wp-block-list-item\"><a href=\"https:\/\/learn.microsoft.com\/en-us\/azure\/foundry\/fine-tuning\/data-generation\" target=\"_blank\" rel=\"noreferrer noopener\">Generate synthetic data for fine-tuning in Microsoft Foundry.<\/a><\/li>\n\n\n\n<li class=\"wp-block-list-item\"><a href=\"https:\/\/learn.microsoft.com\/en-us\/azure\/foundry\/how-to\/model-deployment-policy\" target=\"_blank\" rel=\"noreferrer noopener\">Leverage built-in policies for model deployment in Microsoft Foundry.<\/a><\/li>\n<\/ul>\n<\/div>\n\n\n\n<div class=\"wp-block-group has-global-padding is-content-justification-left is-layout-constrained wp-container-core-group-is-layout-c0392459 wp-block-group-is-layout-constrained\" style=\"padding-right:0;padding-left:0\">\n<div class=\"wp-block-group has-global-padding is-layout-constrained wp-container-core-group-is-layout-7db9d80f wp-block-group-is-layout-constrained\" style=\"padding-right:0;padding-left:0\">\n<figure class=\"wp-block-image alignleft size-full is-resized\"><img loading=\"lazy\" decoding=\"async\" width=\"190\" height=\"190\" src=\"https:\/\/www.microsoft.com\/insidetrack\/blog\/uploads\/prod\/2025\/07\/Wed-like-to-hear-from-you-badge.png\" alt=\"\" class=\"wp-image-19490\" style=\"object-fit:cover;width:75px;height:75px\" srcset=\"https:\/\/www.microsoft.com\/insidetrack\/blog\/uploads\/prod\/2025\/07\/Wed-like-to-hear-from-you-badge.png 190w, https:\/\/www.microsoft.com\/insidetrack\/blog\/uploads\/prod\/2025\/07\/Wed-like-to-hear-from-you-badge-150x150.png 150w\" sizes=\"auto, (max-width: 190px) 100vw, 190px\" \/><\/figure>\n\n\n\n<p class=\"has-body-xl-font-size wp-block-paragraph\" style=\"margin-top:var(--wp--preset--spacing--spacing-24);margin-bottom:0;padding-top:var(--wp--preset--spacing--spacing-24)\">We&#8217;d like to hear from you!<\/p>\n<\/div>\n\n\n\n<ul style=\"margin-top:var(--wp--preset--spacing--spacing-20)\" class=\"wp-block-list is-style-list-no-bullets\">\n<li class=\"wp-block-list-item\"><a href=\"mailto:msitstaff@microsoft.com\">Want more information? Email us and include a link to this story and we\u2019ll get back to you.<\/a><\/li>\n<\/ul>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>Building production-ready solutions with agentic AI comes with inherent risks. When agents make mistakes or hallucinate, the potential impacts can multiply rapidly. \u201cIt turns out that it&#8217;s very easy to write AI-powered software, but it&#8217;s very hard to write AI-powered software that works right in real-world cases,\u201d says Yonatan Zunger, CVP and deputy CISO for [&hellip;]<\/p>\n","protected":false},"author":228,"featured_media":23175,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":true,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_hide_featured_on_single":false,"_show_featured_caption_on_single":true,"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[896],"tags":[864,868,897,263,848,419],"coauthors":[895],"class_list":["post-23173","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-office-of-the-ciso","tag-agent","tag-ai-deployment-and-adoption","tag-cybersecurity","tag-microsoft-365","tag-security-and-risk-management","tag-zero-trust","m-blog-post"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.3 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Microsoft CISO advice: How to build trustworthy agentic AI - Inside Track Blog<\/title>\n<meta name=\"description\" content=\"Corporate Vice President and Deputy Chief Information Security Officer Yonatan Zunger explains the importance of rigorous testing when building trustworthy agentic AI.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.microsoft.com\/insidetrack\/blog\/microsoft-ciso-advice-how-to-build-trustworthy-agentic-ai\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Microsoft CISO advice: How to build trustworthy agentic AI - Inside Track Blog\" \/>\n<meta property=\"og:description\" content=\"Corporate Vice President and Deputy Chief Information Security Officer Yonatan Zunger explains the importance of rigorous testing when building trustworthy agentic AI.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.microsoft.com\/insidetrack\/blog\/microsoft-ciso-advice-how-to-build-trustworthy-agentic-ai\/\" \/>\n<meta property=\"og:site_name\" content=\"Inside Track Blog\" \/>\n<meta property=\"article:published_time\" content=\"2026-04-16T15:15:00+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2026-04-20T15:24:59+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.microsoft.com\/insidetrack\/blog\/uploads\/prod\/2026\/04\/10871-Hero_image.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"2300\" \/>\n\t<meta property=\"og:image:height\" content=\"1293\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Rani Lofstrom\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Rani Lofstrom\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/www.microsoft.com\\\/insidetrack\\\/blog\\\/microsoft-ciso-advice-how-to-build-trustworthy-agentic-ai\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.microsoft.com\\\/insidetrack\\\/blog\\\/microsoft-ciso-advice-how-to-build-trustworthy-agentic-ai\\\/\"},\"author\":{\"name\":\"Rani Lofstrom\",\"@id\":\"https:\\\/\\\/www.microsoft.com\\\/insidetrack\\\/blog\\\/#\\\/schema\\\/person\\\/a84c77f9cb72a705f03dfbc214dd817e\"},\"headline\":\"Microsoft CISO advice: How to build trustworthy agentic AI\",\"datePublished\":\"2026-04-16T15:15:00+00:00\",\"dateModified\":\"2026-04-20T15:24:59+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/www.microsoft.com\\\/insidetrack\\\/blog\\\/microsoft-ciso-advice-how-to-build-trustworthy-agentic-ai\\\/\"},\"wordCount\":378,\"image\":{\"@id\":\"https:\\\/\\\/www.microsoft.com\\\/insidetrack\\\/blog\\\/microsoft-ciso-advice-how-to-build-trustworthy-agentic-ai\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/www.microsoft.com\\\/insidetrack\\\/blog\\\/uploads\\\/prod\\\/2026\\\/04\\\/10871-Hero_image.jpg\",\"keywords\":[\"Agent\",\"AI deployment and adoption\",\"Cybersecurity\",\"Microsoft 365\",\"Security and risk management\",\"Zero Trust\"],\"articleSection\":[\"Office of the CISO\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/www.microsoft.com\\\/insidetrack\\\/blog\\\/microsoft-ciso-advice-how-to-build-trustworthy-agentic-ai\\\/\",\"url\":\"https:\\\/\\\/www.microsoft.com\\\/insidetrack\\\/blog\\\/microsoft-ciso-advice-how-to-build-trustworthy-agentic-ai\\\/\",\"name\":\"Microsoft CISO advice: How to build trustworthy agentic AI - Inside Track Blog\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.microsoft.com\\\/insidetrack\\\/blog\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/www.microsoft.com\\\/insidetrack\\\/blog\\\/microsoft-ciso-advice-how-to-build-trustworthy-agentic-ai\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/www.microsoft.com\\\/insidetrack\\\/blog\\\/microsoft-ciso-advice-how-to-build-trustworthy-agentic-ai\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/www.microsoft.com\\\/insidetrack\\\/blog\\\/uploads\\\/prod\\\/2026\\\/04\\\/10871-Hero_image.jpg\",\"datePublished\":\"2026-04-16T15:15:00+00:00\",\"dateModified\":\"2026-04-20T15:24:59+00:00\",\"author\":{\"@id\":\"https:\\\/\\\/www.microsoft.com\\\/insidetrack\\\/blog\\\/#\\\/schema\\\/person\\\/a84c77f9cb72a705f03dfbc214dd817e\"},\"description\":\"Corporate Vice President and Deputy Chief Information Security Officer Yonatan Zunger explains the importance of rigorous testing when building trustworthy agentic AI.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/www.microsoft.com\\\/insidetrack\\\/blog\\\/microsoft-ciso-advice-how-to-build-trustworthy-agentic-ai\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/www.microsoft.com\\\/insidetrack\\\/blog\\\/microsoft-ciso-advice-how-to-build-trustworthy-agentic-ai\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/www.microsoft.com\\\/insidetrack\\\/blog\\\/microsoft-ciso-advice-how-to-build-trustworthy-agentic-ai\\\/#primaryimage\",\"url\":\"https:\\\/\\\/www.microsoft.com\\\/insidetrack\\\/blog\\\/uploads\\\/prod\\\/2026\\\/04\\\/10871-Hero_image.jpg\",\"contentUrl\":\"https:\\\/\\\/www.microsoft.com\\\/insidetrack\\\/blog\\\/uploads\\\/prod\\\/2026\\\/04\\\/10871-Hero_image.jpg\",\"width\":2300,\"height\":1293,\"caption\":\"Corporate Vice President and Deputy Chief Information Security Officer Yonatan Zunger explains the importance of rigorous testing when building trustworthy agentic AI.\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/www.microsoft.com\\\/insidetrack\\\/blog\\\/microsoft-ciso-advice-how-to-build-trustworthy-agentic-ai\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/www.microsoft.com\\\/insidetrack\\\/blog\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Microsoft CISO advice: How to build trustworthy agentic AI\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/www.microsoft.com\\\/insidetrack\\\/blog\\\/#website\",\"url\":\"https:\\\/\\\/www.microsoft.com\\\/insidetrack\\\/blog\\\/\",\"name\":\"Inside Track Blog\",\"description\":\"How Microsoft does IT\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/www.microsoft.com\\\/insidetrack\\\/blog\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/www.microsoft.com\\\/insidetrack\\\/blog\\\/#\\\/schema\\\/person\\\/a84c77f9cb72a705f03dfbc214dd817e\",\"name\":\"Rani Lofstrom\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/88c3eec1cb70ef934ce9039cd3d24ebd790bdd4d17bba4e5c1cab34692f73822?s=96&d=mm&r=g1f4b72779f158e872aad1ea503fc8b81\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/88c3eec1cb70ef934ce9039cd3d24ebd790bdd4d17bba4e5c1cab34692f73822?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/88c3eec1cb70ef934ce9039cd3d24ebd790bdd4d17bba4e5c1cab34692f73822?s=96&d=mm&r=g\",\"caption\":\"Rani Lofstrom\"},\"url\":\"https:\\\/\\\/www.microsoft.com\\\/insidetrack\\\/blog\\\/author\\\/rlofstrom\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Microsoft CISO advice: How to build trustworthy agentic AI - Inside Track Blog","description":"Corporate Vice President and Deputy Chief Information Security Officer Yonatan Zunger explains the importance of rigorous testing when building trustworthy agentic AI.","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:\/\/www.microsoft.com\/insidetrack\/blog\/microsoft-ciso-advice-how-to-build-trustworthy-agentic-ai\/","og_locale":"en_US","og_type":"article","og_title":"Microsoft CISO advice: How to build trustworthy agentic AI - Inside Track Blog","og_description":"Corporate Vice President and Deputy Chief Information Security Officer Yonatan Zunger explains the importance of rigorous testing when building trustworthy agentic AI.","og_url":"https:\/\/www.microsoft.com\/insidetrack\/blog\/microsoft-ciso-advice-how-to-build-trustworthy-agentic-ai\/","og_site_name":"Inside Track Blog","article_published_time":"2026-04-16T15:15:00+00:00","article_modified_time":"2026-04-20T15:24:59+00:00","og_image":[{"width":2300,"height":1293,"url":"https:\/\/www.microsoft.com\/insidetrack\/blog\/uploads\/prod\/2026\/04\/10871-Hero_image.jpg","type":"image\/jpeg"}],"author":"Rani Lofstrom","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Rani Lofstrom","Est. reading time":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.microsoft.com\/insidetrack\/blog\/microsoft-ciso-advice-how-to-build-trustworthy-agentic-ai\/#article","isPartOf":{"@id":"https:\/\/www.microsoft.com\/insidetrack\/blog\/microsoft-ciso-advice-how-to-build-trustworthy-agentic-ai\/"},"author":{"name":"Rani Lofstrom","@id":"https:\/\/www.microsoft.com\/insidetrack\/blog\/#\/schema\/person\/a84c77f9cb72a705f03dfbc214dd817e"},"headline":"Microsoft CISO advice: How to build trustworthy agentic AI","datePublished":"2026-04-16T15:15:00+00:00","dateModified":"2026-04-20T15:24:59+00:00","mainEntityOfPage":{"@id":"https:\/\/www.microsoft.com\/insidetrack\/blog\/microsoft-ciso-advice-how-to-build-trustworthy-agentic-ai\/"},"wordCount":378,"image":{"@id":"https:\/\/www.microsoft.com\/insidetrack\/blog\/microsoft-ciso-advice-how-to-build-trustworthy-agentic-ai\/#primaryimage"},"thumbnailUrl":"https:\/\/www.microsoft.com\/insidetrack\/blog\/uploads\/prod\/2026\/04\/10871-Hero_image.jpg","keywords":["Agent","AI deployment and adoption","Cybersecurity","Microsoft 365","Security and risk management","Zero Trust"],"articleSection":["Office of the CISO"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/www.microsoft.com\/insidetrack\/blog\/microsoft-ciso-advice-how-to-build-trustworthy-agentic-ai\/","url":"https:\/\/www.microsoft.com\/insidetrack\/blog\/microsoft-ciso-advice-how-to-build-trustworthy-agentic-ai\/","name":"Microsoft CISO advice: How to build trustworthy agentic AI - Inside Track Blog","isPartOf":{"@id":"https:\/\/www.microsoft.com\/insidetrack\/blog\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.microsoft.com\/insidetrack\/blog\/microsoft-ciso-advice-how-to-build-trustworthy-agentic-ai\/#primaryimage"},"image":{"@id":"https:\/\/www.microsoft.com\/insidetrack\/blog\/microsoft-ciso-advice-how-to-build-trustworthy-agentic-ai\/#primaryimage"},"thumbnailUrl":"https:\/\/www.microsoft.com\/insidetrack\/blog\/uploads\/prod\/2026\/04\/10871-Hero_image.jpg","datePublished":"2026-04-16T15:15:00+00:00","dateModified":"2026-04-20T15:24:59+00:00","author":{"@id":"https:\/\/www.microsoft.com\/insidetrack\/blog\/#\/schema\/person\/a84c77f9cb72a705f03dfbc214dd817e"},"description":"Corporate Vice President and Deputy Chief Information Security Officer Yonatan Zunger explains the importance of rigorous testing when building trustworthy agentic AI.","breadcrumb":{"@id":"https:\/\/www.microsoft.com\/insidetrack\/blog\/microsoft-ciso-advice-how-to-build-trustworthy-agentic-ai\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.microsoft.com\/insidetrack\/blog\/microsoft-ciso-advice-how-to-build-trustworthy-agentic-ai\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.microsoft.com\/insidetrack\/blog\/microsoft-ciso-advice-how-to-build-trustworthy-agentic-ai\/#primaryimage","url":"https:\/\/www.microsoft.com\/insidetrack\/blog\/uploads\/prod\/2026\/04\/10871-Hero_image.jpg","contentUrl":"https:\/\/www.microsoft.com\/insidetrack\/blog\/uploads\/prod\/2026\/04\/10871-Hero_image.jpg","width":2300,"height":1293,"caption":"Corporate Vice President and Deputy Chief Information Security Officer Yonatan Zunger explains the importance of rigorous testing when building trustworthy agentic AI."},{"@type":"BreadcrumbList","@id":"https:\/\/www.microsoft.com\/insidetrack\/blog\/microsoft-ciso-advice-how-to-build-trustworthy-agentic-ai\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.microsoft.com\/insidetrack\/blog\/"},{"@type":"ListItem","position":2,"name":"Microsoft CISO advice: How to build trustworthy agentic AI"}]},{"@type":"WebSite","@id":"https:\/\/www.microsoft.com\/insidetrack\/blog\/#website","url":"https:\/\/www.microsoft.com\/insidetrack\/blog\/","name":"Inside Track Blog","description":"How Microsoft does IT","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.microsoft.com\/insidetrack\/blog\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/www.microsoft.com\/insidetrack\/blog\/#\/schema\/person\/a84c77f9cb72a705f03dfbc214dd817e","name":"Rani Lofstrom","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/88c3eec1cb70ef934ce9039cd3d24ebd790bdd4d17bba4e5c1cab34692f73822?s=96&d=mm&r=g1f4b72779f158e872aad1ea503fc8b81","url":"https:\/\/secure.gravatar.com\/avatar\/88c3eec1cb70ef934ce9039cd3d24ebd790bdd4d17bba4e5c1cab34692f73822?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/88c3eec1cb70ef934ce9039cd3d24ebd790bdd4d17bba4e5c1cab34692f73822?s=96&d=mm&r=g","caption":"Rani Lofstrom"},"url":"https:\/\/www.microsoft.com\/insidetrack\/blog\/author\/rlofstrom\/"}]}},"jetpack_featured_media_url":"https:\/\/www.microsoft.com\/insidetrack\/blog\/uploads\/prod\/2026\/04\/10871-Hero_image.jpg","jetpack_sharing_enabled":true,"jetpack_shortlink":"https:\/\/wp.me\/p9hcZA-61L","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/insidetrack\/blog\/wp-json\/wp\/v2\/posts\/23173","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.microsoft.com\/insidetrack\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.microsoft.com\/insidetrack\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/insidetrack\/blog\/wp-json\/wp\/v2\/users\/228"}],"replies":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/insidetrack\/blog\/wp-json\/wp\/v2\/comments?post=23173"}],"version-history":[{"count":5,"href":"https:\/\/www.microsoft.com\/insidetrack\/blog\/wp-json\/wp\/v2\/posts\/23173\/revisions"}],"predecessor-version":[{"id":23309,"href":"https:\/\/www.microsoft.com\/insidetrack\/blog\/wp-json\/wp\/v2\/posts\/23173\/revisions\/23309"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/insidetrack\/blog\/wp-json\/wp\/v2\/media\/23175"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/insidetrack\/blog\/wp-json\/wp\/v2\/media?parent=23173"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.microsoft.com\/insidetrack\/blog\/wp-json\/wp\/v2\/categories?post=23173"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.microsoft.com\/insidetrack\/blog\/wp-json\/wp\/v2\/tags?post=23173"},{"taxonomy":"author","embeddable":true,"href":"https:\/\/www.microsoft.com\/insidetrack\/blog\/wp-json\/wp\/v2\/coauthors?post=23173"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}