{"id":33120,"date":"2026-04-15T14:38:57","date_gmt":"2026-04-15T21:38:57","guid":{"rendered":"https:\/\/www.pingcap.com\/?p=33120"},"modified":"2026-04-17T14:45:35","modified_gmt":"2026-04-17T21:45:35","slug":"what-makes-a-database-for-ai-agents-different","status":"publish","type":"post","link":"https:\/\/www.pingcap.com\/ko\/blog\/what-makes-a-database-for-ai-agents-different\/","title":{"rendered":"What Happens to a Database When the User is an AI agent"},"content":{"rendered":"<p><em>Editor\u2019s note: This post originally appeared on The New Stack and is republished with permission. The original version is available\u00a0<a href=\"https:\/\/thenewstack.io\/databases-for-ai-agents\/\">\uc5ec\uae30<\/a>.<\/em><\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Key_Takeaways\"><\/span><strong>Key Takeaways<\/strong><span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Agents are becoming the primary database users<\/strong>, with fundamentally different needs: speed over ease of use, ephemerality over durability.<\/li>\n\n\n\n<li><strong>Elastic scale is non-negotiable.<\/strong> Separating compute from storage (like TiDB X) handles agent activity spikes without replicating entire clusters.<\/li>\n\n\n\n<li><strong>Isolation keeps agents safe.<\/strong> Serverless branching gives each agent a copy-on-write environment to experiment without noisy-neighbor conflicts, as Manus proved at scale.<\/li>\n\n\n\n<li><strong>Today&#8217;s infrastructure choices will decide who wins the agentic era.<\/strong> Databases optimized for human convenience will fall behind those built for agent speed.<\/li>\n<\/ul>\n<\/blockquote>\n\n\n\n<p>In the past, we judged enterprise databases by how useful they were to people like us. We rated them on how well they helped architects create schemas, DBAs plan capacity, and analysts build queries.&nbsp;<\/p>\n\n\n\n<p>We expected databases to last a long time \u2014 years, probably \u2014 powering sales reports and quarterly projections, growing with the organization.&nbsp;<\/p>\n\n\n\n<p>But now comes a new kind of user: the AI agent. It has different needs. It operates at a different pace. It uses databases to do its work. But once its task is complete, the database can be discarded.<\/p>\n\n\n\n<p>We might imagine a database designed for humans as a time-lapse cityscape viewed from above. Throughout the scene, cranes and bulldozers are busy adding and removing structures, leaving most buildings intact. The details change, but the overall shape of the city and the relationships among its parts remain relatively stable.<\/p>\n\n\n\n<p>A database designed with agents in mind would look quite different. Rather than an interconnected network of streets and buildings \u2014 analogous to a traditional relational database \u2014 the scene is constantly shifting. Apartments and city blocks with no relation to one another pop in and out of existence faster than the eye can register. High-speed photography reveals that the structures are oddly sculpted. They\u2019re not designed for human use. Their shape, location, and above all, their ephemerality, serve the needs of digital users.<\/p>\n\n\n\n<p>All signs suggest that, in the near future, agents, not humans, will be the primary users of databases.\u00a0So, how will databases need to change?<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"A_Database_for_AI_Agents_Will_Need_to_Prioritize_Speed_Over_Ease_of_Use\"><\/span>A Database for AI Agents Will Need to Prioritize Speed Over Ease of Use<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>Like humans, agents plan tasks, execute actions, observe outcomes, and adapt based on what they learn. But unlike humans, agents operate faster than thought. They don\u2019t care about ease of use.&nbsp;<\/p>\n\n\n\n<p>First and foremost, the AI agent values speed. Availability, too, and responsiveness. But speed most of all.<\/p>\n\n\n\n<p>Agents access data continuously. They generate furious spikes in activity and discard their workspace once their work is complete. Their work \u201chabits\u201d strain databases optimized for the infinitely slower, more deliberate interactions of a human user.&nbsp;<\/p>\n\n\n\n<p>As my colleague and cofounder Ed Huang <a href=\"https:\/\/www.pingcap.com\/ko\/blog\/agentic-ai-database-trends-that-will-define-2026\/\">put it<\/a>: \u201cAgents do not slow down, and they do not optimize unless you force them to. Their natural state is a combinatorial explosion.\u201d&nbsp;<\/p>\n\n\n\n<p>A database platform designed for AI agents needs to respond as fast as AI can act.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"A_Database_for_AI_Agents_Will_Also_Have_to_Build_for_Elastic_Ephemerality\"><\/span>A Database for AI Agents Will Also Have to Build for Elastic Ephemerality&nbsp;<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>Typically, scaling up a cloud database involves copying entire clusters of data. As we\u2019ve discussed <a href=\"https:\/\/www.pingcap.com\/ko\/blog\/agentic-ai-systems-architecture-4-decisions-that-scale\/\">elsewhere<\/a>, this is due to the limitations of enterprise networks. To keep performance high, data needs to live near compute. But replicating and persisting data takes time and adds cost.<\/p>\n\n\n\n<p>In human-centric databases, these inefficiencies are undesirable; in AI-centric databases, they\u2019re untenable.<\/p>\n\n\n\n<p>It\u2019s impractical and wasteful to spin up new data clusters whenever an agent spikes CPU usage. AI-friendly databases will need to scale compute up and down while minimizing the impact on local storage and storage costs.&nbsp;<\/p>\n\n\n\n<p>Architectures that separate compute from storage address this requirement directly, especially architectures like TiDB X, which uses cloud object storage as its backbone. In TiDB X, compute scales elastically based on workload intensity and type. Cold data remains in object storage, where costs are minimal. Frequently accessed data is cached near the computer for low-latency performance.<\/p>\n\n\n\n<p>This <a href=\"https:\/\/www.pingcap.com\/ko\/press-release\/pingcap-launches-tidb-x-new-ai-capabilities\/?utm_source=chatgpt.com\">design <\/a>supports rapid scale-up during periods of activity and rapid scale-down when demand subsides, exactly how AI works.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"And_a_Database_for_AI_Agents_Will_Have_to_Enforce_Safety_Through_Isolation\"><\/span>And a Database for AI Agents Will Have to Enforce Safety Through Isolation<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>Agents can be unpredictable. They need guardrails. To support agentic users, databases must provide environments where agents can operate safely, without fear of damaging anything important.<br><br>Serverless branching can be a useful approach. A branching-capable database like TiDB Cloud can create isolated, copy-on-write environments where an agent can work with real data without fear of overwhelming the system\u2019s capacity or corrupting data.<\/p>\n\n\n\n<p>The <a href=\"https:\/\/www.pingcap.com\/ko\/case-study\/manus-agentic-ai-database-tidb\/\">experience<\/a> of Manus, a general-purpose agentic AI platform that amassed millions of users in weeks, illustrates this well. Manus\u2019s \u201cContext Engineering\u201d model generated thousands of iterations per task, each storing state as it went. This required extraordinary read\/write performance.<br><br>Furthermore,<em> <\/em>Manus wanted to create agentic swarms capable of solving complex problems in parallel. Its engineering team needed to support massive concurrency while avoiding \u201cnoisy neighbor\u201d conflicts.&nbsp;<\/p>\n\n\n\n<p>But this level of concurrency would have been impossible with a non-branching architecture. With TiDB Cloud, Manus enabled each agent \u2014 or group of agents \u2014 to fork the database, run experiments, and commit results independently.&nbsp;<\/p>\n\n\n\n<p>This enabled Manus\u2019s agents to evaluate alternative approaches concurrently, compare outcomes, and retain only the results that mattered.&nbsp;<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Preparing_for_an_Agent-First_Future\"><\/span>Preparing for an Agent-First Future<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>Most enterprises are still in the early stages of adopting agentic AI. Yet the infrastructure choices they make now will determine the speed and success of their efforts.&nbsp;<\/p>\n\n\n\n<p>As human users give way to agents, it no longer makes sense to optimize databases for durability, visibility, or ease of use. Agent thrives in environments optimized for rapid creation and teardown, object-based storage, and strong isolation. Ephemerality is the new watchword. Speed is the first priority.&nbsp;<\/p>\n\n\n\n<p>Letting agents into your database doesn\u2019t mean giving up control. It just means control will be enforced through architecture and automation rather than manual human intervention. Databases \u2014 and organizations \u2014 that embrace these principles will be able to get the most out of their agentic employees. Those who do not will inevitably fall behind their peers in a world where AI sets the pace.<\/p>\n\n\n\n<p><em>Manus didn&#8217;t just theorize about agent-first infrastructure. They built on it. Facing thousands of context iterations per task and the need to run agentic swarms in parallel, Manus turned to TiDB Cloud&#8217;s serverless branching to give every agent its own isolated, copy-on-write environment. The result: massive concurrency without noisy-neighbor conflicts, and the freedom to experiment, compare, and commit only what matters.<\/em><\/p>","protected":false},"excerpt":{"rendered":"<p>Editor\u2019s note: This post originally appeared on The New Stack and is republished with permission. The original version is available\u00a0here. In the past, we judged enterprise databases by how useful they were to people like us. We rated them on how well they helped architects create schemas, DBAs plan capacity, and analysts build queries.&nbsp; We [&hellip;]<\/p>\n","protected":false},"author":50,"featured_media":33151,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"ub_ctt_via":"","footnotes":""},"categories":[145],"tags":[483,484,147,485,111],"class_list":["post-33120","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-thought-leadership","tag-ai-agents","tag-database-branching","tag-distributed-sql","tag-manus","tag-tidb"],"acf":[],"featured_image_src":"https:\/\/static.pingcap.com\/files\/2026\/04\/17144530\/Webinar-LP-Banner-4.png","author_info":{"display_name":"Max Liu","author_link":"https:\/\/www.pingcap.com\/ko\/blog\/author\/max-liu\/"},"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v26.9 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>What Makes a Database for AI Agents Different<\/title>\n<meta name=\"description\" content=\"Agents are the new primary users. See why a database for AI agents must prioritize speed, elastic scale, and isolation over ease of use.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/thenewstack.io\/databases-for-ai-agents\/\" \/>\n<meta property=\"og:locale\" content=\"ko_KR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"What Makes a Database for AI Agents Different\" \/>\n<meta property=\"og:description\" content=\"Agents are the new primary users. See why a database for AI agents must prioritize speed, elastic scale, and isolation over ease of use.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/thenewstack.io\/databases-for-ai-agents\/\" \/>\n<meta property=\"og:site_name\" content=\"TiDB\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/facebook.com\/pingcap2015\" \/>\n<meta property=\"article:published_time\" content=\"2026-04-15T21:38:57+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2026-04-17T21:45:35+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/static.pingcap.com\/files\/2026\/04\/17143028\/Blog-LinkedIn-1.png\" \/>\n\t<meta property=\"og:image:width\" content=\"1200\" \/>\n\t<meta property=\"og:image:height\" content=\"627\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"Max Liu\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:image\" content=\"https:\/\/static.pingcap.com\/files\/2026\/04\/17143043\/Blog-Feature-Banner-1.png\" \/>\n<meta name=\"twitter:creator\" content=\"@PingCAP\" \/>\n<meta name=\"twitter:site\" content=\"@PingCAP\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Max Liu\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"6\ubd84\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/thenewstack.io\/databases-for-ai-agents\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/www.pingcap.com\/blog\/what-makes-a-database-for-ai-agents-different\/\"},\"author\":{\"name\":\"Max Liu\",\"@id\":\"https:\/\/www.pingcap.com\/#\/schema\/person\/7aeccb8936b7f908f923bdd0a6b44be8\"},\"headline\":\"What Happens to a Database When the User is an AI agent\",\"datePublished\":\"2026-04-15T21:38:57+00:00\",\"dateModified\":\"2026-04-17T21:45:35+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/www.pingcap.com\/blog\/what-makes-a-database-for-ai-agents-different\/\"},\"wordCount\":1118,\"publisher\":{\"@id\":\"https:\/\/www.pingcap.com\/#organization\"},\"image\":{\"@id\":\"https:\/\/thenewstack.io\/databases-for-ai-agents\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/static.pingcap.com\/files\/2026\/04\/17144530\/Webinar-LP-Banner-4.png\",\"keywords\":[\"AI Agents\",\"Database Branching\",\"Distributed SQL\",\"Manus\",\"TiDB\"],\"articleSection\":[\"Thought Leadership\"],\"inLanguage\":\"ko-KR\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.pingcap.com\/blog\/what-makes-a-database-for-ai-agents-different\/\",\"url\":\"https:\/\/thenewstack.io\/databases-for-ai-agents\/\",\"name\":\"What Makes a Database for AI Agents Different\",\"isPartOf\":{\"@id\":\"https:\/\/www.pingcap.com\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/thenewstack.io\/databases-for-ai-agents\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/thenewstack.io\/databases-for-ai-agents\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/static.pingcap.com\/files\/2026\/04\/17144530\/Webinar-LP-Banner-4.png\",\"datePublished\":\"2026-04-15T21:38:57+00:00\",\"dateModified\":\"2026-04-17T21:45:35+00:00\",\"description\":\"Agents are the new primary users. See why a database for AI agents must prioritize speed, elastic scale, and isolation over ease of use.\",\"breadcrumb\":{\"@id\":\"https:\/\/thenewstack.io\/databases-for-ai-agents\/#breadcrumb\"},\"inLanguage\":\"ko-KR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/thenewstack.io\/databases-for-ai-agents\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"ko-KR\",\"@id\":\"https:\/\/thenewstack.io\/databases-for-ai-agents\/#primaryimage\",\"url\":\"https:\/\/static.pingcap.com\/files\/2026\/04\/17144530\/Webinar-LP-Banner-4.png\",\"contentUrl\":\"https:\/\/static.pingcap.com\/files\/2026\/04\/17144530\/Webinar-LP-Banner-4.png\",\"width\":1800,\"height\":600},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/thenewstack.io\/databases-for-ai-agents\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.pingcap.com\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"What Happens to a Database When the User is an AI agent\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.pingcap.com\/#website\",\"url\":\"https:\/\/www.pingcap.com\/\",\"name\":\"TiDB\",\"description\":\"TiDB | SQL at Scale\",\"publisher\":{\"@id\":\"https:\/\/www.pingcap.com\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.pingcap.com\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"ko-KR\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/www.pingcap.com\/#organization\",\"name\":\"PingCAP\",\"url\":\"https:\/\/www.pingcap.com\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"ko-KR\",\"@id\":\"https:\/\/www.pingcap.com\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/static.pingcap.com\/files\/2021\/11\/pingcap-logo.png\",\"contentUrl\":\"https:\/\/static.pingcap.com\/files\/2021\/11\/pingcap-logo.png\",\"width\":811,\"height\":232,\"caption\":\"PingCAP\"},\"image\":{\"@id\":\"https:\/\/www.pingcap.com\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/facebook.com\/pingcap2015\",\"https:\/\/x.com\/PingCAP\",\"https:\/\/linkedin.com\/company\/pingcap\",\"https:\/\/youtube.com\/channel\/UCuq4puT32DzHKT5rU1IZpIA\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.pingcap.com\/#\/schema\/person\/7aeccb8936b7f908f923bdd0a6b44be8\",\"name\":\"Max Liu\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"ko-KR\",\"@id\":\"https:\/\/www.pingcap.com\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/static.pingcap.com\/files\/2022\/10\/17234942\/avatar.jpg\",\"contentUrl\":\"https:\/\/static.pingcap.com\/files\/2022\/10\/17234942\/avatar.jpg\",\"caption\":\"Max Liu\"},\"description\":\"Co-Founder &amp; CEO\",\"sameAs\":[\"https:\/\/www.linkedin.com\/in\/max-liu-0b2390147\/\"],\"url\":\"https:\/\/www.pingcap.com\/ko\/blog\/author\/max-liu\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"What Makes a Database for AI Agents Different","description":"Agents are the new primary users. See why a database for AI agents must prioritize speed, elastic scale, and isolation over ease of use.","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:\/\/thenewstack.io\/databases-for-ai-agents\/","og_locale":"ko_KR","og_type":"article","og_title":"What Makes a Database for AI Agents Different","og_description":"Agents are the new primary users. See why a database for AI agents must prioritize speed, elastic scale, and isolation over ease of use.","og_url":"https:\/\/thenewstack.io\/databases-for-ai-agents\/","og_site_name":"TiDB","article_publisher":"https:\/\/facebook.com\/pingcap2015","article_published_time":"2026-04-15T21:38:57+00:00","article_modified_time":"2026-04-17T21:45:35+00:00","og_image":[{"width":1200,"height":627,"url":"https:\/\/static.pingcap.com\/files\/2026\/04\/17143028\/Blog-LinkedIn-1.png","type":"image\/png"}],"author":"Max Liu","twitter_card":"summary_large_image","twitter_image":"https:\/\/static.pingcap.com\/files\/2026\/04\/17143043\/Blog-Feature-Banner-1.png","twitter_creator":"@PingCAP","twitter_site":"@PingCAP","twitter_misc":{"Written by":"Max Liu","Est. reading time":"6\ubd84"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/thenewstack.io\/databases-for-ai-agents\/#article","isPartOf":{"@id":"https:\/\/www.pingcap.com\/blog\/what-makes-a-database-for-ai-agents-different\/"},"author":{"name":"Max Liu","@id":"https:\/\/www.pingcap.com\/#\/schema\/person\/7aeccb8936b7f908f923bdd0a6b44be8"},"headline":"What Happens to a Database When the User is an AI agent","datePublished":"2026-04-15T21:38:57+00:00","dateModified":"2026-04-17T21:45:35+00:00","mainEntityOfPage":{"@id":"https:\/\/www.pingcap.com\/blog\/what-makes-a-database-for-ai-agents-different\/"},"wordCount":1118,"publisher":{"@id":"https:\/\/www.pingcap.com\/#organization"},"image":{"@id":"https:\/\/thenewstack.io\/databases-for-ai-agents\/#primaryimage"},"thumbnailUrl":"https:\/\/static.pingcap.com\/files\/2026\/04\/17144530\/Webinar-LP-Banner-4.png","keywords":["AI Agents","Database Branching","Distributed SQL","Manus","TiDB"],"articleSection":["Thought Leadership"],"inLanguage":"ko-KR"},{"@type":"WebPage","@id":"https:\/\/www.pingcap.com\/blog\/what-makes-a-database-for-ai-agents-different\/","url":"https:\/\/thenewstack.io\/databases-for-ai-agents\/","name":"What Makes a Database for AI Agents Different","isPartOf":{"@id":"https:\/\/www.pingcap.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/thenewstack.io\/databases-for-ai-agents\/#primaryimage"},"image":{"@id":"https:\/\/thenewstack.io\/databases-for-ai-agents\/#primaryimage"},"thumbnailUrl":"https:\/\/static.pingcap.com\/files\/2026\/04\/17144530\/Webinar-LP-Banner-4.png","datePublished":"2026-04-15T21:38:57+00:00","dateModified":"2026-04-17T21:45:35+00:00","description":"Agents are the new primary users. See why a database for AI agents must prioritize speed, elastic scale, and isolation over ease of use.","breadcrumb":{"@id":"https:\/\/thenewstack.io\/databases-for-ai-agents\/#breadcrumb"},"inLanguage":"ko-KR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/thenewstack.io\/databases-for-ai-agents\/"]}]},{"@type":"ImageObject","inLanguage":"ko-KR","@id":"https:\/\/thenewstack.io\/databases-for-ai-agents\/#primaryimage","url":"https:\/\/static.pingcap.com\/files\/2026\/04\/17144530\/Webinar-LP-Banner-4.png","contentUrl":"https:\/\/static.pingcap.com\/files\/2026\/04\/17144530\/Webinar-LP-Banner-4.png","width":1800,"height":600},{"@type":"BreadcrumbList","@id":"https:\/\/thenewstack.io\/databases-for-ai-agents\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.pingcap.com\/"},{"@type":"ListItem","position":2,"name":"What Happens to a Database When the User is an AI agent"}]},{"@type":"WebSite","@id":"https:\/\/www.pingcap.com\/#website","url":"https:\/\/www.pingcap.com\/","name":"\ud2f0DB","description":"TiDB | SQL at Scale","publisher":{"@id":"https:\/\/www.pingcap.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.pingcap.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"ko-KR"},{"@type":"Organization","@id":"https:\/\/www.pingcap.com\/#organization","name":"PingCAP","url":"https:\/\/www.pingcap.com\/","logo":{"@type":"ImageObject","inLanguage":"ko-KR","@id":"https:\/\/www.pingcap.com\/#\/schema\/logo\/image\/","url":"https:\/\/static.pingcap.com\/files\/2021\/11\/pingcap-logo.png","contentUrl":"https:\/\/static.pingcap.com\/files\/2021\/11\/pingcap-logo.png","width":811,"height":232,"caption":"PingCAP"},"image":{"@id":"https:\/\/www.pingcap.com\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/facebook.com\/pingcap2015","https:\/\/x.com\/PingCAP","https:\/\/linkedin.com\/company\/pingcap","https:\/\/youtube.com\/channel\/UCuq4puT32DzHKT5rU1IZpIA"]},{"@type":"Person","@id":"https:\/\/www.pingcap.com\/#\/schema\/person\/7aeccb8936b7f908f923bdd0a6b44be8","name":"Max Liu","image":{"@type":"ImageObject","inLanguage":"ko-KR","@id":"https:\/\/www.pingcap.com\/#\/schema\/person\/image\/","url":"https:\/\/static.pingcap.com\/files\/2022\/10\/17234942\/avatar.jpg","contentUrl":"https:\/\/static.pingcap.com\/files\/2022\/10\/17234942\/avatar.jpg","caption":"Max Liu"},"description":"Co-Founder &amp; CEO","sameAs":["https:\/\/www.linkedin.com\/in\/max-liu-0b2390147\/"],"url":"https:\/\/www.pingcap.com\/ko\/blog\/author\/max-liu\/"}]}},"grav_blocks":false,"card_markup":"<a class=\"card-resource bg-white\" href=\"https:\/\/www.pingcap.com\/ko\/blog\/what-makes-a-database-for-ai-agents-different\/\"><div class=\"card-resource__image-container\"><img class=\"card-resource__image\" alt=\"Webinar - LP Banner\" src=\"https:\/\/static.pingcap.com\/files\/2026\/04\/17144530\/Webinar-LP-Banner-4.png\" loading=\"lazy\" width=1800 height=600 \/><\/div><div class=\"card-resource__content-container\"><div class=\"card-resource__content-head\"><div class=\"card-resource__category\">Thought Leadership<\/div><\/div><h5 class=\"card-resource__title\">What Happens to a Database When the User is an AI agent<\/h5><\/div><\/a>","_links":{"self":[{"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/posts\/33120","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/users\/50"}],"replies":[{"embeddable":true,"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/comments?post=33120"}],"version-history":[{"count":20,"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/posts\/33120\/revisions"}],"predecessor-version":[{"id":33147,"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/posts\/33120\/revisions\/33147"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/media\/33151"}],"wp:attachment":[{"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/media?parent=33120"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/categories?post=33120"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/tags?post=33120"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}