{"id":30735,"date":"2025-11-27T04:12:45","date_gmt":"2025-11-27T12:12:45","guid":{"rendered":"https:\/\/www.pingcap.com\/?post_type=case-study&#038;p=30735"},"modified":"2025-12-01T10:59:05","modified_gmt":"2025-12-01T18:59:05","slug":"manus-agentic-ai-database-tidb","status":"publish","type":"case-study","link":"https:\/\/www.pingcap.com\/ko\/case-study\/manus-agentic-ai-database-tidb\/","title":{"rendered":"How Manus Scaled Its Data Foundation for Viral Growth with TiDB"},"content":{"rendered":"<p><em>Manus, a general purpose agentic AI platform, launched in March 2025 and went viral, amassing a two-million-plus waitlist within weeks. Its \u201cContext Engineering\u201d model\u2014persisting thousands of stateful iterations per task\u2014demanded extreme write throughput and low-latency state reconstruction that a monolithic database couldn\u2019t sustain. The team migrated to TiDB Cloud in two weeks, leveraging <a href=\"https:\/\/docs.pingcap.com\/tidb\/stable\/tidb-architecture\" target=\"_blank\" rel=\"noreferrer noopener\">distributed SQL<\/a>, online change, and <a href=\"https:\/\/docs.pingcap.com\/tidbcloud\/scalability-concepts\/#scalability\" target=\"_blank\" rel=\"noreferrer noopener\">horizontal scale<\/a>. The result: a successful public launch and a resilient data layer that now powers Manus\u2019s \u201cWide Research\u201d agent swarms and the features introduced in <a href=\"https:\/\/manus.so\/post\/manus-1.5-introduction\">Manus 1.5<\/a>.<\/em><\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Explosive_Growth_and_Strategic_Infrastructure_Evolution\"><\/span>Explosive Growth and Strategic Infrastructure Evolution<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>Following its March 2025 launch, Manus&#8217;s viral adoption\u2014even under an invite-only model\u2014demonstrated the massive market demand for general-purpose agentic AI.<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>The Opportunity<\/strong>: Within weeks of launch, over two million users had joined the waitlist. Even the controlled beta rollout was generating database workloads that demonstrated the need for a more elastic architecture.<\/li>\n\n\n\n<li><strong>The Strategic Decision<\/strong>: By mid-April, the team recognized that their existing single-instance database, while excellent for traditional workloads, was architected for different patterns than what Manus&#8217;s agentic workloads required. To enable their planned public launch, they needed a database that could scale seamlessly in both compute and storage without major application re-architecture.<\/li>\n\n\n\n<li><strong>The Timeline<\/strong>: As stated by Ziming Miao, Engineering VP of Manus, the goal was clear: &#8220;to find the database system that could scale seamlessly in both compute and storage without major system re-designs, to survive the present and finally unlock their full public launch.&#8221; With MySQL compatibility as a non-negotiable requirement, the team compressed what would typically be a multi-month migration into an aggressive two-week sprint.<\/li>\n<\/ul>\n\n\n\n<p>This is a strategic inflection point. Manus had built something the market wanted at unprecedented scale, and now they needed infrastructure that could match their ambition. But to understand why they needed a fundamentally different database architecture, we must first examine what makes agentic AI workloads unique<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Why_Agentic_AI_Demands_a_Different_Database_Architecture\"><\/span>Why Agentic AI Demands a Different Database Architecture<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>To understand why Manus required a different database architecture, we must examine what makes agentic AI fundamentally different from traditional applications. The answer lies in &#8220;Context Engineering&#8221;, an industry pattern where the database becomes the agent&#8217;s cognitive foundation, not just a data store. Manus&#8217;s scale amplifies this challenge: with tasks requiring up to 15,000 iterations, their implementation pushes this pattern to its limits.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">The Plan-Execute-Verify Loop and Exponential Context Generation<\/h3>\n\n\n\n<p>Manus&#8217;s intelligence is derived from a sophisticated &#8220;Context Engineering&#8221; framework built on top of frontier LLMs. The Manus Action Engine operates on a continuous loop of Planning, Execution, and Verification. This core cognitive process initiates a sequence of steps where each action and its resulting observation are appended to the agent&#8217;s context. This context is then persisted and used as input for the next iteration.<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"960\" height=\"540\" src=\"https:\/\/static.pingcap.com\/files\/2025\/11\/27032349\/Manus-on-TiDB-SCaiLE-2025.png\" alt=\"\" class=\"wp-image-30734\" srcset=\"https:\/\/static.pingcap.com\/files\/2025\/11\/27032349\/Manus-on-TiDB-SCaiLE-2025.png 960w, https:\/\/static.pingcap.com\/files\/2025\/11\/27032349\/Manus-on-TiDB-SCaiLE-2025-300x169.png 300w, https:\/\/static.pingcap.com\/files\/2025\/11\/27032349\/Manus-on-TiDB-SCaiLE-2025-768x432.png 768w\" sizes=\"auto, (max-width: 960px) 100vw, 960px\" \/><\/figure>\n\n\n\n<p class=\"has-text-align-center\"><em>The Manus Action Engine&#8217;s core cognitive loop. Each observation is persisted to the database (acting as Long-Term Memory), forming an ever-growing context that feeds back into the next decision cycle.<\/em><\/p>\n\n\n\n<p>A single user task can generate thousands of these iterations. As stated in <a href=\"https:\/\/www.youtube.com\/watch?v=PP4Ht_JWA7k\">Ziming Miao&#8217;s keynote at TiDB SCaiLE 2025<\/a>, some complex tasks take up to &#8220;thousands of iterations to finish,&#8221; and &#8220;all this context has to go to the persistence in the data infrastructure.&#8221; This creates a massive, append-only, stateful workload where the integrity and low-latency retrievability of the entire context chain are critical for task success.<\/p>\n\n\n\n<p>This is where traditional monolithic database architectures reach their limits. Single-instance databases are optimized for transactional workloads with predictable access patterns\u2014not for the relentless, high-velocity context appends that each Manus agent generates, combined with the need for instant retrieval of complete context chains.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">The Database as the Agent&#8217;s Long-Term Memory: A Paradigm Shift<\/h3>\n\n\n\n<p>The Manus engineering team&#8217;s technical <a href=\"https:\/\/manus.im\/blog\/Context-Engineering-for-AI-Agents-Lessons-from-Building-Manus\">blog<\/a> on &#8220;Context Engineering for AI Agents&#8221; reflects a core principle: &#8220;Use the File System as Context.&#8221; This architectural decision directly translates the challenge of long-term memory to the database. This philosophy, and the strategic choice to build on a scalable database like TiDB Cloud, is what later enabled the &#8220;Unlimited Context&#8221; feature announced in Manus 1.5. When the announcement claims users can &#8220;load huge project details without losing track of earlier data,&#8221; it is the scalability and persistence of the underlying TiDB X database\u2014chosen months prior with foresight\u2014that makes this possible.<\/p>\n\n\n\n<p>Here, the role of the database undergoes a paradigm shift\u2014from a simple system of record to the agent&#8217;s Long-Term Memory (LTM). An agent&#8217;s LTM has three fundamental requirements that demand a different architectural approach:<\/p>\n\n\n\n<figure class=\"wp-block-table\"><table class=\"has-fixed-layout\"><tbody><tr><td><strong>LTM Requirement<\/strong><\/td><td><strong>Traditional Database Constraints<\/strong><\/td><td><strong>\ud2f0DB<\/strong><strong> X Architectural Advantage<\/strong><\/td><\/tr><tr><td>Vast, Scalable Capacity<\/td><td>Single-instance architectures have storage ceilings that require manual intervention to expand.<\/td><td><strong>Decoupled computer-storage (TiDB\/TiKV)<\/strong> <a href=\"https:\/\/docs.pingcap.com\/tidb\/stable\/tidb-storage\/\" target=\"_blank\" rel=\"noreferrer noopener\">allows storage to scale horizontally<\/a> and near-infinitely, providing a limitless memory canvas.<\/td><\/tr><tr><td>High-Throughput, Low-Latency Access<\/td><td>Balancing thousands of writes per second with simultaneous reads for context reconstruction requires careful tuning.<\/td><td><strong>Distributed Query Processing and Raft Consensus<\/strong> handle massive concurrent I\/O, ensuring the LTM is not a bottleneck to the agent&#8217;s &#8220;thinking&#8221; speed.<\/td><\/tr><tr><td>Strong Consistency<\/td><td>An agent cannot function with corrupt or inconsistent memory\u2014every context retrieval must be accurate.<\/td><td><strong>Strong Consistency<\/strong> guarantees that once memory is written, it is immediately and correctly retrievable by any part of the agent swarm, ensuring coherent behavior.<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n<p>Recognizing these requirements, Manus made the strategic decision to partner with TiDB. But first, they had to execute a high-stakes database migration in just two weeks (while their waitlist continued to grow).<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"The_High-Stakes_Migration_Partnership_Under_Pressure\"><\/span>The High-Stakes Migration: Partnership Under Pressure<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>With their public launch scheduled and demand building, the Manus and TiDB teams collaborated on-site to execute the rapid migration. The success of this ambitious operation hinged on a combination of product features and deep partnership:<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"960\" height=\"540\" src=\"https:\/\/static.pingcap.com\/files\/2025\/11\/27035704\/Manus-on-TiDB-SCaiLE-2025-1.png\" alt=\"\" class=\"wp-image-30736\" srcset=\"https:\/\/static.pingcap.com\/files\/2025\/11\/27035704\/Manus-on-TiDB-SCaiLE-2025-1.png 960w, https:\/\/static.pingcap.com\/files\/2025\/11\/27035704\/Manus-on-TiDB-SCaiLE-2025-1-300x169.png 300w, https:\/\/static.pingcap.com\/files\/2025\/11\/27035704\/Manus-on-TiDB-SCaiLE-2025-1-768x432.png 768w\" sizes=\"auto, (max-width: 960px) 100vw, 960px\" \/><\/figure>\n\n\n\n<p class=\"has-text-align-center\"><em>Manus shared their growth story at TiDB SCaiLE Summit 2025<\/em><\/p>\n\n\n\n<h3 class=\"wp-block-heading\">MySQL Compatibility as the Enabler<\/h3>\n\n\n\n<p>The entire two-week timeline was only possible because TiDB Cloud is <a href=\"https:\/\/docs.pingcap.com\/tidb\/stable\/mysql-compatibility\/\" target=\"_blank\" rel=\"noreferrer noopener\">highly compatible with the MySQL protocol.<\/a> As Ziming Miao noted in his keynote, this allowed Manus to migrate &#8220;with almost no structure changes to our code.&#8221; The team could lift-and-shift their existing schema and application logic without a costly rewrite, critical when speed was essential.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">Solving the &#8220;Real Workload&#8221; Challenge<\/h3>\n\n\n\n<p>Despite careful planning, the cutover required three hours of optimization due to query plans that needed tuning for Manus&#8217;s unique state-reconstruction workload. This validated their key lesson learned: &#8220;Test your real workload, not benchmarks.&#8221; Standard TPCC benchmarks didn&#8217;t reflect the production queries that Manus agents actually generated: complex context reconstructions that required different index strategies than traditional transactional patterns.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">The Power of Partnership<\/h3>\n\n\n\n<p>The challenge was solved because on-site TiDB engineers were able to diagnose the issue in real-time and apply <a href=\"https:\/\/docs.pingcap.com\/tidb\/stable\/sql-plan-management\/#sql-binding\" target=\"_blank\" rel=\"noreferrer noopener\">SQL bindings<\/a> directly to force optimal query plans, restoring performance within minutes. As Ziming mentioned during his keynote: &#8220;We chose the hardcore approach, but it can work only if your partners can handle it. Thanks to TiDB, the team debugged with us through the night, fixing issues in minutes. That is the difference between disaster and success.&#8221;<\/p>\n\n\n\n<p>By early May 2025, the migration was complete. Manus successfully launched to the public on May 12, 2025, and the exponential data growth that followed was absorbed seamlessly by TiDB X&#8217;s elastic architecture.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"From_Scale_to_Intelligence_The_Manus_15_Architectural_Breakthrough\"><\/span>From Scale to Intelligence: The Manus 1.5 Architectural Breakthrough<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>But migration solved the immediate scaling challenge. The next frontier was architectural: how could Manus enable agents to explore thousands of solution paths simultaneously without creating chaos in their shared memory?<\/p>\n\n\n\n<p>With their infrastructure now stable and scalable on TiDB, the Manus team turned their attention to their most ambitious vision yet: agent swarms that could tackle complex problems by exploring thousands of solution paths in parallel.<\/p>\n\n\n\n<p>Consider a real use case: a user asks an agent to &#8220;build a modern e-commerce website.&#8221; A truly intelligent agent shouldn&#8217;t just pick one approach and hope it works. Instead, it should explore multiple architectural paths simultaneously (React + Node.js, Next.js + Serverless, Vue + Python). Each exploration needs its own database tables, schemas, and test data.<\/p>\n\n\n\n<p><strong>Here&#8217;s the problem<\/strong>: If all paths write to the same database, they create chaos\u2014conflicting schemas, corrupted test data, overwritten results. Traditional solutions like &#8220;create separate databases&#8221; don&#8217;t scale when you have thousands of agents, each exploring 5-10 paths simultaneously.<\/p>\n\n\n\n<p>As the Manus team began prototyping agent swarms for Manus 1.5, they identified a critical infrastructure gap: traditional databases couldn&#8217;t handle the &#8220;X\u00d7Y\u00d7Z Problem&#8221;\u2014a multiplicative scaling challenge where X tenants run Y agents, each exploring Z parallel branches.<\/p>\n\n\n\n<p>In a traditional setup, creating isolated environments for thousands of concurrent experiments is slow and cost-prohibitive. Manus needed a database that could operate like a code repository\u2014instantly branching state, isolating schema changes, and merging results without affecting the main production line.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">The Solution: Serverless Branching<\/h3>\n\n\n\n<p>Manus solved this by leveraging TiDB Cloud\u2019s serverless architecture and <a href=\"https:\/\/docs.pingcap.com\/tidbcloud\/branch-overview\/?plan=starter\">Database Branching<\/a>. This allows the platform to treat the database like code:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Safety in Scale:<\/strong> Agents can now &#8220;fork&#8221; the database instantly to test risky hypotheses. This enables massive parallel execution (swarms) where thousands of agents work simultaneously without data corruption.<\/li>\n\n\n\n<li><strong>Agent-Autonomy<\/strong>: Agents are granted the freedom to evolve their own schemas on the fly, adapting to new tasks without waiting for human intervention.<\/li>\n\n\n\n<li><strong>Economic Viability<\/strong>: With TiDB&#8217;s serverless model, Manus only pays for active processing, making it financially feasible to spin up 10,000 ephemeral branches for rapid experimentation.<\/li>\n<\/ul>\n\n\n\n<p><em><strong>Technical Deep Dive<\/strong><\/em>\uff1a<em>How does TiDB X technically achieve sub-second branching for thousands of agents?<\/em> <em>Read the full Engineering Story -&gt; <\/em><strong><em><a href=\"https:\/\/www.pingcap.com\/ko\/blog\/how-manus-1-5-uses-tidb-x-to-let-agents-ship-full-stack-apps-at-scale\/\">How Manus 1.5 Uses TiDB X to Let Agents Ship Full-Stack Apps at Scale<\/a><\/em> <\/strong><\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Impact_From_Viral_Scale_to_Future_Innovation\"><\/span>Impact: From Viral Scale to Future Innovation<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>Since the public launch, Manus has successfully supported its viral growth while transforming its data layer from a scaling constraint into a driver of product innovation. By adopting a serverless, branching-capable architecture, the database has evolved from a passive store to an active participant in the agent&#8217;s cognitive loop\u2014empowering swarms to iterate and evolve schemas autonomously. This operational agility allowed the engineering team to focus on their core AI models rather than database management, securing the foundation needed to define the next generation of software development.<\/p>\n\n\n\n<p><em>Ready to Build the Next Wave of AI?<\/em> <em>Scaling agentic workloads are the defining challenges of modern AI development. Find out how leaders like Manus are solving them in our\u00a0<strong><a href=\"https:\/\/www.pingcap.com\/ko\/ai\/use-case\/\"><\/a><em><strong><a href=\"https:\/\/www.pingcap.com\/ko\/ai\/use-case\/\">AI Use Case Gallery<\/a><\/strong><\/em><\/strong>.<\/em><\/p>","protected":false},"excerpt":{"rendered":"<p>Manus, a general purpose agentic AI platform, launched in March 2025 and went viral, amassing a two-million-plus waitlist within weeks. Its \u201cContext Engineering\u201d model\u2014persisting thousands of stateful iterations per task\u2014demanded extreme write throughput and low-latency state reconstruction that a monolithic database couldn\u2019t sustain. The team migrated to TiDB Cloud in two weeks, leveraging distributed SQL, [&hellip;]<\/p>\n","protected":false},"author":264,"featured_media":30732,"template":"","tags":[138,9,31],"customer":[438],"industry":[183],"class_list":["post-30735","case-study","type-case-study","status-publish","has-post-thumbnail","hentry","tag-ai","tag-scalability","tag-tidb-cloud","customer-manus","industry-saas"],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v26.9 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>How Manus Scaled Its Agentic AI Database for Viral Growth | TiDB<\/title>\n<meta name=\"description\" content=\"How did Manus scale virally? Find out how TiDB solved their unique agentic AI database challenges for a resilient backend.\" \/>\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.pingcap.com\/ko\/case-study\/manus-agentic-ai-database-tidb\/\" \/>\n<meta property=\"og:locale\" content=\"ko_KR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"How Manus Scaled Its Agentic AI Database for Viral Growth | TiDB\" \/>\n<meta property=\"og:description\" content=\"How did Manus scale virally? Find out how TiDB solved their unique agentic AI database challenges for a resilient backend.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.pingcap.com\/ko\/case-study\/manus-agentic-ai-database-tidb\/\" \/>\n<meta property=\"og:site_name\" content=\"TiDB\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/facebook.com\/pingcap2015\" \/>\n<meta property=\"article:modified_time\" content=\"2025-12-01T18:59:05+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/static.pingcap.com\/files\/2025\/11\/27032346\/Manus-Banner-1.png\" \/>\n\t<meta property=\"og:image:width\" content=\"1801\" \/>\n\t<meta property=\"og:image:height\" content=\"901\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:site\" content=\"@PingCAP\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"8\ubd84\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.pingcap.com\/case-study\/manus-agentic-ai-database-tidb\/\",\"url\":\"https:\/\/www.pingcap.com\/case-study\/manus-agentic-ai-database-tidb\/\",\"name\":\"How Manus Scaled Its Agentic AI Database for Viral Growth | TiDB\",\"isPartOf\":{\"@id\":\"https:\/\/www.pingcap.com\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.pingcap.com\/case-study\/manus-agentic-ai-database-tidb\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.pingcap.com\/case-study\/manus-agentic-ai-database-tidb\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/static.pingcap.com\/files\/2025\/11\/27032340\/Manus-Banner-2.png\",\"datePublished\":\"2025-11-27T12:12:45+00:00\",\"dateModified\":\"2025-12-01T18:59:05+00:00\",\"description\":\"How did Manus scale virally? Find out how TiDB solved their unique agentic AI database challenges for a resilient backend.\",\"breadcrumb\":{\"@id\":\"https:\/\/www.pingcap.com\/case-study\/manus-agentic-ai-database-tidb\/#breadcrumb\"},\"inLanguage\":\"ko-KR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.pingcap.com\/case-study\/manus-agentic-ai-database-tidb\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"ko-KR\",\"@id\":\"https:\/\/www.pingcap.com\/case-study\/manus-agentic-ai-database-tidb\/#primaryimage\",\"url\":\"https:\/\/static.pingcap.com\/files\/2025\/11\/27032340\/Manus-Banner-2.png\",\"contentUrl\":\"https:\/\/static.pingcap.com\/files\/2025\/11\/27032340\/Manus-Banner-2.png\",\"width\":1801,\"height\":601},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.pingcap.com\/case-study\/manus-agentic-ai-database-tidb\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.pingcap.com\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Case Studies\",\"item\":\"https:\/\/www.pingcap.com\/customers\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"How Manus Scaled Its Data Foundation for Viral Growth with TiDB\"}]},{\"@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\"]}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"How Manus Scaled Its Agentic AI Database for Viral Growth | TiDB","description":"How did Manus scale virally? Find out how TiDB solved their unique agentic AI database challenges for a resilient backend.","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.pingcap.com\/ko\/case-study\/manus-agentic-ai-database-tidb\/","og_locale":"ko_KR","og_type":"article","og_title":"How Manus Scaled Its Agentic AI Database for Viral Growth | TiDB","og_description":"How did Manus scale virally? Find out how TiDB solved their unique agentic AI database challenges for a resilient backend.","og_url":"https:\/\/www.pingcap.com\/ko\/case-study\/manus-agentic-ai-database-tidb\/","og_site_name":"TiDB","article_publisher":"https:\/\/facebook.com\/pingcap2015","article_modified_time":"2025-12-01T18:59:05+00:00","og_image":[{"width":1801,"height":901,"url":"https:\/\/static.pingcap.com\/files\/2025\/11\/27032346\/Manus-Banner-1.png","type":"image\/png"}],"twitter_card":"summary_large_image","twitter_site":"@PingCAP","twitter_misc":{"Est. reading time":"8\ubd84"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.pingcap.com\/case-study\/manus-agentic-ai-database-tidb\/","url":"https:\/\/www.pingcap.com\/case-study\/manus-agentic-ai-database-tidb\/","name":"How Manus Scaled Its Agentic AI Database for Viral Growth | TiDB","isPartOf":{"@id":"https:\/\/www.pingcap.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.pingcap.com\/case-study\/manus-agentic-ai-database-tidb\/#primaryimage"},"image":{"@id":"https:\/\/www.pingcap.com\/case-study\/manus-agentic-ai-database-tidb\/#primaryimage"},"thumbnailUrl":"https:\/\/static.pingcap.com\/files\/2025\/11\/27032340\/Manus-Banner-2.png","datePublished":"2025-11-27T12:12:45+00:00","dateModified":"2025-12-01T18:59:05+00:00","description":"How did Manus scale virally? Find out how TiDB solved their unique agentic AI database challenges for a resilient backend.","breadcrumb":{"@id":"https:\/\/www.pingcap.com\/case-study\/manus-agentic-ai-database-tidb\/#breadcrumb"},"inLanguage":"ko-KR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.pingcap.com\/case-study\/manus-agentic-ai-database-tidb\/"]}]},{"@type":"ImageObject","inLanguage":"ko-KR","@id":"https:\/\/www.pingcap.com\/case-study\/manus-agentic-ai-database-tidb\/#primaryimage","url":"https:\/\/static.pingcap.com\/files\/2025\/11\/27032340\/Manus-Banner-2.png","contentUrl":"https:\/\/static.pingcap.com\/files\/2025\/11\/27032340\/Manus-Banner-2.png","width":1801,"height":601},{"@type":"BreadcrumbList","@id":"https:\/\/www.pingcap.com\/case-study\/manus-agentic-ai-database-tidb\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.pingcap.com\/"},{"@type":"ListItem","position":2,"name":"Case Studies","item":"https:\/\/www.pingcap.com\/customers\/"},{"@type":"ListItem","position":3,"name":"How Manus Scaled Its Data Foundation for Viral Growth with TiDB"}]},{"@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"]}]}},"card_markup":"<div class=\"card-case-study\"><div class=\"card-case-study__image-container\"><img class=\"card-case-study__image\" alt=\"Manus-Logo-White\" src=\"https:\/\/static.pingcap.com\/files\/2025\/11\/27030923\/Manus-Logo-White-1.svg\" loading=\"lazy\" \/><\/div><span class=\"card-case-study__title\">How Manus Scaled Its Data Foundation for Viral Growth with TiDB<\/span><div class=\"card-case-study__button\"><a class=\"video js--trigger-video-modal\" href=\"https:\/\/www.youtube.com\/watch?v=PP4Ht_JWA7k\">Tech Talk<i><\/i><\/a><a class=\"button--secondary\" href=\"https:\/\/www.pingcap.com\/ko\/case-study\/manus-agentic-ai-database-tidb\/\" target=\"_blank\">View Case Study<\/a><\/div><\/div>","_links":{"self":[{"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/case-study\/30735","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/case-study"}],"about":[{"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/types\/case-study"}],"author":[{"embeddable":true,"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/users\/264"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/media\/30732"}],"wp:attachment":[{"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/media?parent=30735"}],"wp:term":[{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/tags?post=30735"},{"taxonomy":"customer","embeddable":true,"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/customer?post=30735"},{"taxonomy":"industry","embeddable":true,"href":"https:\/\/www.pingcap.com\/ko\/wp-json\/wp\/v2\/industry?post=30735"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}