Artificial Intelligence
Building AI-powered Apps with MongoDB
The Future of AI Software Development is Agentic
September 17, 2025
Artificial Intelligence
Simplify AI-Driven Data Connectivity With MongoDB and MCP Toolbox
The wave of generative AI applications is revolutionizing how businesses interact with and derive value from their data. Organizations need solutions that simplify these interactions and ensure compatibility with an expanding ecosystem of databases. Enter MCP Toolbox for Databases , an open-source Model Context Protocol (MCP) server that enables seamless integration between gen AI agents and enterprise data sources using a standardized protocol pioneered by Anthropic. With the built-in capability to query multiple data sources simultaneously and unify results, MCP Toolbox eliminates fragmented integration challenges, empowering businesses to unlock the full potential of their data. With MongoDB Atlas now joining the ecosystem of databases supported by MCP Toolbox, enterprises using MongoDB’s industry-leading cloud-native database platform can benefit from streamlined connections to their gen AI systems. As businesses adopt gen AI to unlock insights and automate workflows, the choice of database is critical to meeting demands for dynamic data structures, scalability, and high-performance applications. MongoDB Atlas, with its fully managed, document-oriented NoSQL design and capabilities for flexible schema modeling, is the ultimate companion to MCP Toolbox for applications requiring unstructured or semistructured data connectivity. This blog post explores how MongoDB Atlas integrates into MCP Toolbox, its advantages for developers, and the key use cases for enabling AI-driven data solutions in enterprise environments. Figure 1. MongoDB as a source for MCP Toolbox for Databases. How it works The integration of MongoDB Atlas with MCP Toolbox enables users to perform Create, Read, Update, Delete (CRUD) operations on MongoDB data sources using the standardized MCP. Beyond fundamental data management tasks, this integration also unlocks capabilities from MongoDB’s aggregation framework , enabling users to seamlessly execute complex data transformations, computations, and analyses. This empowers businesses to not only access and modify their data but also uncover valuable insights by harnessing MongoDB’s powerful query functionality within workflows driven by MCP Toolbox. By combining the scalability and flexibility of MongoDB Atlas with MCP Toolbox’s ability to query across multiple data sources, organizations can develop advanced AI-driven applications, enhance operational efficiency, and uncover deeper analytical opportunities. The use of MongoDB as both a source and a sink within MCP Toolbox is simple and highly versatile, thanks to the flexibility of the configuration file. To configure MongoDB as a data source, you can define it under the sources section, specifying parameters such as its kind ("mongodb") and the connection’s Uniform Resource Identifier (URI) to establish access to your MongoDB instance. sources: my-mongodb: kind: mongodb uri: "mongodb+srv://username:password@host.mongodb.net" In the tools section, various operations—such as retrieving, updating, inserting, or deleting data—can be defined by linking the appropriate source, specifying the target database and dataset, and configuring parameters such as filters, projections, sorting, or payload structures. Additionally, databases can act as sinks for storing data by enabling operations to write new records or modify existing ones, making them ideal for workflows where applications or systems need to interact dynamically with persistent storage. The toolsets section facilitates grouping related tools, making it easy to load and manage specific sets of operations based on different use cases or requirements. Whether used for reading or writing data, the integration of databases via MCP Toolbox provides a streamlined and consistent approach to managing and interacting with diverse data sources. Below is an example of running "find query" on MongoDB Atlas using the MCP Toolbox. tools: get_user_profile: kind: mongodb-find-one source: my-mongo-source description: Retrieves a user's profile by their email address. database: user_data collection: profiles filterPayload: | { "email": {{json .email}} } filterParams: - name: email type: string description: The email address of the user to find. projectPayload: | { "password_hash": 0, "login_history": 0 } Getting started The integration of MongoDB Atlas and MCP Toolbox for Databases marks a significant step forward in simplifying database interactions for enterprises embracing gen AI. By enabling seamless connectivity, advanced data operations, and cross-source queries, this collaboration empowers businesses to build AI-driven applications that maximize the value of their data while enhancing efficiency and scalability. Get started today through Google Cloud Marketplace . Set up MCP Toolbox for Databases locally. Set up MongoDB Atlas source connector . And then set up MongoDB Atlas tools .
Supercharge Self-Managed Apps With Search and Vector Search Capabilities
MongoDB is excited to announce the public preview of search and vector search capabilities for use with MongoDB Community Edition and MongoDB Enterprise Server. These new capabilities empower developers to prototype, iterate, and build sophisticated, AI-powered applications directly in self-managed environments with robust search functionality. Versatility is one of the reasons why developers love MongoDB. MongoDB can run anywhere. 1 This includes local setups where many developers kickstart their MongoDB journey, to the largest enterprise data centers when it is time to scale, and MongoDB’s fully managed cloud service, MongoDB Atlas . Regardless of where development takes place, MongoDB effortlessly integrates with any developer's workflow. MongoDB Community Edition is the free, source-available version of MongoDB that millions of developers use to learn, test, and grow their skills. MongoDB Enterprise Server is the commercial version of MongoDB’s core database. It offers additional enterprise-grade features for companies that prefer to self-manage their deployments on-premises or in public, private, or hybrid cloud environments. With native search and vector search capabilities now available for use with Community Edition and Enterprise Server, MongoDB aims to deliver a simpler and consistent experience for building great applications wherever they are deployed. What is search and vector search? Similar to the offerings in MongoDB Atlas, MongoDB Community Edition and MongoDB Enterprise Server now support two distinct yet complementary search capabilities: Full-text search is an embedded capability that delivers a seamless, scalable experience for building relevance-based app features. Vector search enables developers to build intelligent applications powered by semantic search and generative AI using native, full-featured vector database capabilities. There are no functional limitations on the core search aggregation stages in this public preview. Therefore, $search , $searchMeta , and $vectorSearch are all supported with functional parity to what is available in Atlas, excluding features in a preview state. For more information, check out the search and vector search documentation pages. Solving developer challenges with integrated search Historically, integrating advanced search features into self-managed applications often required bolting on external search engines or vector databases to MongoDB. This approach created friction at every stage for developers and organizations, leading to: Architectural complexity: Managing and synchronizing data across multiple, disparate systems added layers of complexity, demanded additional skills, and complicated development workflows. Operational overhead: Handling separate provisioning, security, upgrades, and monitoring for each system placed a heavy load on DevOps teams. Decreased developer productivity: Developers are forced to learn and use different query APIs and languages for both the database and the search engine. This resulted in frequent context switching, steeper learning curves, and slower release cycles. Consistency challenges: Aligning the primary database with separate search or vector indexes risked producing out-of-sync results. Despite promotions of transactional guarantees and data consistency, these indexes were only eventually consistent. This led to incomplete results in rapidly changing environments. With search and vector search now integrated into MongoDB Community Edition and MongoDB Enterprise Server, these trade–offs disappear. Developers can now create powerful search capabilities using MongoDB's familiar query framework, removing the synchronization burden and the need to manage multiple single-purpose systems. This release simplifies data architecture, reduces operational overhead, and accelerates application development. With these capabilities, developers can harness sophisticated out-of-the-box capabilities to build a variety of powerful applications. Potential use cases include: table, th, td { border: 1px solid black; border-collapse: collapse; } th, td { padding: 5px; } Use Case Description Keyword/Full-text search Autocomplete and fuzzy search Create real-time suggestions and correct spelling errors as users type, improving the search experience Search faceting Apply quick filtering options in applications like e-commerce, so users can narrow down search results based on categories, price ranges, and more Internal search tools Build search tools for internal use or for applications with sensitive data that require on-premises deployment Vector search AI-powered semantic search Implement semantic search and recommendation systems to provide more relevant results than traditional keyword matching Retrieval-augmented generation (RAG) Use search to retrieve factual data from a knowledge base to bring accurate, context-aware data into large language model (LLM) applications AI agents Create agents that utilize tools to collect context, communicate with external systems, and execute actions Hybrid search Hybrid search Combine keyword and vector search techniques Data processing Text analysis Perform text analysis directly in the MongoDB database MongoDB offers native integrations with frameworks such as LangChain , LangGraph , and LlamaIndex . This streamlines workflows, accelerates development, and embeds RAG or agentic features directly into applications. To learn more about other AI frameworks supported by MongoDB, check out this documentation . MongoDB’s partners and champions are already experiencing the benefits from utilizing search and vector search across a wider range of environments: “We’re thrilled that MongoDB search and vector search are now accessible in the already popular MongoDB Community Edition. Now our customers can leverage MongoDB and LangChain in either deployment mode and in their preferred environment to build cutting-edge LLM applications.”—Harrison Chase, CEO, LangChain. “MongoDB has helped Clarifresh build awesome software, and I’ve always been impressed with its rock-solid foundations. With search and vector search capabilities now available in MongoDB Community Edition, we gain the confidence of accessible source code, the flexibility to deploy anywhere, and the promise of community-driven extensibility. It’s an exciting milestone that reaffirms MongoDB’s commitment to developers.”—Luke Thompson, MongoDB Champion, Clarifresh. “We’re excited about the next interaction of search experiences in MongoDB Community Edition. Our customers want the highest flexibility to be able to run their search and gen AI-enabled applications, and bringing this functionality to Community unlocks a whole new way to build and test anywhere.”—Jerry Liu, CEO, LlamaIndex. “Participating in the Private Preview of Full-text and Vector Search for MongoDB Community has been an exciting opportunity. Having $search, $searchMeta, and $vectorSearch directly in Community Edition brings the same powerful capabilities we use in Atlas—without additional systems or integrations. Even in early preview, it’s already streamlining workflows and producing faster, more relevant results.”—Michael Höller, MongoDB Champion, akazia Consulting. Accessing the public preview The public preview is available for free and is intended for testing, evaluation, and feedback purposes only. Search and Vector Search with MongoDB Community Edition. The new capabilities are compatible with MongoDB version 8.2+, and operate on a separate binary, mongot, which interacts with the standard mongodb database binary. To get started, ensure that: A MongoDB Community Server cluster is running using one of the following three methods: Download MongoDB Community Server version 8.2 from the MongoDB Downloads page . As of public preview, this feature is available for self-managed deployments on supported Linux distributions and architectures for MongoDB Community Edition version 8.2+. Download the ```mongot``` binary from the MongoDB Downloads page . Pull the container image for Community Server 8.2 from a public Docker Hub repository . Coming soon: Deploy using the MongoDB Controllers for Kubernetes Operator (Search Support for Community Server is planned for version 1.5+ ). Search and Vector Search for use with MongoDB Enterprise Server . The new capabilities are deployed as self-managed search nodes in a customer's Kubernetes environment. This will seamlessly connect to any MongoDB Enterprise Server clusters, residing inside or outside Kubernetes itself. To get started, ensure that: A MongoDB Enterprise Server cluster is running. version 8.0.10+ (for MongoDB Controllers for Kubernetes operator 1.4). version 8.2+ (for MongoDB Controllers for Kubernetes operator 1.5+). A Kubernetes environment. The MongoDB Controllers for Kubernetes Operator are installed in the Kubernetes cluster. Find installation instructions here . Comprehensive documentation for setup for MongoDB Community Edition and MongoDB Enterprise Server is also available. What's next? During the public preview, MongoDB will deliver additional updates and roadmap features based on customer feedback. After the public preview, these search and vector search capabilities are anticipated to be generally available for use with on-premise deployments. For Community Edition, these capabilities will be available at no additional cost as part of the Server Side Public License (SSPL) . For MongoDB Enterprise Server, these capabilities will be included in a new paid subscription offering that will launch in the future. Pricing and packaging details for the subscription will be available closer to launch. For developers seeking a fully managed experience in the cloud, MongoDB Atlas offers a production-ready version of these capabilities today. MongoDB would love to hear feedback! Suggest new features or vote on existing ideas at feedback.mongodb.com . The input is critical for shaping the future of this product. Users can contact their MongoDB account team to provide more comprehensive feedback. Check out MongoDB’s documentation to learn how to get started with Search and Vector Search in MongoDB Community Edition and MongoDB Enterprise Server . 1 MongoDB can be deployed as a fully managed multi-cloud service across all major public cloud providers, in private clouds, locally, on-premises and hybrid environments.
MongoDB AMP: An AI-Driven Approach to Modernization
Why should a database company be your modernization partner? It’s a fair question. From over a decade of experience with database migrations, we've learned that the database is often the single biggest blocker preventing digital transformation. It's where decades of business logic have been embedded, where critical dependencies multiply, and where the complexity that blocks innovation actually lives. But by working with MongoDB, customers have found that transforming their data layer removed the barriers that had stalled previous modernization attempts. This post is also available in: Deutsch , Français , Español , Português , Italiano , 한국어 , 简体中文 . Now, with today’s launch of the MongoDB Application Modernization Platform (AMP), we're providing customers a proven approach to full-stack modernization. MongoDB AMP is an AI-powered solution that rapidly and safely transforms legacy applications into modern, scalable services. MongoDB AMP integrates agentic AI workflows into our modernization methodology, alongside reusable, battle-tested tooling, and the expertise we've developed through customer engagements over the past decade—a powerful combination of tools, technique, and talent. By combining AMP tooling with MongoDB’s proven, repeatable framework, customers have seen tasks like code transformation sped up by 10x or more—with overall modernization projects implemented 2–3 times faster on average. Figure 1. The MongoDB Application Modernization Platform. The common challenges Many of our customers are facing the same impossible choice: accept growing technical debt that slows every business initiative, or risk disruption with a full system rewrite. Their teams are stuck maintaining legacy code instead of building new capabilities. These legacy systems have evolved into interconnected webs (“spaghetti messes”) where even simple changes require coordination across multiple systems and teams. Database changes require corresponding updates to middleware integrations, application business logic, and user interface components. Teams struggle to update systems because any change brings risks breaking something else they don't fully understand. Innovation initiatives often get blocked because new capabilities struggle to integrate within the constraints of legacy systems. Technical debt accumulates with every workaround, making each subsequent change more complex and risky than the last. Before working with MongoDB, Intellect Design's Wealth Management platform exemplified this challenge perfectly . Key business logic was locked in hundreds of SQL stored procedures, leading to batch processing delays of up to eight hours and limiting scalability as transaction volumes grew. The platform’s rigid architecture hindered innovation and blocked integration with other systems, such as treasury and insurance platforms, preventing the delivery of unified financial services that their enterprise clients demanded. In cases like this, the result is stagnation disguised as stability. Systems "work" but can't evolve. Applications can handle today's requirements, but can't adapt to tomorrow's opportunities. Legacy architectures have become the foundation on which everything else depends—and the constraint that prevents everything else from changing. Battle-tested solutions By working through challenges with customers, we've built a comprehensive methodology for modernization, backed by sophisticated tools that address the messy reality of legacy applications. Our approach empowers application teams with proven processes and purpose-built technology to systematically address key challenges. Central to our methodology is a test-first philosophy that has proven essential for safe, reliable modernization. Before any transformation begins, we develop comprehensive test coverage for existing applications, creating a baseline that captures how legacy systems actually behave in production. This upfront investment in testing becomes the foundation for everything that follows, providing guardrails that ensure modernized code performs identically to the original while giving teams the confidence to make changes without fear of breaking critical business processes. Our test-driven approach ensures modernization is a methodical, validated process where every change is verified. Before we make any code changes, we establish a complete picture of the legacy system. We've built sophisticated analysis tools that comprehensively map legacy application architectures. These tools uncover the complex interdependencies and embedded logic that make legacy applications far more intricate than they appear on the surface. This deep analysis isn't just about cataloging complexity; it's about understanding the true scope, informing execution of the transformation, and identifying potential risks before they derail projects. Analysis is just the start. By working with customers, we've learned that successful modernization requires careful sequencing and planning. Our dependency analysis capabilities help teams understand not just what needs to be migrated, but the critical order of operations and what safeguards need to be in place at each step. It's critical to avoid the temptation to migrate everything at once. MongoDB’s approach is designed to make complex modernizations successful by transforming applications incrementally with robust validation. Instead of crossing your fingers and hoping everything works after months of development, our methodology decomposes large modernization efforts into manageable components where every component is iteratively tested and verified. Issues are caught early when they're easy to fix, not after months of development when rollback becomes costly and complex. Each successful iteration reduces risk rather than accumulating it. The agentic AI acceleration MongoDB AMP represents over two years of dedicated effort to integrate AI-powered automation into our battle-tested processes, dramatically accelerating modernization while maintaining the reliability our customers depend on. AI powerfully expands our validation processes by generating additional test cases to validate modernized applications against their legacy counterparts. This dramatically improves confidence in migration results while reducing the time teams spend manually creating test cases for the complex business logic they are trying to preserve. Our existing analysis tools, which decompose embedded logic into smaller segments, now feed directly into AI systems that can automatically transform the code components they discover. What once required weeks of manual code conversion can now happen in hours, with testing frameworks providing the same rigorous validation we've always insisted on. For example, Bendigo and Adelaide Bank reduced the development time to migrate a banking application by up to 90% . The difference is speed and scale, without sacrificing quality or safety. Figure 2. The AMP process. Years of customer engagement and refined processes provide the foundation and guardrails that make AI-powered modernization effective and safe. With MongoDB AMP, AI becomes a force multiplier that transforms our proven approach into something that can tackle modernization challenges at unprecedented speed and scale. Migrating simple code is now 50 to 60 times quicker, and we can migrate small applications 20 times faster to MongoDB. Regression testing also went from three days to three hours with automated test generation. Fabrice Bidard, Head of Technical Architecture, Lombard Odier Ready to begin your modernization journey? Legacy application modernization doesn't have to be a leap of faith. With MongoDB as your partner, you gain access to proven methodologies, battle-tested tools, and the accelerated capabilities that agentic AI brings to our existing expertise. Contact our team to discuss your specific challenges and learn how our proven methodology can be applied to your environment.
Unlock AI With MongoDB and LTIMindtree’s BlueVerse Foundry
Many enterprises are eager to capitalize on gen AI to transform operations and stay competitive, but most remain stuck in proofs of concept that never scale. The problem isn’t ambition. It’s architecture. Rigid legacy systems, brittle pipelines, and fragmented data make it hard to move from idea to impact. That’s why LTIMindtree partnered with MongoDB to create BlueVerse Foundry : a no-code, full-stack AI platform powered by MongoDB Atlas , built to help enterprises quickly go from prototype to production without compromising governance, performance, or flexibility. The power of MongoDB: Data without limits At the heart of this platform is MongoDB Atlas, a multi-cloud database that redefines how enterprises manage and use data for AI. Unlike traditional relational databases, MongoDB’s document model adapts naturally to complex, evolving data, without the friction of rigid schemas or heavy extract, transform, and load pipelines. For AI workloads that rely on diverse formats like vector embeddings, images, or audio, MongoDB is purpose built. Its real-time data capabilities eliminate delays and enable continuous learning and querying. Search is another differentiator. With MongoDB Atlas Search and Atlas Vector Search , MongoDB enables enterprises to combine semantic and keyword queries for highly accurate, context-aware results. GraphRAG adds another layer, connecting relationships in data through retrieval-augmented generation (RAG) to reveal deeper insights. Features like semantic caching ensure performance remains high even under pressure, while built-in support for both public and private cloud deployments makes it easy to scale. Together, these capabilities turn MongoDB from a data store into an AI acceleration engine, supporting everything from retrieval to real-time interaction to full-stack observability. The challenge: Building with limitations Traditional systems were never designed for the kind of data modern AI requires. As enterprises embrace gen AI models that integrate structured and unstructured data, legacy infrastructure shows its cracks. Real-time processing becomes cumbersome, multiple environments create redundancy, and rising computing needs inflate costs. Building AI solutions often demands complex coding, meticulous model training, and extensive infrastructure planning, resulting in a delayed time to market. Add to that the imperative of producing responsible AI, and the challenge becomes even steeper. Models must not only perform but also be accurate, unbiased, and aligned with ethical standards. Enterprises are left juggling AI economics, data security, lineage tracking, and governance, all while trying to deliver tangible business value. This is precisely why a flexible, scalable, and AI-ready data foundation like MongoDB is critical. Its ability to handle diverse data types and provide real-time access directly addresses the limitations of traditional systems when it comes to gen AI. The solution: A smarter way to scale AI With BlueVerse Foundry and MongoDB Atlas, enterprises get the best of both worlds: LTIMindtree’s rapid no-code orchestration and MongoDB’s flexible, scalable data layer. This joint solution eliminates common AI bottlenecks and accelerates deployment, without the need for complex infrastructure or custom code. BlueVerse Foundry’s modular, no-code architecture enables enterprises to quickly build, deploy, and scale AI agents and apps without getting bogged down by technical complexity. This is significantly amplified by MongoDB’s inherent scalability, schema flexibility, and native RAG capabilities, which were key reasons for LTIMindtree choosing MongoDB as the foundational data layer. With features like the no-code agent builder, agent marketplace, and business-process-automation blueprints, enterprises can create tailored solutions that are ready for production, all powered by MongoDB Atlas. A synergistic partnership: Smarter together The collaboration between MongoDB and LTIMindtree’s BlueVerse Foundry brings together powerful AI capabilities with a future-ready database backbone. This partnership highlights how MongoDB’s AI narrative and broader partner strategy focus on enabling enterprises to build intelligent applications faster and more efficiently. Together, they simplify deployment, enable seamless integration with existing systems, and create a platform that can scale effortlessly as enterprise needs evolve. What makes this partnership stand out is the ability to turn ideas into impact faster. With no-code tools, prebuilt agents, and MongoDB’s flexible data model, enterprises don’t need to wait months to see results. They can use their existing infrastructure, plug in seamlessly, and start delivering real-time AI-driven insights almost immediately. Governance, performance, and scalability aren’t afterthoughts; they’re built into every layer of this ecosystem. “We’re seeing a shift from experimentation to execution—enterprises are ready to scale gen AI, but they need the right data foundation,” said Haim Ribbi, Vice President of Global CSI, VAR and Tech Partner at MongoDB. “That’s where MongoDB Atlas fits in, and where an agentic platform like LTIMindtree’s BlueVerse Foundry uses it to its full potential for innovation.” Real-world impact: From data to differentiated experiences This joint solution is already delivering real-world impact. A leading streaming platform used LTIMindtree’s solution, powered by MongoDB, to personalize content recommendations in real time. With MongoDB handling the heavy lifting of diverse data management and live queries, the company saw a 30% rise in user engagement and a 20% improvement in retention. Central to this transformation is the platform’s content hub, which acts as a unified data catalog, organizing enterprise information so it’s accessible, secure, and ready to power next-generation AI solutions with MongoDB’s robust data management. Whether dealing with text, images, or audio, the platform seamlessly manages multimodal data, eliminating the need for separate systems or processes. For businesses looking to accelerate development, BlueVerse Foundry and Marketplace offer a no-code builder, prebuilt agents, and templates, enabling teams to go from concept to deployment in a fraction of the time compared to traditional methods. BlueVerse Foundry’s RAG pipelines simplify building smart applications, using MongoDB Atlas Search and MongoDB Atlas Vector Search for highly effective RAG. Advanced orchestration connects directly with AI models, enabling rapid experimentation and deployment. A globally acclaimed media company has been using BlueVerse Foundry to automate content tagging and digital asset management, cutting its discovery time by 40% and reducing overheads by 15%—clear evidence of gen AI’s bottom-line impact when implemented right. BlueVerse Foundry’s strength lies in combining speed and control. By providing everything from ready-to-use user-experience kits, over 25 plug-and-play microservices, token-based economic models, 100+ safe listed large language models (LLMs), tools and agents, and full-stack observability, BlueVerse Foundry and Marketplace enables enterprises to move faster without losing sight of governance. Its support for voice interfaces, regional languages, Teams, mobile, and wearables like Meta AI Glasses ensures an omnichannel experience out of the box. Responsible AI: A built-in capability LTIMindtree doesn’t just build AI faster; it builds it responsibly. With built-in measures like LLM output evaluation, moderation, and audit trails, the platform ensures enterprises can trust the results their models generate. This is further supported by MongoDB’s robust security features and data governance capabilities, ensuring a secure and ethical AI ecosystem. It’s not just about preventing hallucinations or bias; it’s about creating an ecosystem where quality, transparency, and ethics are fundamental, not optional. Scaling: Streamlined for the long term The platform’s libraries, app galleries, and FinOps tooling enable businesses to test, deploy, and expand with confidence. Powered by MongoDB Atlas’s inherent scalability and multi-cloud flexibility, BlueVerse Foundry is built for long-term AI success, not just early experimentation. Enterprise AI: From possibility to production The BlueVerse Foundry and Marketplace, powered by MongoDB, is more than a technological partnership; it’s a new standard for enterprise AI. It combines deep AI expertise with an agile data foundation, helping organizations escape the trap of endless proofs of concept and unlock meaningful value. For enterprises still unsure about gen AI’s return on investment, this solution offers a proven path forward, grounded in real-world success, scalability, and impact. The future of AI isn’t something to wait for. With LTIMindtree and MongoDB, it’s already here. Explore how LTIMindtree and MongoDB are transforming gen AI from a concept into an enterprise-ready reality. Learn more about building AI applications with MongoDB through the AI Learning Hub .
How MongoDB Helps Your Brand Thrive in the Age of AI
The Zero Moment of Truth (ZMOT) was coined by Google to describe the moment when a user researches a product online before buying—typically through search, reviews, or videos. In a world where AI agents are intermediating shopping decisions (such as through assistant bots, personal agents, or even procurement AIs), the traditional concept of ZMOT starts to break down, because: The “moment” is no longer directly human. The “truth” might be algorithmically filtered. The user delegates the decision process (partially or fully) to an agent. For retailers, this isn't a minor trend—it’s a "change everything" moment. The traditional customer journey is being radically rewired. For decades, the battle was to win the top spot on a search engine results page. But what happens when the customer isn't a person searching, but is instead an AI agent executing a command like, "Buy me the best-value noise-canceling headphones"? If your brand isn't visible to that agent, you are, for all practical purposes, invisible. The brands that will win in this new landscape are the ones that can make their products and services discoverable and transactable not just by humans, but by AI. This shift presents a profound challenge that goes beyond marketing. Brands are shifting their direct relationship with the customer, handing it over to an AI intermediary. Traditional strategies built for human psychology and search engine algorithms become obsolete when the shopper is an AI agent. The core challenges are therefore immense: How do you build trust with an algorithm? How do you communicate your brand's value in a machine-readable format? And most importantly, how do you ensure your product is the one an agent selects from a sea of competitors? This article is meant to provide you with clarity on what the future of online shopping will look like, how your brand will be affected by this new paradigm and why the MongoDB document model is the best underlying tool for organizing and exposing your product catalog to this upcoming agentic ecommerce era. So, how might we rename or reframe ZMOT for this agent-mediated paradigm? To understand this shift, let's first clarify what we mean by 'agentic AI' and 'agents.' Agentic AI refers to artificial intelligence systems capable of acting autonomously to achieve specific goals on behalf of a user, often by interacting with various tools and services. An 'agent' in this context is the specific AI entity that performs these actions. For example, imagine telling your AI assistant, ' Book me a flight to London next month within a £500 budget, departing in the morning .' An AI agent would then autonomously search, compare, and potentially book the flight for you, acting as your personal delegate. Ever since reading the news of OpenAI naming Instacart’s CEO their new Head of Applications, I haven’t stopped thinking about what this will mean for the world of e-commerce and (yes, I’m a millennial) how the term “googling” came to be and became part of our zeitgeist in the early 2000s. The world of e-commerce is on the brink of a similar paradigmatic shift. For years, brands have poured resources into search engine optimization (SEO), battling for coveted spots on search engine results pages. But what if the search engine as we know it gets disrupted? What if, instead of searching, customers simply ask an AI to find and buy for them? This isn't a far-off futuristic fantasy. It's happening now. With the rise of powerful AI assistants like OpenAI's Improved Shopping Results from ChatGPT Search and the new Operator agent, we are entering a new era of "agentic commerce." This is the Agentic Moment of Truth (AMOT): the precise point at which an autonomous agent, acting on behalf of a user, synthesizes data, context, and intent to make or recommend a purchase decision. For retailers, this is a "change everything" moment. The traditional customer journey, from discovery to purchase, is being radically rewired. The brands that will win in this new landscape are the ones that can make their products and services discoverable and transactable not just by humans, but by AI agents. Figure 1. Evolution of the customer journey thanks to agentic AI. The new customer flow: From ZMOT to AMOT For over a decade, marketers have been obsessed with the ZMOT. But, AI agents are collapsing the ZMOT. Instead of a human spending hours browsing websites, reading reviews, and comparing prices, an AI can do it in seconds. This new customer flow, driven by agents, looks something like this: The prompt: A user gives a natural language command to their AI assistant, like, "Find me the best noise-canceling headphones for under $200 with good battery life." The agent's work: The AI agent, like OpenAI's Operator, goes to work. It doesn't just crawl the web in the traditional sense. It interacts with various services and APIs to gather information, compare options, and make a recommendation. The transaction: Once the user approves the recommendation, the agent can complete the purchase, all without the user ever visiting a traditional e-commerce website. This shift has profound implications for retailers. If your brand isn't "agent-friendly," you're essentially invisible in this new world of commerce. So, how do you make your brand discoverable and transactable by AI agents? The answer is to build a remote MCP server. But what exactly is an MCP server, and what are the operational challenges for an e-commerce business in deploying one? An MCP (Model Context Protocol) server is an open standard that allows AI models to connect to and interact with external tools and data sources. Think of it as a universal language for AI. In our context, think of it as a universal translator that enables AI agents to understand and use your product catalog, inventory, pricing, and even checkout functionalities. While this is suitable for internal agentic applications, how can you provide third-party online agents with real-time, up-to-date, and commercially strategic product data? This is where a remote MCP server , powered by technologies like MongoDB Atlas , becomes not just a nice-to-have, but a mission-critical component of your tech stack. However, creating and deploying such a server generates significant operational challenges for an e-commerce business. You need to manage complex, dynamic data structures for product information, rapidly adapt to new AI agent requirements, ensure your infrastructure can scale globally and reliably, and, critically, protect sensitive customer and product data. By creating your own remote MCP server, you can expose your product catalog, inventory, pricing, and even checkout functionality to AI agents in a structured, machine-readable format, and MongoDB Atlas directly addresses these operational hurdles: Superior architecture (the document model): E-commerce data is inherently varied and complex, with products having diverse attributes. The flexible document model of MongoDB Atlas allows you to store product information in a rich, nested structure that mirrors real-world objects. Innovate faster: With the agility of the document model and MongoDB Atlas's developer-friendly environment, your teams can respond to the dynamic needs of agentic commerce at an unprecedented pace. You can rapidly iterate on how your product data is exposed and consumed by AI agents, testing new features and optimizing agent interactions without time-consuming database migrations or refactoring. This speed is crucial in a fast-evolving AI landscape. Build once, deploy everywhere: E-commerce demands low-latency access for agents and users across diverse geographic locations. MongoDB Atlas offers multi-cloud and multi-region deployment options, allowing you to deploy your remote MCP server and product catalog close to your agents and customers, wherever they are. This global distribution capability minimizes latency and ensures high availability, overcoming infrastructure management complexities and guaranteeing that your brand is always transactable. Built-in enterprise security: Exposing your valuable product catalog and transactional capabilities to AI agents requires robust security. MongoDB Atlas provides comprehensive, built-in enterprise-grade security features, including encryption at rest and in transit, network isolation, fine-grained access controls, and auditing. This ensures that your data is protected from unauthorized access and cyber threats, mitigating the significant security challenges associated with opening your systems to external AI interactions. Why retailers must act now The shift to agentic commerce is not a question of if, but when. The MCP Registry, a public directory for AI agents to discover MCP-compliant servers, is set to launch in the fall of 2025. This will be the "yellow pages" for AI agents, and if your brand isn't listed, you'll be left behind. Discover how MongoDB powers the future of retail and helps brands thrive in the age of AI. Learn more about MongoDB for Retail . Ready to boost your MongoDB skills? Visit the Atlas Learning Hub to get started.
Building an Interactive Manhattan Guide with Chatbot Demo Builder
Question: Know any good spots? Response: Based on the context provided, I can recommend a few good pizza spots in Manhattan: Joe's Pizza (7 Carmine St) - This is described as "one of the most beloved slice joints in the city" with a "thin, crispy crust and always fresh" pizza, perfect for a quick bite. Prince Street Pizza (27 Prince St) - Known for its "thick, square pepperoni slice with those crispy-edged 'roni cups." $1 Pizza Slices - The context mentions that $1 pizza slices can still be found, especially around 6th Ave and 8th St in Greenwich Village. This is described as a "quintessential NYC food experience." That’s from a conversation with a chatbot we built in about 10 minutes. There was no coding, no database setup—just a PDF and the Chatbot Demo Builder tool. What made the experience so valuable wasn’t just getting a good response, but seeing exactly what was happening behind the scenes after submitting our question. 🤖 Meet Chatbot Demo Builder Chatbot Demo Builder is the newest addition to the Atlas Search Playground . This no-code tool gives users an intuitive way to explore MongoDB’s vector search capabilities by building interactive Q&A bots with sample data or their own uploads. Powered by MongoDB Atlas Vector Search and Voyage AI , the Builder automatically handles index creation, query generation, and embedding, removing the common setup barriers that often slow down RAG ( retrieval-augmented generation ) experimentation. What makes the tool particularly powerful is its accessibility. Like all tools in the Atlas Search Playground, it runs entirely in your browser without requiring a MongoDB Atlas account, cluster, or collection. This means you can test ideas, iterate quickly, and share prototypes with teammates and stakeholders, all without spinning up additional infrastructure. With MongoDB.local NYC coming up on September 17, we thought it was the perfect time to put the Chatbot Demo Builder through its paces. So we decided to create something practical: a Q&A chatbot to help visitors explore Manhattan. 🧑💻 Building in the browser The entire process happened without leaving our browser. We started by uploading our Manhattan travel guide PDF to the Chatbot Demo Builder. Next, we configured how the chatbot would process our content using the Data Settings modal. For our chunking strategy, we chose recursive chunking with 500-token chunks and 50-token overlap. This preserves paragraph flow while ensuring important information isn’t split awkwardly across boundaries. For the embedding model, we selected voyage-3-large, which excels at general knowledge retrieval tasks. Once configured, we hit "Create Embeddings" and watched as the Builder processed our guide into a demo document collection containing metadata, chunked text, and vector embeddings. Figure 1. Data Settings modal used for chunking configuration and embedding model selection. 📍 Testing like tourists With embeddings generated, we started asking questions like curious visitors: "Where can I find a public restroom near Central Park?" "What are some good day trip ideas?" "What are some fun facts about New York City?" Each query highlighted the Builder's most powerful feature: complete transparency. When we asked about pizza, we could see the exact vector search query that ran, which chunks scored highest, and how the LLM prompt was constructed. This visibility turned experimentation from guesswork into informed iteration. We could understand not just what answers we got, but also why we got them and how to improve them. Figure 2. Vector search query and scored document results for the pizza recommendation question. 🧐 Optimizing for better results Fine-tuning our retrieval settings produced even better outputs. The Builder made these optimizations easily accessible and provided insight into exactly how they would affect results. We started by modifying numCandidates, which controls how many potential matches the system initially examines before selecting the best results. The recommended setting is at least 20 times higher than the limit value, allowing more potential matches to be evaluated before selecting the best ones; this trades a bit of latency for significantly better recall. For even higher precision, the Builder offers an exact nearest neighbor (ENN) search, which calculates distances to all indexed embeddings. While computationally intensive, it guarantees finding the exact nearest neighbors when accuracy is key. Since our Manhattan guide only had 25 documents, we could afford to use ENN without worrying about performance impact. Figure 3. Retrieval settings panel for adjusting search parameters and enabling exact nearest neighbor search. 💡 Sharing and takeaways Once we were happy with the responses, it was easy to share our work. The Builder generated a snapshot link that let the entire team test the chatbot for themselves without any additional setup. In just a few steps, we transformed a static travel PDF into a conversational guide for exploring Manhattan. Along the way, we saw how decisions about chunking strategies, embeddings, and retrieval settings directly affect answer quality. We also gained visibility into what was happening behind the scenes, giving us the insights we needed to optimize these decisions. Figure 4. Output panel tabs displaying data source, vector index, search query, and prompt details By the end, we had a chatbot capable of providing helpful local insights about Manhattan, from day trip ideas to restaurant recommendations, all while giving us complete visibility into how it generated its answers. 🗽 Beyond the big apple Chatbot Demo Builder makes it easy to explore RAG techniques. Whether you're prototyping a customer support bot, building an internal knowledge assistant, or creating an interactive travel guide, Chatbot Demo Builder allows you to gain a clearer understanding of what works best for your AI use case. Ready to get started? Try the Chatbot Demo Builder in the Atlas Search Playground, or check out the official documentation to learn about the other tools available. And if you're joining us in New York for MongoDB.local , consider this your preview of what the city has to offer—courtesy of a chatbot that knows its way around Manhattan.
MongoDB and Hope AI: Craft Enterprise Code with AI
The world of software development is constantly evolving, and the demand for tools that streamline processes, increase efficiency, and enable developers to easily create robust applications continues to rise. For this context, MongoDB and Bit.dev have teamed up to bring a transformative integration to the table, combining MongoDB’s leading database platform with Bit Cloud’s AI-powered, component-based development platform, featuring the Hope AI agent. Bit Cloud is the platform that brings powerful AI and composability capabilities directly to developers through Hope AI. Designed to support smarter, faster development, Hope AI enables architecture planning with control, code generation, collaborative management, and production-ready output. This partnership showcases how Bit Cloud, with Hope AI, empowers developers to innovate efficiently without sacrificing control. Let’s explore the features of Hope AI and see how it transforms the development process. Figure 1. The release process. Going from concept to plan: AI-generated code architecture One of Hope AI’s standout features is its ability to create a code architecture based on user input. This isn’t just about diving straight into coding—Hope AI first provides developers with a clear, visual plan for implementation. Think of it as having an AI architect that listens to your idea, understands your goals, and crafts a tailored blueprint for your application. At this stage, Hope AI does not generate any code; this enables developers to focus on shaping the architecture to fit their unique requirements. Whether they need to make tweaks or add entirely new elements, this phase is highly customizable. Developers can approve the initial plan at their own pace, knowing that any changes are an integral part of the process. Generating code for new or existing applications Once the architecture is approved, Hope AI seamlessly transitions into code generation. This integration is ideal for developers building new applications as well as those enhancing existing ones. For existing applications, adding features is simple—Hope AI can work off the current application and produce code that integrates directly into the existing framework. This versatility positions Hope AI as an innovative tool for projects in all stages of development, helping developers spend less time working around limitations and more time realizing their creative visions. While its current focus is on web application development, Hope AI plans to expand its capabilities to mobile app development in future iterations, making this partnership even more promising for the broader developer community. Gaining full control and ongoing flexibility A major concern with AI-generated code is the possibility of losing control over what’s created. MongoDB and Hope AI address this head-on—developers maintain complete control and can review every line of the AI-generated code. If edits are required, users can make changes directly within the generated code, ensuring the final product aligns precisely with their vision and requirements. Beyond initial creation, Hope AI remains an active participant throughout the development process. Need additional components or features later? The AI is always available to assist, making sure your code evolves alongside your project. Achieving collaboration at the core One of the most exciting features introduced by Hope AI is the ability to “snap” the code. This functionality enables developers to share and manage code with teammates, promoting seamless collaboration. Teams can work together on the project, implement updates, and review progress without any barriers. This collaborative aspect is crucial for modern development teams that thrive on interconnected workflows. Taking a privacy-first approach to code creation Another remarkable feature of Hope AI is its emphasis on privacy. The code generated by Hope AI is 100% private—no sharing for AI model training, no public access to your work. The data is protected, and only the designated project members can access the code. In today’s data-sensitive landscape, this level of privacy is critical. Developers and organizations can trust that their intellectual property is secure and that the AI agent isn’t repurposing their unique codebase for other uses. Integrating MongoDB: Configuring MongoDB Atlas credentials MongoDB plays a crucial role in this collaboration. Hope AI is designed to use MongoDB Community Edition by default, offering developers access to MongoDB’s fast, efficient, and reliable database. However, developers and organizations have the flexibility to choose MongoDB Atlas if they prefer a fully managed, customizable solution. Hope AI fully supports integration with MongoDB Atlas, allowing seamless configuration for those who opt for it. MongoDB Atlas opens up possibilities for advanced database management, including automatic scaling, global data replication, and powerful analytics features. With this level of customization, developers can create applications that meet even the most complex infrastructure demands. Promoting the future of AI-assisted development The collaboration between MongoDB and Hope AI signals more than just a technical partnership; it represents a vision for the future of development. By harnessing the power of AI to streamline coding and by empowering developers to maintain control over their projects, this integration creates an environment where creativity meets efficiency. As Hope AI expands into mobile app support and MongoDB continues to innovate on its platform capabilities, this partnership will likely set the stage for groundbreaking developments that appeal to large-scale organizations. Choosing MongoDB and Hope AI For IT decision-makers, the MongoDB-Hope AI partnership is a win for teams wanting to build faster without compromising quality or security. Here’s why this collaboration stands out: Rapid prototyping and scaling: The AI-powered architecture design and code generation significantly reduce project timelines while safeguarding customization. Secure code management: Privacy-first code generation is designed to prioritize data protection and support security best practices. Enhanced team collaboration: The Snap functionality ensures teamwork thrives, making Hope AI suitable for distributed teams. On-premises availability: The product extends its flexibility by offering an on-premises deployment option, catering to businesses that require hosting within their own infrastructures. Integrated MongoDB services: MongoDB Atlas credentials provide unparalleled database management flexibility while MongoDB Community Edition caters to developers just getting started. Building the future together The integration of MongoDB and Hope AI empowers developers everywhere. Whether you’re designing from scratch, enhancing an existing app, or scaling your team’s efforts across platforms, this partnership promises the tools and capabilities to bring your ideas to life with unprecedented efficiency and control. MongoDB and Hope AI are building the future—and developers are at the center of this exciting transformation. Ready to unlock the full potential of AI-powered development? Visit the MongoDB AI Learning Hub to learn how to begin building AI applications with MongoDB. Connect with Hope AI today to see how MongoDB and Hope AI can transform your ideas into reality.
Streamlining Editorial Operations with Gen AI and MongoDB
Are you overwhelmed by the sheer volume of information and the constant pressure to produce content that truly resonates? Audiences constantly demand engaging and timely topics. As the daily influx of information grows massively, it’s becoming increasingly tough to identify what’s interesting and relevant. Consequently, teams are spending more time researching trends, verifying sources, and managing tools than actually creating compelling stories. This is where artificial intelligence enters the media landscape to offer newer possibilities. Tapping into AI capabilities calls for a flexible data infrastructure in order to streamline content workflows, provide real-time insights, and help teams stay focused on what matters most. In this blog, we will explore how combining gen AI with modern databases, such as MongoDB, can efficiently improve editorial operations. Why are your content ideas running dry? Creative fatigue significantly impacts content production. Content leads face constant pressure to generate fresh ideas under tight deadlines, leading to creative blocks. In fact, a recent report from Hubspot, 16% of content marketers struggle with finding compelling new content ideas . This pressure often compromises work quality due to time constraints, leaving little room for delivering authentic content. Another main hurdle is identifying credible and trending topics quickly. In order to find reliable pieces of information, a lot of time is spent on researching and discovery rather than actual creation. This leads to missed opportunities in identifying what’s trending and reduces the audience engagement as well. This presents a clear opportunity for AI, leveraged with modern databases, to deliver a transformative solution. Using MongoDB to streamline content operations MongoDB provides a flexible, unified storage solution through its collections for modern editorial workflows. The need for a flexible data infrastructure Developing an AI-driven publishing tool necessitates a system that can ingest, process, and structure a high volume of diverse content from multiple sources.. Traditional databases often struggle with this complexity. Such a system demands the ability to ingest data from many sources, dynamically categorize content by industry, and perform advanced AI-enabled searches to scale applications. Combining flexible document-oriented databases with embedding techniques transforms varied content into structured, easily retrievable insights. Figure 1 below illustrates this integrated workflow, from raw data ingestion to semantic retrieval and AI-driven topic suggestions. Figure 1. High-level architectural diagram of the Content Lab solution, showing the flow from the front-end through microservices, backend services, and MongoDB Atlas to AI-driven topic suggestions. Raw data into actionable insights We store a diverse mix of unstructured and semi-structured content in dedicated MongoDB collections such as news, Reddit posts, suggestions, userProfiles, and drafts, organized by topic, vertical (e.g., business, health), and source metadata for efficient retrieval and categorization. These collections are continuously updated from external APIs like NewsAPI and Reddit, alongside AI services (e.g., AWS Bedrock, Anthropic Claude) integrated via backend endpoints. By leveraging embedding models, we transform raw content into organised, meaningful data, stored in their specific categories (e.g., business, health) in the form of vectors. MongoDB Atlas Vector Search and Aggregation Pipeline enables fast semantic retrieval, allowing users to query abstract ideas or keywords and get back the most relevant, trending topics ranked by a similarity score. Generative AI services then draw upon these results to automate the early stages of content development, suggesting topics and drafting initial articles to substantially reduce creative fatigue. From a blank page to first draft – With gen AI and MongoDB Once a user chooses a topic, they’re taken to a draft page, as depicted in the third step of Figure 2. Users are then guided by a large language model (LLM)-based writing assistant and supported by Tavily’s search agent, which pulls in additional contextual information. MongoDB continues to handle all associated metadata and draft state, ensuring the user’s entire journey stays connected and fast. Figure 2. Customer flow pipeline & behind-the-scenes. We also maintain a dedicated userProfiles collection, linked to both the drafts and chatbot systems. This enables dynamic personalization so, for example, a Gen Z user receives writing suggestions aligned with their tone and preferences. This level of contextual adaptation improves user engagement and supports editorial consistency. User-generated drafts are stored as new entries in a dedicated drafts collection. This facilitates persistent storage, version control, and later reuse which is essential for editorial workflows. MongoDB’s flexible schema lets us evolve the data model as we add new content types or fields without migrating data. Solving the content credibility challenge Robust data management directly addresses the content credibility. When we generate topic suggestions, we capture and store the source URLs within MongoDB, embedding these links directly into the suggestion cards shown in the UI. This allows users to quickly verify each topic’s origin and reliability. Additionally, by integrating Tavily, we retrieve related contextual information along with their URLs, further enriching each suggestion. MongoDB’s efficient handling of complex metadata and relational data ensures that editorial teams can consistently and confidently vet content sources, delivering trustworthy, high-quality drafts. By combining Atlas Vector Search, flexible collections, and real-time queries, MongoDB assists greatly in building an end-to-end content system that’s agile, adaptable and intelligent. The next section shows how this translates into a working editorial experience. From raw ideas to ready stories: Our system in action With our current solution, the editorial teams can rapidly transition from scattered ideas to structured, AI-assisted drafts, all within a smart, connected system. The combination of generative AI, semantic search, and flexible data handling enables the workflow to become faster, more spontaneous and less dependent on manual effort. Consequently, the system focuses back on creativity as it becomes convenient to discover relevant topics from verified sources and produce personalised drafts. Adaptability and scalability become the essential factors in developing intelligent systems that can produce great results within the content scope. As editorial demands grow constantly, it necessitates an infrastructure that can ingest diverse data, produce insights, and assist in real-time collaboration. This system illustrates how AI coupled with a flexible, document-oriented backend can assist teams to reduce fatigue, enhance quality and accelerate the production without increasing difficulty. It’s not just about automation; it’s about providing a more focused, efficient, and reliable path from idea to publication. Here are a few next steps to help you explore the tools and techniques behind AI-powered editorial systems: Dive Deeper with Atlas Vector Search : Explore our comprehensive tutorial to understand how Atlas Vector Search empowers semantic search and enables real-time insights from your data. Discover Real-World Applications: Learn more about how MongoDB is transforming media operations by reading the AI-Powered Media article. Check out the MongoDB for Media and Entertainment page to learn more about how we meet the dynamic needs of modern media workflows.
New Benchmark Tests Reveal Key Vector Search Performance Factors
Search at scale is challenging. As powerful as vector search is, it can be tough to know how to properly weigh key factors like accuracy, cost, and throughput for larger workloads. We recently released the MongoDB Benchmark for Atlas Vector Search , which outlines crucial performance optimization strategies for vector search, providing a comprehensive guide to achieving optimal results with large-scale datasets. The primary goal of our guide is to significantly reduce friction for your first vector test at scale (>10M vectors) when evaluating performance for Atlas Vector Search. With this new guide, our aim is to provide more context around how to use the benchmark, to explore the dataset (including factors considered), and to summarize and contextualize the results. Let’s take a closer look! A note on benchmarking data Every good presentation includes the requisite safe harbor slide, and the art and science of benchmarking is no different. Embarking on a large-scale vector workload can present significant hurdles stemming from a lack of accurate information and the inherent friction of initial benchmarks. Furthermore, the landscape of vector search and embedding models is rapidly evolving, and information can become outdated quickly, leading users down inefficient or incorrect paths. Without clear, up-to-date guidance, users can struggle to predict system behavior, optimize configurations, and confidently allocate resources. It’s also worth noting that numerous factors (quantization, dimensionality, filtering, search node configuration, concurrency, sharding, and more) interact in complex ways. Understanding these interactions and their specific impact on a particular workload requires deep, accurate insights. Without this, users might optimize one aspect only to inadvertently degrade another. This informational vacuum—coupled with the considerable setup overhead, complex parameter tuning, and the cost of experimentation involved in running the first benchmark—creates a substantial barrier to proving out and scaling a solution. Nonetheless, we feel that these benchmarks provide confidence in POCs for our customers and give them a starting point to work with (as opposed to having no compass to start with). With these factors in mind, let's jump into an overview of the dataset. A look at the dataset The core of this performance analysis revolves around tests conducted on subsets of the Amazon Reviews 2023 dataset, which contained 48M item descriptions across 33 product categories. The dataset was chosen due to the ability to provide a realistic, large-scale e-commerce scenario, as well as offering rich data, including user reviews (ratings, text, helpfulness votes), item metadata (price, images), and detailed item names and descriptions, which are ideal to search over. For the variable dimension tests, subsets of 5.5 million items were used, embedded with voyage-3-large to produce 2048-dimensional vectors. Views were then created to slice these into 1024, 512, and 256-dimensional vectors for testing different dimensionalities. For the large-scale, high-dimensional test, a 15.3 million-item subset—also embedded with 2048-dimensional vectors from voyage-3-large —was used. One of the key takeaways from the report is that at the highest dimensionality (15.3M vectors using voyage-3-large embeddings at 2048 dimensions), Atlas Vector Search with scalar or binary quantization configured retains 90–95% accuracy with less than 50ms of query latency. One item of note is that binary quantization can have higher latency when the number of candidates requested is in the hundreds due to the additional cost of rescoring with full-fidelity vectors, but still might be preferable for many large scale workloads due to cost effectiveness. Figure 1. Binary versus scalar quantization performance. Methodology: Benchmarking with the Amazon reviews dataset Now that we talked a little bit about the data itself and the information included, let’s outline some of the key factors that impact performance for Atlas Vector Search, and how we configured our benchmark to test them. It's also important to acknowledge why these variables are critical: Not every customer will be optimizing their search for the same thing. With that in mind, we will also attempt to identify the interplay and trade-offs between them. While this list is not exhaustive ( see the full report for more details), let’s review some of the key performance factors: Recall : Recall (a measure of search accuracy) is significantly impacted by quantization and vector dimensionality. The report highlights that while scalar quantization generally starts with higher recall, binary quantization can approach similar accuracy levels by increasing numCandidates, though this often incurs higher latency due to an additional rescoring step. Furthermore, higher-dimensional vectors (1024d and 2048d) consistently maintain better recall, especially with larger datasets and quantization, compared to lower dimensions (256d and 512d), which struggle to exceed 70-80% recall. Sizing and cost : The table in the benchmark details the resources required (RAM, storage) and associated costs for different search node tiers based on three different test cases involving varying dataset sizes, vector dimensions, and quantization methods (scalar or binary). The guide provides an example of a sample dataset noting the resource requirements scale linearly, noting how quantization reduces memory requirements substantially. Concurrency and throughput : Throughput is evaluated with multiple requests issued concurrently. Scalar quantization generally achieves higher queries per second (QPS) across various limit values due to less work per query and no rescoring. Concurrency bottlenecks are often observed, indicating that higher latency can occur. Scaling out the number of search nodes or increasing available vCPUs is recommended to resolve these bottlenecks and achieve higher QPS. Figure 2. Node tiers for different test cases. Optimizing your vector search performance This benchmark report thoroughly examines the performance of MongoDB Atlas Vector Search across various configurations and large datasets, specifically the Amazon Reviews 2023 dataset. It explores the impact of factors such as quantization (scalar and binary), vector dimensionality, filtering, search node configurations, binData compression, concurrency, and sharding on recall, latency, and throughput. While there is never a “silver bullet” due to everyone’s definition of search “success” being different, we wanted to highlight some of the various levers to consider, and methods to get the most out of your own deployment. Our goal is to provide some key considerations for how to evaluate and improve your own vector search performance, and help you to properly weigh and contextualize the key factors. Ready to optimize your vector search experience? Explore the guide in our documentation . Run it yourself with our GitHub repo .
Powering Long-Term Memory for Agents With LangGraph and MongoDB
We're excited to introduce the MongoDB Store for LangGraph—a powerful integration that brings flexible and scalable long-term memory to AI agents. This new integration between MongoDB and LangGraph , LangChain’s open-source agent orchestration framework, allows agents to remember and build on previous interactions across multiple sessions instead of only retaining memory for the current session. The result is more intelligent, context-aware agentic systems that learn and improve over time. This new integration complements MongoDB’s existing checkpointer integration, which handles short-term memory and persistent conversation history. Together, the MongoDB Store for LangGraph and MongoDB’s support for checkpointers provide a complete solution for building production-ready, memory-enabled agents. The need for agent memory An AI agent is a system designed to take actions or make decisions based on input, often using tools and reasoning to complete tasks. By default, agents don’t retain memory between conversations, which severely constrains what they can accomplish. Agent memory (and memory management) is a computational exocortex for AI agents. It is a dynamic, systematic process that integrates an agent’s large language model (LLM) memory (context window and parametric weights) with a persistent memory management system to encode, store, retrieve, and synthesize knowledge and experiences. Agent memory is typically divided into two main types: short-term memory and long-term memory. In a memory context, LangGraph uses “threads” to represent individual conversations or sessions. Short-term memory, managed through thread-scoped checkpointers that MongoDB supports, maintains context within a given session. While this preserves conversation continuity and manages history, it doesn’t help agents learn continuously from the past across different conversations to adapt and optimize their behavior over time. This is why we introduced the MongoDB Store for LangGraph, enabling your agents to retain memories across conversations through a cross-thread memory store. Figure 1. Short and long-term memory integration between LangGraph and MongoDB. MongoDB Store: Enabling cross-thread long-term memory The new langgraph-store-mongodb package introduces a MongoDBStore class. Available now through PyPI , this production-ready integration provides: Cross-thread persistence: Store and recall information across different conversation sessions and user interactions, allowing agents to build on previous knowledge. Native JSON structure: LangGraph stores long-term memories as JSON documents, which map directly to MongoDB documents. Each memory is organized using namespaces and a key-value structure. This enables the usage of MongoDB’s native and optimized data formats and search capabilities for efficient retrieval. Vector Search capabilities: Leverage MongoDB Atlas Vector Search for semantic memory retrieval based on meaning, not just keyword matching. Asynchronous support: Support for both synchronous and asynchronous operations for high-performance applications. Automatic connection management: Robust connection pooling and error handling to ensure reliability. Optimized TTL indexes: MongoDB’s Time-to-Live (TTL) indexes are integrated with LangGraph’s TTL system, allowing automatic removal of stale or outdated data. This improves retrieval performance, reduces storage costs, and ensures the system "forgets" obsolete memories efficiently. Ready to give your AI agents persistent long-term memory? The langgraph-store-mongodb package is available now: pip install langgraph-store-mongodb The MongoDB Store for LangGraph enables developers to build more powerful agents for different use cases, including: Customer support agents: Build agents that remember customer preferences, past issues, and resolution patterns across multiple support channels. Personal assistant applications: Build agents that learn user habits and preferences to provide increasingly personalized experiences. Enterprise knowledge management: Create agents that accumulate organizational knowledge and can retrieve relevant information semantically. Multi-agent systems: Enable agent teams to share learned experiences and coordinate through persistent memory. Why MongoDB for agent memory? Effective agentic memory requires comprehensive mechanisms for storing, retrieving, updating, and deleting memories. MongoDB Atlas provides a unified database that meets all these complex requirements: Flexible document model: Store complex, nested memories as rich JSON, matching how agents naturally read, organize, and update evolving information. Semantic search: Native vector search enables retrieval by meaning, not just exact matches. State-of-the-art models: Voyage AI provides embedding models and rerankers for cutting-edge memory retrieval. Scalable architecture: Distributed architecture, workload isolation, autoscaling, and automatic sharding capabilities for scaling AI agent memory. Enterprise security: Fine-grained role-based access control (RBAC) allows precise management of both access scope (specific services or databases) and access type (read-only or read-write). MongoDB Atlas and LangChain: A complete solution for AI agent memory Short-term memory provides an agent with immediate context, current conversation state, prior exchanges within that session, or shared memory for coordination in multi-agent systems. The most common form of short-term memory is working memory—an active, temporary context accessible during a session. MongoDB's integration with LangGraph checkpointers supports this by persisting and restoring conversation states. Other short-term memory implementations include semantic caches, such as using MongoDB's semantic cache integration with LangChain , which stores recent prompts and LLM responses for retrieval when similar queries occur. Shared memory is also used in multi-agent systems to provide a common space for coordination and information sharing. Long-term memory serves as the agent’s knowledge base, storing diverse kinds of information for future use. It includes several functional types, each requiring specific storage and retrieval strategies: Episodic memory: captures specific events and interactions, such as conversation history or summaries of key occurrences with metadata (e.g., timestamps, participants). For instance, a customer support agent can use this to recall a user’s past issues and offer personalized responses. Procedural memory: records instructions or rules for recurring tasks. A typical implementation is a social content generator agent that remembers past feedback on writing style and formatting to improve its process. Semantic memory: remembers general knowledge, facts, and concepts. This is often implemented through retrieval-augmented generation (RAG), where data is stored as vector embeddings and retrieved based on semantic similarity. Associative memory: stores key entities and relationships between different pieces of information, enabling an agent to identify patterns and make inferences by navigating these connections. It's often implemented using graph structures that support efficient exploration of relationships. One practical approach is GraphRAG . The MongoDB Store for LangGraph supports these memory types through flexible filtering and semantic search, making it a versatile approach for building reliable long-term memory in agents. LangChain also provides LangMem, a toolkit featuring pre-built tools designed specifically for extracting and managing procedural, episodic, and semantic memories. LangMem integrates natively with LangGraph, streamlining the memory engineering process. For developers seeking a straightforward approach to using various memory types with MongoDB, explore this comprehensive tutorial for implementing MongoDB alongside LangGraph and LangMem . The future of intelligent agents With the new MongoDB Store for LangGraph, we're enabling developers to build AI agents that can learn and adapt. Agents that remember user preferences, learn from mistakes, and build knowledge over time will transform how we interact with AI systems. The combination of LangGraph's sophisticated orchestration capabilities with MongoDB's flexible, scalable storage creates unprecedented opportunities for building intelligent, persistent AI agents that feel truly alive and responsive. Ready to build memory-enabled agents with LangGraph and MongoDB Atlas? Get started with the documentation .
Building an Agentic AI Fleet Management Solution
Artificial intelligence is revolutionizing the manufacturing and motion industry, with AI-powered solutions now capable of delivering precise, real-time insights that can optimize everything from route planning to predictive maintenance. Modern vehicles can generate an overwhelming amount of data—nearly 25 GB per hour, through a diverse range of sensors, according to an article from S&P Global Mobility. Contextualizing this data with user feedback, maintenance records, and technical knowledge becomes increasingly challenging as the system scales. These complexities can create inefficiencies, introduce overhead while processing data, and drive up operational costs, hindering the full potential of AI-driven systems. An efficient fleet management architecture can address these problems by reducing redundancies, optimizing data retrieval processes, and enabling the seamless integration and use of embeddings. MongoDB’s flexible document model fits perfectly to this approach. Unlike legacy SQL databases, MongoDB excels at managing unstructured, semi-structured, and structured data. This capability allows fleet management software to ingest and process diverse data types, including vehicle signal data, geospatial zones, fleet configurations, query logs, route telemetry, maintenance records, and real-time performance scores. In this post, we will use various MongoDB Atlas features—such as geospatial query operations, time-series collections, Atlas Charts, and aggregation pipelines—to create an agentic AI-powered fleet management system. This system demonstrates how an AI agent can enable intelligent data processing, providing real-time, context-aware responses to user queries in a streamlined manner. Fleet management software with AI overview A traditional fleet management system provides features like resource planning, route optimization, and maintenance scheduling which work together to improve Cost Management, Regulatory Compliance, and Overall Operational Effectiveness (OEE). Our solution harnesses the power of MongoDB's flexible document schema, time-series collections, and geospatial query support to give fleet managers the ability to query, filter and operate on data effectively. Additionally, an AI Agent assists users in obtaining actionable insights through a chat-driven interface. Figure 1. Architecture of the solution. The AI agent has a chatbot UI. The data captured by the agent is used to trigger an orchestration service which then calls various tools as required and gets data from MongoDB in order to complete its task. In Figure 1, the telemetry data from our cars is stored in MongoDB in time series collections via microservices. In addition to the telemetry data we store stationary car information (e.g., brand, model, year, VIN, among others) and user configurations, such as past queries and fleet settings. All of this data is leveraged by the agentic system to answer user queries and provide deeper insights for future references to similar queries. Figure 2 shows the user interface of the agentic system where queries can be submitted directly. Filters allow users to narrow results by fleet, time range, or geozone, while the AI Agent delivers answers using real-time and historical data. Figure 2. Demo chat section. When a user inputs a question into the chat box, the AI Agent analyzes it by embedding the query into metadata and searching for similar prior questions in the historical recommendations collection. Depending on the tools required, the system accesses contextual data across collections, such as time-series metrics, geospatial locations, or maintenance logs, through aggregation pipelines. Once the relevant data is assembled, the AI synthesizes the information into actionable insights, providing the user with an accurate and informative response. MongoDB features for a fleet management system RAG framework with MongoDB Vector Search Agents powered by retrieval-augmented generation (RAG) are transforming fleet management systems by seamlessly integrating real-time contextual information during response generation. MongoDB’s flexible NoSQL model complements RAG by embedding fast, low-latency document data. Combined with Voyage AI’s cost-efficient embedding model, MongoDB accelerates vector search workflows for smarter decision-making MongoDB’s Atlas Vector Search empowers the agent to operate proactively by connecting user queries with relevant insights stored in the database. For instance, when a fleet manager asks about the current positions of vehicles, the agent leverages MongoDB’s vector search to match the query against historical recommendations. If similar queries already exist, the agent retrieves pre-existing results instantly, reducing both latency and operational costs. In situations where no matching results are found, the agent complements vector search by invoking LLMs to dynamically generate answers, ensuring fleet managers receive accurate and actionable responses. This streamlined workflow, powered by MongoDB’s unique combination of vector search and flexible data modeling, allows fleet managers to act on real-time, context-aware insights. From analyzing geospatial patterns to addressing systemic vehicle issues, MongoDB enables the agent to simplify complex decision-making while maintaining efficiency. By combining predictive AI capabilities with an optimized, scalable database, this solution transforms fleet management into a more proactive, data-driven process. Polymorphysm MongoDB’s document model allows storing polymorphic data structures within the same collection, meaning documents can vary in structure and embed other documents. This flexibility enables our demo to optimize workflows by storing application-specific metadata tailored to fleet operations. For instance, the historical_recommendations collection stores query and recommendation histories generated by the system’s AI engine, with the ability to embed metadata dynamically, such as the initial question asked, the tool chosen, and the results it got. This enables improved context for future queries by streamlining read operations, and giving more context for our AI agent. For example, a document in this collection might appear as follows: Figure 3. Document model of historical_recommendations. This variability in structure without sacrificing efficiency enables MongoDB to adapt to dynamic data storage requirements inherent in polymorphic workflows. By embedding detailed context and avoiding null values, the system can streamline read operations and provide richer context to the AI agent for future queries. Time series collections MongoDB's time series collections simplify working with time series data. These specialized collections provide several benefits, including automatic creation of compound indexes for faster data retrieval, reduced disk usage, and lower I/O overhead for read operations. This makes time series collections highly efficient for managing time-stamped data, such as a constant stream of sensor data from vehicles in our application. With these capabilities, fleet managers can enable near real-time access to data, empowering AI agents to rapidly extract actionable insights for fleet management. In this demo, MongoDB optimizes query efficiency in our time series collections using its bucketing mechanism. This mechanism groups multiple data points within the same time range into compressed blocks, reducing the number of documents scanned during queries. This results in documents scanned during queries. By grouping multiple data points within the same time range, bucketing minimizes read operations and disk usage, enabling faster range queries and ensuring sustained, optimized cluster performance, even under a humongous load. GeoSpatial queries MongoDB’s native support for geospatial queries enables seamless integration of robust location-based functionalities. The ability to handle complex geographic data is a powerful tool for industries relying on real-time location-based decision-making. In our demo, this capability is leveraged to locate vehicles under various conditions, such as identifying vehicles near or inside a specified geofence, while being able to filter by maximum or minimum distance. Also, geospatial queries can be incorporated directly into aggregation pipelines, enhancing AI-driven workflows powered by our AI Agent. Key takeaways MongoDB enables fleet managers to efficiently gather, process, and analyze data to uncover actionable insights. These capabilities empower managers to optimize operations, enhance vehicle oversight, and implement smarter, data-driven strategies that drive efficiency and performance. Visit MongoDB Atlas to start modernizing your fleet management system. Ready to transform your fleet management operations? Unlock real-time insights, optimize systems, and make smarter decisions with MongoDB’s advanced features. If you're interested in exploring how MongoDB enables intelligent fleet management, check out our Leafy Fleet GitHub repository. Access the Leafy Fleet on GitHub . Additionally, dive deeper into best practices for modeling connected vehicle signal data and learn how MongoDB’s flexible data model simplifies telemetry management at scale. Read the blog post .
Unlock Multi-Agent AI Predictive Maintenance with MongoDB
The manufacturing sector is navigating a growing number of challenges: evolving customer demands, intricate software-mechanical product integrations, just-in-time global supply chains, and a shrinking skilled labor force. Meanwhile, the entire sector is working under intense pressure to improve productivity, manage energy consumption, and keep costs in check. To stay competitive, the industry is undergoing a digital transformation—and data is at the center of that shift. Data-driven manufacturing offers a powerful answer to many of these challenges. On the shop floor, one of the most critical and high-impact applications of these strategies is predictive maintenance. Downtime isn’t just inconvenient—it’s expensive. For example, every unproductive hour in the automotive sector now costs $2.3 million (according to Siemens "The True Cost of Downtime 2024" report). For manufacturers across all sectors, predictive maintenance is no longer optional. It’s a foundational pillar of operational excellence. At its core, predictive maintenance is about using data to anticipate machine failures before they happen. It began with traditional statistical models, evolved with machine learning, and is now entering a new era. As equipment ages and failure behaviors shift, models must adapt. This has led to the adoption of more advanced approaches, including generative AI with retrieval-augmented generation (RAG) capabilities. But the next frontier is multi-agent systems—AI-powered agents working together to monitor, reason, and act. We’ve explored how generative AI powers predictive maintenance in previous posts. In this blog post, we’ll go deeper into multi-agent systems and how MongoDB makes it easy to build and scale them for smart, responsive maintenance strategies. Advance your data-driven manufacturing strategy with Agentic AI AI agents combine large language models (LLMs) with tools, memory, and logic to autonomously handle complex tasks. On the shop floor, this means agents can automate inspections, reoptimize production schedules, assist with fault diagnostics, and more. According to a LangChain survey , 78% of companies are actively developing AI agents, and over half already have at least one agent in production. Manufacturing companies can especially benefit from agentic capabilities across a great variety of practical use cases, as shown in Figure 1. Figure 1. Agent capabilities and related practical use cases in manufacturing. But leveraging AI agents in industrial environments presents unique challenges. Integration with industrial protocols like Modbus or PROFINET is complex. Governance and security requirements are strict, especially when agents interact with production equipment. Latency is also a concern as AI models need fast, reliable data access to support real-time responses. And with agents generating and consuming large volumes of data, companies need a data foundation that is reliable and can scale without sacrificing performance. Many of these challenges are not new to manufacturers—and MongoDB has a proven track record of addressing them. Industry leaders in manufacturing and automotive trust MongoDB to power critical IoT and telemetry use cases. Bosch , for example, uses MongoDB to store, manage, and analyze huge amounts of data to power its Bosch IoT Insights solution. MongoDB’s flexible document model is ideal for diverse sensor inputs and machine telemetry, while allowing systems to iterate and evolve quickly. It’s important to remember that, at its core, MongoDB was built for change, so when it comes to integrating AI in the shopfloor, it’s no surprise that MongoDB is emerging as the ideal data layer foundation. Companies like Novo Nordisk and Cisco rely on MongoDB to build and scale their AI capabilities, and leading platforms like XMPro APEX AI leverage MongoDB Atlas to create and manage advanced AI agents for industrial applications. MongoDB Atlas makes it easy to build AI Agents and operate them at scale. As both a vector and a document database, Atlas supports various search methods for agentic RAG, while also enabling agents to store short and long-term memory in the same database. The result is a unified data layer that bridges industrial IoT and agentic AI. Predictive maintenance is a perfect example of how these capabilities come together to drive real impact on the shop floor. In the next section, we’ll walk through a practical blueprint for building a multi-agent predictive maintenance system using MongoDB Atlas. Building a multi-agent predictive maintenance system This solution demonstrates how to build a multi-agent predictive maintenance system using MongoDB Atlas, LangGraph, and Amazon Bedrock. This system can streamline complex processes, such as detecting equipment anomalies, diagnosing root causes, generating work orders, and scheduling maintenance. At a high level, this solution leverages MongoDB Atlas as the unified data layer. LangGraph provides the orchestration layer, enabling graph-based coordination among agents, while Amazon Bedrock powers the underlying foundational models used by the agents to reason and make decisions. The architecture follows a supervisor-agent pattern. The supervisor coordinates tasks and delegates to three specialized agents: Failure agent , which performs root cause analysis and generates incident reports. Work order agent , which drafts maintenance work orders with detailed requirements. Planning agent , which identifies the optimal time slot for the maintenance task based on availability and production constraints. Figure 2. High-level architecture of a multi-agent predictive maintenance system. This modular design enables the system to scale easily and adapt to different operational needs. Let’s walk through the full process in four key steps. Step 1: Failure prediction kicks off the agentic workflow The process begins with an alert—something unusual in the machine data or logs that could point to a potential failure. MongoDB provides a unified view of operational data, real-time processing capabilities, and seamless compatibility with machine learning tools. Sensor data is processed in real-time using Atlas Stream Processing integrated with ML inference models. Features like native support for Time Series data and Online Archive facilitate managing telemetry data at scale efficiently. All while the downstream applications remain up to date with the latest notifications and dashboards by using Atlas Triggers , Change Streams , and Atlas Charts . From there, the supervisor agent takes over and coordinates the next steps. Figure 3. End-to-end failure prediction process that generates the alerts. Step 2: Leverage your data for root cause analysis The supervisor notifies the Failure Agent about the alert. Manual diagnostics of a machine can take hours—sifting through manuals, historical logs, and environmental data. The AI agent automates this process. It collects relevant documents, retrieves contextual insights using Atlas vector search, and analyzes environmental conditions stored in the database—like temperature or humidity at the time of failure. With this data, the agent performs a root cause analysis and proposes corrective actions. It generates a concise incident report and shares it with the supervisor agent, which then moves the workflow forward. Figure 4. Failure Agent performing root cause analysis. Step 3: Work order process automation The Work Order Agent receives the incident report and drafts a comprehensive maintenance work order. It pulls from previous similar tasks to estimate time requirements, identify the necessary materials, and ensure the right skill sets are listed. All of this is pre-filled into a standardized work order template and saved back into MongoDB Atlas. This step also includes a human-in-the-loop checkpoint. Technicians or supervisors can review and modify the draft before it is finalized. Figure 5 Work Order Agent is generating a draft work order and routing it for human validation. Step 4: Finding the optimal maintenance schedule Once the work order is approved, the Planning Agent steps in. Its task is to schedule the maintenance activity without disrupting production. The agent queries the production calendar, checks staff shift schedules, and verifies inventory availability for required materials. It considers alert severity and rescheduling constraints to find the most efficient time slot. Once the optimal window is identified, the agent sends the updated plan to the scheduling system. Figure 6. Planning Agent is evaluating constraints to identify the optimal maintenance schedule. While we focused on a predictive maintenance work flow, this architecture can be easily extended. Need agents for compliance reporting, spare parts procurement, or shift planning? No problem. With the right foundation, the possibilities are endless. Unlocking manufacturing excellence with Agentic AI Agentic AI represents a new chapter in the evolution of predictive maintenance, enabling manufacturers to move from reactive responses to intelligent, autonomous decision-making. By combining AI agents with real-time telemetry and a unified data foundation, teams can reduce downtime, cut maintenance costs, and boost equipment reliability. But to work at scale, these systems need flexible, high-performance infrastructure. With native support for time series data, vector search, stream processing, and more, MongoDB makes it easier to build, operate, and evolve multi-agent solutions in complex industrial environments. The result is smarter operations, greater resilience, and a clear path to manufacturing excellence. Clone the GitHub repository if you are interested in trying out this solution yourself. To learn more about MongoDB’s role in the manufacturing industry, please visit our manufacturing and automotive webpage .