Artificial Intelligence
Building AI-powered Apps with MongoDB
Production-Ready Agents Need A Production-Ready Data Platform
There’s a common theme to the conversations I’ve been having with AI teams lately: change. Constant, head-spinning change. Teams across industries are evaluating and re-evaluating model providers, agent frameworks, and harnesses on a continuous basis. At MongoDB, we believe that your choice of technology partner—specifically, your data platform—should simplify how you build with AI. It should deliver performance at scale, enable you to build and run anywhere, and it should allow you to choose your own providers and frameworks. This is exactly what MongoDB offers, and it’s why more than 67,000 customers rely on us for their most important applications. The organizations seeing the most AI success are the ones whose technology stacks are set up for the current pace of change. For example, DevRev’s AgentOS platform is powered by MongoDB Atlas. AgentOS handles billions of requests each month, for everything from AI-assisted insights and analytics to internal communications and development. Relying on MongoDB Atlas has helped DevRev get innovations to market faster, and enables the company to scale seamlessly as it grows. MongoDB is ideal for agentic AI in two key ways. First, an agent is only as smart as its context—which requires blending short-term memory, long-term knowledge, and enterprise data. Because this information is highly dynamic and unstructured, JSON is the ideal format. It provides the schema flexibility inherently needed by the data and allows attaching metadata like IDs and confidence scores. MongoDB stores JSON natively and provides the scale and consistency required to run thousands of concurrent agents. Second, it’s designed for how agents work. As memory accumulates, agents must pinpoint the precise context needed for a request. MongoDB solves this by providing state-of-the-art information retrieval capabilities (search, vector search, hybrid search, embeddings) directly where the operational data already lives, eliminating the need to constantly sync data across separate systems. Customers get high-precision semantic retrieval without the operational headache of managing multiple fragmented products. A good example of how MongoDB powers agents is ElevenLabs. The company relies on MongoDB Atlas to power the long-term memory and knowledge base for its autonomous agents. By leveraging Atlas Search and Vector Search, ElevenLabs enables their agents to retain complex context and deliver highly personalized interactions in real-time. Adobe, meanwhile, chose MongoDB as the long-term memory and reasoning layer for Journey Agent, its composite multimodal AI agent that unifies Adobe's marketing suite and orchestrates end-to-end customer journeys. Adobe leverages MongoDB Atlas Search and Atlas Vector Search together to power the sub-100 millisecond hybrid search the agent needs to act in real time. Defining an open standard for agent memory Last month, MongoDB partner LangChain announced the launch of Context Hub in LangSmith, a place to store, version, and collaborate on the files that define how agents behave, like AGENT.md and agent skills. But context engineering goes beyond that. Agents also rely on memory: short-term context captured in states, sessions, and interaction history, and long-term memory that persists across sessions. Figure 1. Agent memory with MongoDB. Production-Ready Agents blog image 1 media Today, there is no broadly adopted open standard for defining and managing portable agent memory across agent frameworks. Now, MongoDB—alongside LangChain and ecosystem partners—is working on an open reference architecture and contributing toward greater interoperability in this space. This work will help define what has been missing from the AI ecosystem: shared interfaces, metadata conventions, versioning patterns, and retrieval semantics for the data that differentiate agentic experiences and shape agent behavior. The aim is to enable organizations to switch model providers or try a new framework on a Tuesday—and not lose Wednesday rewriting memory plumbing. Ultimately, we want to make agent memory and context easier (and faster) to manage. For customer-facing agents to make real-time decisions, such as responding to a support request or making a policy change, they need contextual information instantly. Not info from a data warehouse that might be 30 minutes old. The context layer needs to be real-time, a required capability we’ve been delivering for tens of thousands of customers going on almost two decades. MongoDB’s performant, flexible platform = agentic success The next generation of agents will increasingly be long-horizon systems, running for hours or more. As they take on more complex tasks, context will become even more critical, and agent memory will be central to making them effective. This will create a demand for diverse, high-performance memory systems, and MongoDB is positioned to provide the flexibility and scalability agents require. With the recent release MongoDB 8.3, our core database has evolved to better support the speed and demands of AI workloads. MongoDB also delivers the retrieval accuracy necessary for agent outputs to be trusted (a non-negotiable for customer-facing applications) while optimizing tokens and cost in production. Every AI team is currently making a bet about what the future of the agentic stack will look like. The ones betting on a flexible, production-ready data platform like MongoDB—that enables teams to innovate now while ensuring structure and resilience for the future—will be able to pivot quickly. The ones betting on rigid schema designs, or on a smattering of specific models and frameworks, might end up redoing their plumbing instead of shipping products. Figure 2. Advantages of MongoDB's flexible schema for AI workloads. Production Ready Agents Blog - Image 2 media MongoDB is built for AI: JSON is the lingua franca of AI. The information agents need is highly dynamic and can be structured, semi-structured, and unstructured. MongoDB provides the schema flexibility inherently needed by the data and allows attaching metadata for richer, more precise context. Dynamic, adaptive schemas that evolve in place as fast as thought without breaking what runs on top. The MongoDB document model isn’t adapted for AI; it’s the natural shape of AI data. MongoDB offers one data platform: Every data requirement for production AI is natively integrated. Search, vector search, embeddings, hybrid retrieval, time series, and streaming run on the same OLTP foundation 67,000+ customers trust with mission-critical applications—with one API, one security model, one operational footprint.
Security in the Age of AI
Everything we do at MongoDB starts with customers and we work backward from their needs. As a result, I frequently engage with customers, partners, and industry peers to proactively find new ways to collectively strengthen our defenses—ideally, long before any issues arise.
LG Uplus Works With MongoDB to Expand AI Services and Modernize Architecture
LG Uplus, a key subsidiary of LG Corporation and a leader in mobile, internet, and AI transformation, today announced that it will work with MongoDB to expand the use of generative AI and accelerate its modernization strategy across the company.
MongoDB as the Mandate Ledger for Agentic Commerce: Supporting A2A, AP2 & UCP
Agentic commerce is here! Retailers and technologists are faced with the task of creating new architectures to support trustworthy, secure, and auditable agentic commerce. The tech sector has moved quickly to meet this challenge with a new wave of agentic protocols. The industry is moving fast: following the launch of Agent to Agent Protocol (A2A) in April 2025, Google launched Agents Payments Protocol (AP2) in Sept 2025, followed by Unified Commerce Protocol (UCP) in January 2026.
Improved Multitenancy Support in Vector Search: Introducing Flat Indexes
The future of AI is personal. The more accustomed to AI tools users are, the more they want their experience of working with them to be personalized and agentic. Whether it is an AI assistant recalling your past conversations, a legal tool reviewing a specific company's contracts, or a personal knowledge base searching through your private documents, these applications all rely on one core capability: providing "memory" specific to a single user or business.
Introducing MongoDB Agent Skills and Plugins for Coding Agents
Software engineering is evolving into agentic engineering. According to the Stack Overflow Developer Survey 2025, 84% of respondents use or plan to use AI tools in their development, up from 76% the previous year. At this rate, the tooling needs to keep pace. Last year, we introduced the MongoDB MCP Server to give agents the connectivity they need to interact with MongoDB, helping them generate context-aware code. But connectivity was only the start. Agents are generalists by design, and they don't inherently know the best practices and design patterns that real-world production systems demand. Today, we're addressing this by introducing official MongoDB Agent Skills: structured instructions, best practices, and resources that agents can discover and apply to generate more reliable code across the full development lifecycle, from schema design and performance optimization to implementing advanced capabilities like AI retrieval. To bring this directly into the tools you use, we're also launching plugins for Claude Code, Cursor, Gemini CLI, and VS Code, combining the MongoDB MCP Server and Agent Skills in a single, ready-to-use package. Turning coding agents into MongoDB experts Coding agents are great at producing working code, but they still make common mistakes in production systems, often defaulting to relational thinking that doesn't translate well to MongoDB, such as: Over-normalizing schemas, ignoring MongoDB's document-oriented strengths. Underusing compound indexes, causing performance bottlenecks at scale. Misusing indexes and search indexes, overlooking the consistency trade-off for high-performance full-text search. Because these pitfalls mirror common human errors, they are naturally reflected in agent outputs. MongoDB Agent Skills address this by providing expert guidance to agents, like schema design heuristics, indexing strategies, query patterns, and operational safeguards, enabling agents to ship more reliable, more consistent code faster. Agent Skills were introduced by Anthropic as an open standard and have since been adopted by the leading AI development tools, including Claude Code, Cursor, Codex, and more. This initial release covers the full application development lifecycle on MongoDB, from connection management and schema design to guidance on implementing advanced capabilities. We will continue to update and expand our skills library based on user needs. Figure 1. MongoDB Agent Skills. Scaling agentic engineering with MongoDB As organizations embrace agentic software engineering, existing processes and workflows must be reimagined. The MongoDB MCP Server and MongoDB Agent Skills are built for this shift and work best together, giving builders and agents the tools to move fast without sacrificing guardrails or control. The MongoDB MCP Server serves as the connectivity layer for your MongoDB deployments. It manages authentication and defines exactly what agents can access and do. Combined with MongoDB’s native authorization, it ensures agents operate with only the permissions they need, while giving teams governance through configurable controls like disabling specific tools. Agent Skills ensure agents follow best practices from the start, reducing architectural risk, accelerating implementation, and raising the baseline quality of every agent-generated code. While some skills can be used independently, others work in conjunction with the MongoDB MCP Server for workflows that require it. To simplify setup, the MCP Server and skills are now packaged together as plugins and extensions for Claude Code, Cursor, Gemini CLI, and VS Code, bringing these capabilities directly into your preferred tools. Figure 2. MongoDB for Claude plugin in action. We also encourage you to build your own skills as your agentic workflows mature. Whether enforcing internal naming conventions, custom data modeling patterns, or team-specific workflows, skills give you a practical way to codify institutional knowledge and ensure every agent and every developer works from the same playbook. How to get started Whether you’re using Claude Code, Cursor, Gemini CLI, or other AI development tools, you can install the MongoDB MCP Server and Agent Skills in seconds. For example, in Claude Code, install the plugin that bundles both: Code Snippet /plugin marketplace add mongodb/agent-skills /plugin install mongodb@mongodb-plugins For Cursor, Gemini CLI, and VS Code extensions, refer to their respective documentation. You can also install the skills for most coding agents using the Vercel Skills CLI (requires Node.js): Code Snippet npx skills add mongodb/agent-skills If you prefer, you can manually clone the GitHub repository and copy the skills into the appropriate folder for your agent. Similarly, to install the MongoDB MCP Server, use the following command: Code Snippet npx mongodb-mcp-server@latest setup Agentic engineering is changing how teams work, and it is changing fast. Agents need the context and guidance to meet the standards of real-world production applications. With the official MongoDB Agent Skills and plugins, builders can move faster with confidence, and organizations can adopt coding agents knowing that MongoDB best practices are embedded directly into every workflow. Next Steps Ship faster, more reliable apps on MongoDB with Agent Skills. Install for Claude Code, Cursor, Gemini CLI and VS Code!
Zomato Cuts $11M in Support Costs With MongoDB-Powered AI Platform
With more than 25 million active monthly users—and hundreds of millions of food delivery orders annually—Indian-born Zomato is the world's second-largest food delivery company. At the heart of the business’s success is Zomato’s ability to seamlessly scale, manage complex data, and build innovative AI-powered applications at pace.
Unlocking Agentic Power to Modernize Cross-Border Payment Systems
The global payments landscape is a complex web of independent systems enabling international trade. According to Juniper Research, the market reached a value of $187 trillion in 2025 and is projected to hit $224 trillion by 2030. However, operational friction undermines this scale. Failed payments drain the global economy of over $100 billion annually, according to a study by LexisNexis.
Edge AI Made Easy: MongoDB and ObjectBox Data Synchronization
AI is currently undergoing a shift, from massive centralized models to distributed, real-world deployments. While the cloud remains the foundation for large-scale AI training and analytics, AI’s next evolution lies at the edge—where data is created, where decisions require instant action, and where connectivity cannot be guaranteed. At MongoDB, we are committed to helping organizations build intelligent applications that span cloud and edge environments seamlessly. That’s why we are excited to highlight our work with ObjectBox, a lightweight, high-performance on-device database and sync solution purpose-built for edge AI and offline-first applications. Together, MongoDB and ObjectBox are making it easier for developers to build hybrid architectures that deliver fast, private, and resilient AI experiences across devices and environments. Figure 1. Example cloud-edge AI setup. Example cloud-edge AI setup. ObjectBox: A purpose-built database for the edge Founded by Markus Junginger and Dr. Vivien Dollinger, ObjectBox was designed specifically to support edge computing and offline-first use cases. At its core, ObjectBox’s design prioritizes efficiency (including speed, privacy, battery use, and memory consumption) and ease of development. This strong foundation makes ObjectBox particularly well-suited for next-generation applications that need to run reliably in edge environments—whether on a factory floor, in a retail store, or through a remote healthcare device. ObjectBox empowers developers to build responsive, privacy-conscious applications that work even when connectivity is limited or unavailable. The platform includes the following features: A fast, local vector database that stores data directly on devices, supporting on-device AI and local vector search. Built-in data sync, which keeps data consistent across devices even when offline, and now integrates directly with MongoDB. Multi-language support, including support for C++, Swift, Flutter, Python, Go, Java, and Kotlin, makes ObjectBox accessible to developers across ecosystems. These features make ObjectBox an ideal solution for building intelligent applications that run reliably at the edge. This includes a wide range of devices—from smartphones and industrial sensors to automotive ECUs and point-of-sale (POS) devices. Edge to cloud data sync: The MongoDB Atlas native connector ObjectBox's new MongoDB Sync Connector combines local-first edge processing with centralized cloud intelligence (i.e., hybrid AI). This is increasingly important as organizations seek to process data closer to where it is generated—at the edge—while still benefiting from the power and scalability of the cloud. Managing this dual environment efficiently is key to unlocking performance, resilience, and real-time insights. Developers can now use ObjectBox for real-time, low-latency operations on edge devices while syncing relevant data to MongoDB Atlas, enabling organizations to achieve: Long-term storage Centralized dashboards and analytics AI model retraining Cloud-based coordination and automation This hybrid architecture aligns with how modern applications are being built—distributing intelligence where it makes the most sense. Figure 2. Central Sync for ObjectBox and MongoDB Atlas. Central Sync for ObjectBox and MongoDB Atlas. Figure 3. Edge setup for ObjectBox and MongoDB Atlas. Edge setup for ObjectBox and MongoDB Atlas Bringing AI to the edge isn’t just about performance. It is also about privacy, sustainability, and user experience. By processing data locally: Privacy is enhanced—sensitive information stays on the device. Latency is reduced—actions can be taken instantly. Bandwidth usage drops—lowering costs and improving efficiency. Battery and CPU use are optimized—extending the life of edge devices. This aligns with MongoDB’s commitment to empowering developers to build intelligent, resilient, and user-centric applications—wherever they need. Real-world use cases Industrial IoT Industrial IoT (IIoT) is a prime example of where edge and cloud must work together. On a modern factory floor, everything from low-frequency brownfield devices to high-frequency greenfield machines generates vast amounts of data. Data generated include vibration levels, temperature readings, pressure changes, and machine runtimes. In short, the sort of data that often needs to be processed locally to monitor systems in real time and to trigger alerts when anomalies or threshold breaches occur. With ObjectBox running on device, this critical operational data can be captured, analyzed, and used onsite and within AI applications immediately, even with limited or no connectivity. ObjectBox is designed for efficient, high-throughput I/O, enabling real-time processing of high-frequency data streams even on resource-constrained edge devices. It supports a broad range of data types—from objects and time series data, to tree structures (e.g., UMATI) and vector embeddings—with a lightweight database (typically only a few MB in size). This makes it well-suited for production deployments that need to integrate modern AI and edge workloads with legacy systems and heterogeneous hardware, typical for the manufacturing industry. The ObjectBox Sync Server can run on almost any device, enabling fast, reliable, and secure offline data synchronization across the shop floor. Paired with the MongoDB Sync Connector, the most relevant insights can then be synced to the cloud, where they can be aggregated, enriched with AI models, and stored for long-term analysis (like anomaly detection or RUL models). This hybrid architecture enables advanced use cases such as predictive maintenance, where historical records, live equipment data, and machine learning models are combined to forecast potential failures before they happen. (For more details, explore our Predictive Maintenance solutions library.) With this architecture, the system provides: Real-time responsiveness on the shop floor Centralized analytics and cross-site dashboards at cloud scale Support for predictive maintenance workflows in offline or intermittently connected environments Unified data access across heterogeneous data sources, from individual sensors to full production lines By combining low-latency edge processing with centralized intelligence, developers and operators gain visibility into how equipment is performing from the health of a single machine, to trends across an entire fleet or factory network—without compromising performance or reliability. Figure 4. Industrial IoT. Industrial IoT. Point-of-sale systems Point-of-sale (POS) systems—such as those used in restaurants—are another strong fit for edge AI and hybrid architectures. During peak dining hours, cashiers and servers need instant, reliable access to menus, order histories, and payment processing—even if their internet connection is unstable or drops. With ObjectBox’s offline-first, on-device database, restaurants can process real-time transactions, track inventory, and personalize customer experiences with local AI directly at the POS terminal. This helps store owners avoid service disruptions or lost sales. With MongoDB Sync Connector, relevant data (like sales trends, customer preferences, and stock levels) syncs to MongoDB Atlas. This enables restaurant managers to run centralized dashboards, perform demand forecasting, and train AI models that optimize staffing, menu design, and supply chain planning. In summary, this hybrid POS architecture of local-first responsiveness and cloud-powered insights ensures: Seamless customer experiences without downtime Accurate, up-to-date data whenever needed Scalable, resilient operations across multiple restaurant locations Figure 5. Point-of-sale systems. Point-of-sale systems. What’s next With the release of ObjectBox 5.0 and its new MongoDB Connector, ObjectBox has taken a major step toward simplifying user‑specific data sync at the edge. Together, MongoDB and ObjectBox offer a modern foundation for building intelligent, distributed applications that run reliably from device to cloud. This partnership makes it easier than ever to pair low‑latency edge data processing with the flexibility, security, and global reach of MongoDB Atlas.
Heidi’s AI Scribe Scales to 81M Clinical Consultations
Clinicians spend up to 40% of their working hours on documentation tasks. Heidi, a rapidly growing Australian-based global AI startup, is on a mission to protect and extend the human touch in healthcare. In just 18 months, Heidi has returned more than 18 million hours to frontline clinicians by streamlining critical administrative tasks.
Unlock Historical Archive Value with Multimodal AI
Digitization was supposed to solve the archive problem. Scan the pages, run Optical Character Recognition (OCR), enable keyword search—done. Yet decades and millions of dollars later, most newspaper archives remain essentially unusable for serious research.
Semantic Power, Lexical Precision: Advanced Filtering for Vector Search
We are excited to announce the launch of Lexical Prefilters for MongoDB Vector Search, providing developers with a way to use advanced text and geo analysis filters alongside vector search. This new capability simplifies the challenge of building advanced applications by helping developers build richer and more sophisticated search experiences through the combination of semantic understanding and precise text filtering.
Introducing the Embedding and Reranking API on MongoDB Atlas
The next frontier for AI isn’t simply more capable models. It’s better context. As LLMs become embedded in every process and product, their accuracy and trust depend on grounding generation in the right data. Search and retrieval are foundational to this shift, powering everything from AI chatbots and assistants to fully autonomous agents. But building AI retrieval today means stitching together databases, vector search, and retrieval model providers—each introducing operational complexity.
Kindred Tech uses AI and MongoDB to Fight Child Exploitation in India
Faced with a steep increase in online child exploitation in India, law enforcement agencies are turning to advanced AI-driven tools to accelerate investigations and deliver justice. According to the National Centre for Missing and Exploited Children (NCMEC) agencies in India received 2.2 million cybertips related to abuse in 2024.
Enterprise-Level, Scalable AI with Morphik and MongoDB
As AI continues to revolutionize how large enterprises operate, the most crucial startups are those capable of turning massive amounts of unstructured information into actionable intelligence. Morphik, one of the fastest-growing AI knowledge platforms for enterprises, uses MongoDB to deliver secure, high-performance, multitenant systems that power real-world automation at scale.
Revolutionize Asset Maintenance with MongoDB and MaintainX
We’re excited to announce that MongoDB and MaintainX are joining forces to help manufacturers achieve excellence in maintenance operations. This joint solution enables a digital thread from raw production data to maintenance execution.
Building Next-gen AI agents: The MongoDB Atlas-Microsoft Foundry Integration
Generative AI is rapidly evolving from experimenting with models to relying on intelligent, autonomous multi-agent workflows that can reason, act, and adapt in real time. Together, Microsoft and MongoDB are defining the future of AI by providing companies everywhere a robust, secure, scalable foundation for building innovative, next-generation AI agents.
How Rierino Scales AI-Native Low-Code with MongoDB
Launched in 2020, the AI-native low-code development platform Rierino was founded to close a critical gap in enterprise technology. Businesses demanded faster innovation, but existing development tools lagged behind the pace of change.
Unlocking Financial Services Document Intelligence with Agentic AI and MongoDB
Driven by rising customer expectations and the demand for greater efficiency, accuracy, and agility, the financial services industry is undergoing a profound transformation. Gone are the days of painstaking manual document reviews, and welcome instead to the era of agentic AI, where intelligent systems and a robust data foundation redefine how financial data is processed and understood. Powered by MongoDB’s flexible, scalable platform, organizations can seamlessly manage multimodal data to unlock insights, automate workflows, and stay ahead in this evolving landscape.
Announcing the MongoDB Plugin for Firebase Genkit
We’re thrilled to introduce the MongoDB Plugin for Genkit, designed to accelerate your AI-powered applications with advanced search and database tooling—all within the Genkit ecosystem. Whether you're building chatbots, intelligent assistants, or recommendation engines, this plugin brings together MongoDB’s cutting-edge search capabilities and Genkit’s AI workflows, enabling seamless vector, full-text, and hybrid search with zero hassle.
Smarter AI Search, Powered by MongoDB Atlas and Pureinsights
We’re excited to announce that the integration of MongoDB Atlas with the Pureinsights Discovery Platform is now generally available—bringing to life a reimagined search experience powered by keyword, vector, and gen AI. What if your search box didn’t just find results, but instead understood intent? That’s exactly what this integration delivers! Beyond search: From matching to meaning Developers rely on MongoDB’s expansive knowledge ecosystem to find answers fast. But even with a rich library of technical blogs, forum threads, and documentation, traditional keyword search often falls short—especially when queries are nuanced, multilingual, or context-driven. That’s where the MongoDB-Pureinsights solution shines. Built on MongoDB Atlas and orchestrated by the Pureinsights Discovery platform, this intelligent search experience starts with the fundamentals: fast, accurate keyword results, powered by MongoDB Atlas Search . But as queries grow more ambiguous—say, “tutorials for AI”—the platform steps up. MongoDB Atlas Vector Search with Voyage AI , available as an embedding and reranking option (now part of MongoDB), goes beyond literal keywords to interpret intent—helping applications deliver smarter, more relevant results. The outcome: smarter, semantically aware responses that feel intuitive and accurate—because they are. What’s more, with generative answers enabled, the platform synthesizes information across MongoDB’s ecosystem (blog content, forums, and technical docs) to deliver clear, contextual answers using state-of-the-art language models. But it's not just pointing you to the right page. Instead, the platform is providing the right answer, with citations, ready to use. It’s like embedding a domain-trained AI assistant directly into your search bar. “As organizations look to move beyond traditional keyword search, they need solutions that combine speed, relevance, and contextual understanding,” said Haim Ribbi, Vice President, Global CSI, VAR & Tech Partner at MongoDB. “MongoDB Atlas provides the foundation for smarter discovery, and this collaboration with Pureinsights shows how easily teams can deliver gen AI-powered search experiences using their existing content.” Built for users everywhere But intelligence alone doesn’t make it transformational. What sets this experience apart is its adaptability. Whether you’re a developer troubleshooting in Berlin or a product owner building in São Paulo, the platform tailors responses to your preferences. Prefer concise summaries or deep technical dives? Want to translate answers in real time? Need responses that reflect your role and context? You’re in control. From tone and length to language and specificity, this is a search that truly understands you—literally and figuratively. Built on MongoDB. Elevated by Voyage AI. Delivered by Pureinsights. At the core of this solution is MongoDB Atlas, which unifies fast, scalable data access to structured content through Atlas Search and Atlas Vector Search. Looking ahead, by integrating with Voyage AI’s industry-leading embedding models, MongoDB Atlas aims to make semantic search and retrieval-augmented generation (RAG) applications even more accurate and reliable. While currently in private preview, this enhancement signals a promising future for developers building intelligent, AI-powered experiences. Pureinsights handles the orchestration layer. Their Discovery Platform ingests and enriches content, blends keyword, vector, and generative search into a seamless UI, and integrates with large language models like GPT-4. The platform supports multilingual capabilities, easy deployment, and enterprise-grade scalability out of the box. While generative answers are powered by integrated large language models (LLMs) and may vary by deployment, the solution is enterprise-ready, cloud-native, and built to scale. Bringing intelligent discovery to your own data Watch the demo video to see AI-powered search in action across 4,000+ pages of MongoDB content—from community forums and blog posts to technical documentation. While the demo features MongoDB’s content, the solution is built to adapt. You can bring the same AI-powered experience to your internal knowledge base, customer support portal, or developer hub—no need to build from scratch. Visit our partner page to learn more about MongoDB and Pureinsights and how we’re helping enterprises build smarter, AI-powered search experiences. Apply for a free gen AI demo using your enterprise content.
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 .
The Future of AI Software Development is Agentic
Today in New York, our flagship MongoDB.local event is bringing together thousands of developers and tech leaders to discuss the future of building with MongoDB. Among the many exciting innovations and product announcements shared during the event, one theme has stood out: empowering developers to reliably build with AI and create AI solutions at scale on MongoDB. This post will explore how these advancements are set to accelerate developer productivity in the AI era. Ship faster with the MongoDB MCP Server Software development is rapidly evolving with AI tools powered by large language models (LLMs). From AI-driven editors like VS Code with GitHub Copilot and Windsurf, to terminal-based coding agents like Claude Code, these tools are transforming how developers work. While these tools bring tremendous productivity gains already, coding agents are still limited by the context they have. Since databases hold the core of most application-related data, access to configuration details, schemas, and sample data from databases is essential for generating accurate code and optimized queries. With Anthropic’s introduction of the Model Context Protocol (MCP) in November 2024, a new way emerged to connect AI agents with data sources and services. Database connection and interaction quickly became one of the most popular use cases for MCP in agentic coding. Today, we’re excited to announce the general availability (GA) of the MongoDB MCP Server, giving AI assistants and agents access to the context they need to explore, manage, and generate better code with MongoDB. Building on our public preview used by thousands of developers, the GA release introduces key capabilities to strengthen production readiness: Enterprise-grade authentication (OIDC, LDAP, Kerberos) and proxy connectivity. Self-hosted remote deployment support, enabling shared deployments across teams, streamlined setup, and centralized configuration. Note that we recommend following security best practices , such as implementing authentication for remote deployments. Accessible as a bundle with the MongoDB for VS Code extension , it delivers a complete experience: visually explore your database with the extension or interact with the same connection through your AI assistant, all without switching context. Figure 1. Overview of the MongoDB MCP Server. Meeting developers where they are with n8n and CrewAI integrations AI is transforming how developers build with MongoDB, not just in coding workflows, but also in creating AI applications and agents. From retrieval-augmented generation (RAG) to powering agent memory, these systems demand a database that can handle diverse data types—such as unstructured text (e.g., messages, code, documents), vectors, and graphs—all while supporting comprehensive retrieval mechanisms at scale like vector and hybrid search. MongoDB delivers this in a single, unified platform: the flexible document model supports the varied data agents need to store, while advanced, natively integrated search capabilities eliminate the need for separate vector databases. With Voyage AI by MongoDB providing state-of-the-art embedding models and rerankers, developers get a complete foundation for building intelligent agents without added infrastructure complexity. As part of our commitment to making MongoDB as easy to use as possible, we’re excited to announce new integrations with n8n and CrewAI . n8n has emerged as one of the most popular platforms for building AI solutions, thanks to its visual interface and out-of-the-box components that make it simple and accessible to create reliable AI workflows. This integration adds official support for MongoDB Atlas Vector Search , enabling developers to build RAG and agentic RAG systems through a flexible, visual interface. It also introduces an agent chat memory node for n8n agents, allowing conversations to persist by storing message history in MongoDB. Figure 2. Example workflow with n8n and MongoDB powering an AI agent. Meanwhile, CrewAI—a fast-growing open-source framework for building and orchestrating AI agents—makes multi-agent collaboration more accessible to developers. As AI agents take on increasingly complex and productive workflows such as online research, report writing, and enterprise document analysis, multiple specialized agents need to interact and delegate tasks with each other effectively. CrewAI provides an easy and approachable way to build such multi-agent systems. Our official integration adds support for MongoDB Atlas Vector Search , empowering developers to build agents that leverage RAG at scale. Learn how to implement agentic RAG with MongoDB Atlas and CrewAI. The future is agentic AI is fundamentally reshaping the entire software development lifecycle, including for developers building with MongoDB. New technology like the MongoDB MCP Server is paving the way for database-aware agentic coding, representing the future of software development. At the same time, we’re committed to meeting developers where they are: integrating our capabilities into their favorite frameworks and tools so they can benefit from MongoDB’s reliability and scalability to build AI apps and agents with ease. Start building your applications with the MongoDB MCP Server today by following the Get Started guide . Visit the AI Learning Hub to learn more about building AI applications with MongoDB.
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. This post is also available in: Deutsch , Français , Español , Português , Italiano , 한국어 , 简体中文 . 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 and Instant Checkout , we are entering a new era of "agentic commerce" with the company already defining an Agentic Commerce Protocol. This is why I believe brands will now move to analyzing 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.
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.
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.
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.
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.
How Tavily Uses MongoDB to Enhance Agentic Workflows
As AI agents grow in popularity and are used in increasingly mission-critical ways, preventing hallucinations and giving agents up-to-date context is more important than ever. Context can come from many sources—prompts, documents, proprietary internal databases, and the internet itself. Among these sources, the internet stands out as uniquely valuable, a best-in-class resource for humans and LLMs alike due to its massive scale and constant updates. But how can large language models (LLMs) access the latest and greatest information from the internet?
Fine-tune MongoDB Deployments with AppMap’s AI Tools and Diagrams
In a rapidly changing landscape, organizations that adapt for growth, efficiency, and competitiveness will be best positioned to succeed. Central to this effort is the continuous fine-tuning and troubleshooting of existing deployments, enabling companies to deliver high-performance applications that meet their business requirements.
Revolutionizing Inventory Classification with Generative AI
In today's volatile geopolitical environment, the global automotive industry faces compounding disruptions that require a fundamental rethink of data and operations strategy. After decades of low import taxes, the return of tariffs as a tool of economic negotiations has led the global automotive industry to delay model-year transitions and disrupt traditional production and release cycles. As of June 2025, only 3% of US automotive inventory comprises next-model-year vehicles—less than half the number seen at this time in previous years.
Build an AI-Ready Data Foundation with MongoDB Atlas on Azure
It’s time for a database reality check. While conversations around AI usually focus on its immense potential, these advancements are also bringing developers face to face with an immediate challenge: Their organizations’ data infrastructure isn’t ready for AI.
Unified Commerce for Retail Innovation with MongoDB Atlas
Unified commerce is often touted as a transformative concept, yet it represents a long-standing challenge for retailers—disparate data sources and siloed systems. It’s less of a revolutionary concept and more of a necessary shift to make long-standing problems more manageable. Doing so provides a complete business overview—and enables personalized customer experiences—by breaking down silos and ensuring consistent interactions across online, in-store, and mobile channels. Real-time data analysis enables targeted content and recommendations.
Intellect Design Accelerates Modernization by 200% with MongoDB and Gen AI
It’s difficult to overstate the importance of modernization in the age of AI. Because organizations everywhere rely on software to connect with customers and run their businesses, how well they manage the AI-driven shift in what software does—from handling predefined tasks and following rules, to being a dynamic, problem-solving partner—will determine whether or note they succeed.
MongoDB and deepset Pave the Way for Effortless AI App Creation
Building robust AI-powered applications has often been a complex, resource-intensive process. It typically demands deep technical and domain expertise, significant development effort, and a long time to value. For IT decision-makers, the goal is clear: enable AI innovation to achieve real business outcomes without compromising scalability, flexibility, or performance, and without creating bottlenecks for development teams serving business teams and customers.
PointHealth AI: Scaling Precision Medicine for Millions
For years, the healthcare industry has grappled with a persistent, frustrating challenge: the absence of a unified, precise approach to patient treatment. Patients often endure "trial-and-error prescribing," leading to delayed recovery and a system bogged down by inefficiency. The core problem lies in scaling precision medicine—making advanced, individualized care accessible to millions of people.
Enhancing AI Observability with MongoDB and Langtrace
Building high-performance AI applications isn’t just about choosing the right models—it’s also about understanding how they behave in real-world scenarios. Langtrace offers the tools necessary to gain deep insights into AI performance, ensuring efficiency, accuracy, and scalability.
Navigating the AI Revolution: The Importance of Adaptation
In 1999, Steve Ballmer gave a famous speech in which he said that the “key to industry transformation, the key to success is developers developers developers developers developers developers developers, developers developers developers developers developers developers developers! Yes!”
Luna AI and MongoDB Throw Lifeline to Product Teams
Product and engineering leaders face a constant battle: making crucial real-time decisions amidst a sea of fragmented, reactive, and disconnected progress data. The old ways—chasing updates, endlessly pinging teams on Slack, digging through Jira, and enduring endless status meetings—simply aren't cutting it. This struggle leaves product and engineering leads wasting precious hours on manual updates, while critical risks silently slip through the cracks. This crucial challenge is precisely what Luna AI, powered by its robust partnership with MongoDB, is designed to overcome.
Secure Your RAG Workflows with MongoDB Atlas + Enkrypt AI
Generative AI is no longer a futuristic concept—it's already transforming industries from healthcare and finance, to software development and media. According to a 2023 McKinsey report, generative AI could add up to $4.4 trillion annually to the global economy across a wide range of use cases. At the core of this transformation are vector databases, which act as the "memory" that powers retrieval-augmented generation (RAG), semantic search, intelligent chatbots, and more.
OrderOnline: AI Improves Conversion Rate by 56% with MongoDB
Established by Ordivo Group in 2018, OrderOnline has quickly become a driving force behind Indonesia’s thriving social commerce market. OrderOnline offers an end-to-end solution for organizations and individuals selling on social platforms like Facebook Marketplace, typically through social ads, landing pages, and storefronts.
Capgemini & MongoDB: Smarter AI and Data for Business
AI is reshaping the way enterprises operate, but one fundamental challenge still exists: Most applications were not built with AI in mind. Traditional enterprise systems are designed for transactions, not intelligent decision-making, making it difficult to integrate AI at scale. To bridge this gap, MongoDB and Capgemini are enabling businesses to modernize their infrastructure, unify data platforms, and power AI-driven applications. This blog explores the trends driving the AI revolution and the role that Capgemini and MongoDB play in powering AI solutions.
Reimagining Investment Portfolio Management with Agentic AI
Risk management in capital markets is becoming increasingly complex for investment portfolio managers. The need to process vast amounts of data—from real-time market to unstructured social media data—demands a level of flexibility and scalability that traditional systems struggle to keep up with.
Multi-Agentic Systems in Industry with XMPro & MongoDB Atlas
In 2025, agentic AI applications are no longer pet projects—companies around the world are investing in software to incorporate AI agents into their business workflows. The most common use of an AI agent is to assist with research analysis or writing code. LangChain’s recent survey of over 1000 professionals across multiple industries showed that over 51% have already deployed agents in production, with 60% using the agents for research and summarization tasks.
VPBank Builds OpenAPI Platform With MongoDB
Open banking is the practice of banks sharing some of their financial data and services to developers for third-party financial service providers through an API. Open banking has accelerated the digitization of the financial services and banking industries. It also helps foster innovation and enhance customer experience by helping create customer-centric, personalized services and experiences.
Transforming News Into Audio Experiences with MongoDB and AI
You wake up, brew your coffee, and start your day with a perfectly tailored podcast summarizing the latest news—delivered in a natural, engaging voice. No manual curation, no human narration, just seamless AI magic. Sounds like the future? It's happening now, powered by MongoDB and generative AI.
GraphRAG with MongoDB Atlas: Integrating Knowledge Graphs with LLMs
A key challenge AI developers face is providing context to large language models (LLMs) to build reliable AI-enhanced applications; retrieval-augmented generation (RAG) is widely used to tackle this challenge. While vector-based RAG, the standard (or baseline) implementation of retrieval-augmented generation, is useful for many use cases, it is limited in providing LLMs with reasoning capabilities that can understand relationships between diverse concepts scattered throughout large knowledge bases. As a result, the accuracy of vector RAG-enhanced LLM outputs in applications can disappoint—and even mislead—end users.
MongoDB Powers M-DAQ’s Anti-Money Laundering Compliance Platform
Founded and headquartered in Singapore, M-DAQ Global is a fintech powerhouse providing seamless cross-border transactions for businesses worldwide. M-DAQ’s comprehensive suite of foreign exchange, collections, and payments solutions help organizations of all sizes navigate the complexities of global trade, offering FX clarity, certainty, and payment mobility.
LangChainGo and MongoDB: Powering RAG Applications in Go
MongoDB is excited to announce our integration with LangChainGo, making it easier to build Go applications powered by large language models (LLMs). This integration streamlines LLM-based application development by leveraging LangChainGo’s abstractions to simplify LLM orchestration, MongoDB’s vector database capabilities, and Go’s strengths as a performant, scalable, and easy-to-use production-ready language.
Building Gen AI with MongoDB & AI Partners | February 2025
February was big for MongoDB—and, more importantly, for anyone looking to build AI applications that deliver highly accurate, relevant information (in other words, for everyone building AI apps). MongoDB announced the acquisition of Voyage AI, a pioneer in state-of-the-art embedding and reranking models that power next-generation AI applications.
ORiGAMi: A Machine Learning Architecture for the Document Model
The document model has proven to be the optimal paradigm for modern application schemas. At MongoDB, we've long understood that semi-structured data formats like JSON offer superior expressiveness compared to traditional tabular and relational representations. Their flexible schema accommodates dynamic and nested data structures, naturally representing complex relationships between data entities.
AI-Powered Java Applications With MongoDB and LangChain4j
MongoDB is pleased to introduce its integration with LangChain4j, a popular framework for integrating large language models (LLMs) into Java applications. This collaboration simplifies the integration of MongoDB Atlas Vector Search into Java applications for building AI applications.
Multi-Agent Collaboration for Manufacturing Operations Optimization
While there are some naysayers across the media landscape who doubt the potential impact of AI innovations, for those of us immersed in implementing AI on a daily basis, there’s wide agreement that its potential is huge and world-altering. It’s now generally accepted that Large Language Models (LLMs) will eventually be able to perform tasks as well—if not better—than a human. And the size of the potential AI market is truly staggering. Bain’s AI analysis estimates that the total addressable market (TAM) for AI and gen AI-related hardware and software will grow between 40% and 55% annually, reaching between $780 billion and $990 billion by 2027. This growth is especially relevant to industries like manufacturing, where generative AI can be applied across the value chain. From inventory categorization to product risk assessments, knowledge management, and predictive maintenance strategy generation, AI's potential to optimize manufacturing operations cannot be overstated.
Smarter Care: MongoDB & Microsoft
Healthcare is on the cusp of a revolution powered by data and AI. Microsoft, with innovations like Azure OpenAI, Microsoft Fabric, and Power BI, has become a leading force in this transformation. MongoDB Atlas complements these advancements with a flexible and scalable platform for unifying operational, metadata, and AI data, enabling seamless integration into healthcare workflows.
Supercharge AI Data Management With Knowledge Graphs
WhyHow.AI has built and open-sourced a platform using MongoDB, enhancing how organizations leverage knowledge graphs for data management and insights. Integrated with MongoDB, this solution offers a scalable foundation with features like vector search and aggregation to support organizations in their AI journey.
Building Gen AI with MongoDB & AI Partners | January 2025
Even for those of us who work in technology, it can be hard to keep track of the awards companies give and receive throughout the year. For example, in the past few months MongoDB has announced both our own awards (such as the William Zola Award for Community Excellence) and awards the company has received—like the AWS Technology Partner of the Year NAMER and two awards from RepVue. And that’s just us! It can be a lot!
Automate Network Management Using Gen AI Ops with MongoDB
Imagine that it’s a typical Tuesday afternoon and that you’re the operations manager for a major North American telecommunications company. Suddenly, your Network Operations Center (NOC) receives an alert that web traffic in Toronto has surged by hundreds of percentage points over the last hour—far above its usual baseline. At nearly the same moment, a major Toronto-based client complains that their video streams have been buffering nonstop.
Securing Digital Transformation with MongoDB and RegData
Data security and privacy have long been paramount to the financial industry, but they are especially critical for institutions undergoing digital transformations or those implementing new technology. For example, the integration of artificial intelligence (AI) and machine learning (ML) into organizations’ infrastructure and offerings introduces security and privacy complexities, making it all the more essential for financial organizations to safeguard sensitive information while complying with regulations.
Building Gen AI with MongoDB & AI Partners | December 2024
Now that 2024 is behind us, we can see clearly how much change, innovation, and progress there was across the AI landscape in 2024. For MongoDB, the year was particularly marked by collaboration with our AI partners, and by the possibilities that AI collaboration holds; as the saying goes, it takes a village. From the release of breakthrough tools and frameworks, to AI-enriched workflows (for both prototyping and production), together we empowered customers and developers alike to build cutting-edge AI applications.
Building a Unified Data Platform for Gen AI
In today’s digital-first world, data is the lifeblood of innovation and decision-making. Yet, businesses often find themselves constrained by outdated and fragmented systems that fail to meet the demands of a fast-paced, interconnected landscape. Legacy architectures—such as the 1970s-era mainframes still used in industries like banking—create inefficiencies, siloed data, and operational bottlenecks, leaving organizations struggling to deliver timely, actionable insights.
AI-Powered Retail With Together AI and MongoDB
Generative AI (gen AI) is changing retail in fascinating ways. It’s providing new avenues for IT leaders at retailers to enhance customer experiences, streamline operations, and grow revenue in a fast-paced environment. Recently, we’ve been working closely with a fascinating organization in this space—Together AI. In this blog, we’ll explore how Together AI and MongoDB Atlas tremendously accelerated the adoption of gen AI by combining the capabilities of both platforms to bring high-impact retail use cases to life.
Using Agentic RAG to Transform Retail With MongoDB
In the competitive world of retail and ecommerce, it’s more important than ever for brands to connect with customers in meaningful, personalized ways. Shoppers today expect relevant recommendations, instant support, and unique experiences that feel tailored just for them.
Building Gen AI with MongoDB & AI Partners | November 2024
Unless you’ve been living under a rock, you know it’s that time of year again—re:Invent season! Last week, I was in Las Vegas for AWS re:Invent, one of our industry’s most important annual conferences. re:Invent 2024 was a whirlwind of keynote speeches, inspirational panels and talks, and myriad ways to spend time with colleagues and partners alike.
AI-Powered Call Centers: A New Era of Customer Service
Customer satisfaction is critical for insurance companies. Studies have shown that companies with superior customer experiences consistently outperform their peers. In fact, McKinsey found that life and property/casualty insurers with superior customer experiences saw a significant 20% and 65% increase in Total Shareholder Return, respectively, over five years.
Better Digital Banking Experiences with AI and MongoDB
Interactive banking represents a new era in financial services where customers engage with digital platforms that anticipate, understand, and meet their needs in real-time. This approach encompasses AI-driven technologies such as chatbots, virtual assistants, and predictive analytics that allow banks to enhance digital self-service while delivering personalized, context-aware interactions.
MongoDB, Microsoft Team Up to Enhance Copilot in VS Code
As modern applications grow increasingly complex, developers face the challenge of meeting market demands for faster, smarter solutions. To stay ahead, they need tools that streamline their workflows, available directly in the environments where they build. According to the 2024 Stack Overflow Developer Survey, Microsoft’s Visual Studio Code (VS Code) is the integrated development environment (IDE) of choice for 74% of professional developers, serving as a central hub for building, testing, and deploying applications. With the rise of AI-powered tools like GitHub Copilot—which is used by 44% of professional developers—there’s a growing demand for intelligent assistance in the development process without disrupting flow.
Building Gen AI with MongoDB & AI Partners | October 2024
It’s no surprise that AI is a topic of seemingly every professional conversation and meeting nowadays—my friends joke that 11 out of 10 words that come out of my mouth are “gen AI.” But an important question remains: do organizations truly know how to harness AI, or do they simply feel pressured to join the crowd? Are they driven by FOMO more than anything else?
Reflections On Our Recent AI "Think-A-Thon"
Interesting ideas are bound to emerge when great minds come together, so there was no shortage of interesting ideas on October 2nd, when MongoDB’s Developer Relations team hosted our second-ever AI Build Together event at MongoDB.local London.
Gamuda Puts AI in Construction with MongoDB Atlas
Gamuda Berhad is a leading Malaysian engineering and construction company with operations across the world, including in Australia, Taiwan, Singapore, Vietnam, the United Kingdom, and more. The company is known for its innovative approach to construction through the use of cutting-edge technology.
Built With MongoDB: Buzzy Makes AI Application Development More Accessible
AI adoption rates are sky-high and showing no signs of slowing down. One of the driving forces behind this explosive growth is the increasing popularity of low- and no-code development tools that make this transformative technology more accessible to tech novices. Buzzy, an AI-powered no-code platform that aims to revolutionize how applications are created, is one such company. Buzzy enables anyone to transform an idea into a fully functional, scalable web or mobile application in minutes.
Announcing Hybrid Search Support for LlamaIndex
MongoDB is excited to announce enhancements to our LlamaIndex integration. By combining MongoDB’s robust database capabilities with LlamaIndex’s innovative framework for context-augmented large language models (LLMs), the enhanced MongoDB-LlamaIndex integration unlocks new possibilities for generative AI development.
From Chaos to Control: Real-Time Data Analytics for Airlines
Delays are a significant challenge for the airline industry. They disrupt travel plans, erode customer loyalty, and inflict significant financial losses. In an industry built on precision and punctuality, even minor setbacks can have cascading effects. Whether due to adverse weather conditions or unforeseen technical issues, these delays ripple through flight schedules, affecting both passengers and operations managers. While neither group is typically at fault, the ability to quickly reallocate resources and return to normal operations is crucial.
Building Gen AI with MongoDB & AI Partners | September 2024
Last week I was in London for MongoDB.local London—the 19th stop of the 2024 MongoDB.local tour—where MongoDB, our customers, and our AI partners came together to share solutions we’ve been building that enable companies to accelerate their AI journey. I love attending these events because they offer an opportunity to celebrate our collective achievements, and because it’s great to meet so many (mainly Zoom) friends in person!
Introducing Two MongoDB Generative AI Learning Badges
Want to boost your resume quickly? MongoDB is introducing two new Learning Badges, Building gen AI Apps and Deploying and Evaluating gen AI Apps. Unlike high-stakes certifications, which cover a large breadth and depth of subjects, these digital credentials are focused on specific topics, making them easier and quicker to earn. Best of all, they’re free!
Revolutionizing Sales with AI: Glyphic AI’s Journey with MongoDB
When connecting with customers, sales teams often struggle to understand and address the unique needs and preferences of each prospect, leading to ineffective pitches. Additionally, time-consuming admin tasks like data entry, sales tool updates, follow-up management, and maintaining personalized interactions across numerous leads can overwhelm teams, leaving less time for impactful selling.
Ahamove Rides Vietnam’s E-commerce Boom with AI on MongoDB
The energy in Vietnam’s cities is frenetic as millions of people navigate the busy streets with determination and purpose. Much of this traffic is driven by e-commerce, with food and parcel deliveries perched on the back of the country’s countless motorcycles or in cars and trucks. In the first quarter of 2024, online spending in Vietnam grew a staggering 79% over the previous year. Explosive growth like this is expected to continue, raising the industry’s value to $32 billion by 2025, with 70% of the country’s 100 million population making e-commerce transactions.
AI Agents, Hybrid Search, and Indexing with LangChain and MongoDB
Since we announced integration with LangChain last year, MongoDB has been building out tooling to help developers create advanced AI applications with LangChain. With recent releases, MongoDB has made it easier to develop agentic AI applications (with a LangGraph integration), perform hybrid search by combining Atlas Search and Atlas Vector Search, and ingest large-scale documents more effectively.
Building Gen AI with MongoDB & AI Partners | August 2024
As the AI landscape continues to evolve, companies, industries, and developers seek tailored solutions to their unique challenges. Gone are the days when general-purpose AI models could be applied universally. Now, organizations are looking for industry-specific applications, verticalized AI solutions, and specialized tools to gain a competitive edge and best serve their customers. And as gen AI use cases have diversified—from healthcare diagnostics and autonomous driving, to personalized recommendations and creative content generation—so has the technology stack supporting them.
Elevate Your Java Applications with MongoDB and Spring AI
MongoDB is excited to announce an integration with Spring AI, enhancing MongoDB Atlas Vector Search for Java developers. This collaboration brings Vector Search to Java applications, making it easier to build intelligent, high-performance AI applications.
Better Business Loans with MongoDB and Generative AI
Business loans are a cornerstone of banking operations, providing significant benefits to both financial institutions and broader economies. For example, in 2023 the value of commercial and industrial loans in the United States reached nearly $2.8 trillion. However, these loans can present unique challenges and risks that banks must navigate. Besides credit risk, where the borrower may default, banks also face business risk, in which economic downturns or sector-specific declines can impact borrowers' ability to repay loans.
Find Hidden Insights in Vector Databases: Semantic Clustering
Vector databases, a powerful class of databases designed to optimize the storage, processing, and retrieval of large volume, multi-dimensional data, have increasingly been instrumental to generative AI (gen AI) applications, with Forrester predicted a 200% increase in the adoption of vector databases in 2024. But their power extends far beyond these applications. Semantic vector clustering, a technique within vector databases, can unlock hidden knowledge within your organization’s data, democratizing insights across teams. View the tutorial to get started.
Building Gen AI with MongoDB & AI Partners | July 2024
My colleague Richmond Alake recently published an article about the evolution of the AI stack that breaks down the “comprehensive collection of integrated tools, solutions, and components designed to streamline the development and management of AI applications.”
How MongoDB Scales CoPilot AI’s Humanized Sales Interactions
In a world where sales and marketing are the engines behind many tech companies’ growth in a highly competitive landscape, it’s more important than ever that those functions find better and fresher ways to implement personalization into campaigns, sales pitches, and everything in between to reach more customers. CoPilot AI has been at the helm of helping businesses do just that through their AI-powered sales enablement tool, automating personalized interactions to achieve revenue growth, all with the help of MongoDB.
Enhancing Retail with Retrieval-Augmented Generation (RAG)
In the rapidly evolving retail landscape, tech innovations are reshaping how businesses operate and interact with customers. Generative AI could add up to $275 billion of profit to the apparel, fashion, and luxury sectors’ by 2028, according to McKinsey analysis. One of the most promising developments in this realm is retrieval-augmented generation (RAG), a powerful application of artificial intelligence (AI) that combines the strength of data retrieval with generative capabilities to supercharge retail enterprises.
Building Gen AI Applications Using Iguazio and MongoDB
AI can lead to major enterprise advancements and productivity gains. By offering new capabilities, they open up opportunities for enhancing customer engagement, content creation, process automation, and more.
The Converged AI and Application Datastore for Insurance
In the inherently information-driven insurance industry, companies ingest, analyze, and process massive amounts of data, requiring extensive decision-making. To manage this, they rely on a myriad of technologies and IT support staff to keep operations running smoothly but often lack effectiveness due to their outdated nature.
Anti-Money Laundering and Fraud Prevention With MongoDB Vector Search and OpenAI
Fraud and anti-money laundering (AML) are major concerns for both businesses and consumers, affecting sectors like financial services and e-commerce. Traditional methods of tackling these issues, including static, rule-based systems and predictive artificial intelligence (AI) methods, work but have limitations, such as lack of context and feature engineering overheads to keeping the models relevant, which can be time-consuming and costly.
Building Gen AI with MongoDB & AI Partners | June 2024
Even for those of us who work in AI, keeping up with the latest news in the AI space can be head-spinning. In just the last few weeks, OpenAI introduced their newest model (GPT-4o), Anthropic continued to develop Claude with the launch of Claude 3.5 Sonnet, and Mistral launched Mixtral 8x22B, their most efficient open model to date. And those are only a handful of recent releases!
AI Apps: What the World Sees vs. What Developers See
Imagine you’re in the market for a new home in, say, Atlanta. And you’re on vacation in a different city. You see an amazing-looking house, whose design you love. You open up your favorite real estate app, snap a picture of this house, and type: “Find me a home that looks like this in Atlanta, in my price range, and within my budget, that’s also next to a park.” Seconds later, you’re served a list of homes that not only resemble this one, but match all your other specifications.
Building Gen AI-Powered Predictive Maintenance with MongoDB
In today’s fast-evolving industrial landscape, digital transformation has become a necessity. From manufacturing plants to connected vehicles, the push towards predictive maintenance excellence is driving organizations to embrace smarter, more efficient ways of managing operations. One of the most compelling advancements in this domain is predictive maintenance powered by generative AI, a cutting-edge approach that will revolutionize how industries maintain and optimize their equipment.
MongoDB Atlas Once Again Voted Most Loved Vector Database
The 2024 Retool State of AI report has just been released, and for the second year in a row, MongoDB Atlas was named the most loved vector database. Atlas Vector Search received the highest net promoter score (NPS), a measure of how likely a user is to recommend a solution to their peers.
Transforming Predictive Maintenance with AI: Real-Time Audio-Based Diagnostics with Atlas Vector Search
Wind turbines are a critical component in the shift away from fossil fuels toward more sustainable, green sources of energy. According to the International Energy Agency (IEA), the global capacity of wind energy has been growing rapidly, reaching over 743 gigawatts by 2023. Wind energy, in particular, has one of the greatest potentials to increase countries' renewable capacity growth. Solar PV and wind additions are forecast to more than double by 2028 compared with 2022, continuously breaking records over the forecast period.
Search PDFs at Scale with MongoDB and Nomic
Data is only valuable if it’s accessible. For example, storing photos, audio files, or PDFs without the ability to extract information from them is like keeping junk in your basement, thinking you might need it someday. The problem is finding what you need to dig through your junk when the day comes.
Building AI with MongoDB: Conversation Intelligence with Observe.AI
What's really happening in your business? The answer to that question lies in the millions of interactions between your customers and your brand. If you could listen in on every one of them, you'd know exactly what was up--and down. You’d also be able to continuously improve customer service by coaching agents when needed. However, the reality is that most companies have visibility in only 2% of their customer interactions. Observe.AI is here to change that. The company is focused on being the fastest way to boost contact center performance with live conversation intelligence.
Building AI With MongoDB: Integrating Vector Search And Cohere to Build Frontier Enterprise Apps
Cohere is the leading enterprise AI platform, building large language models (LLMs) which help businesses unlock the potential of their data. Operating at the frontier of AI, Cohere’s models provide a more intuitive way for users to retrieve, summarize, and generate complex information.
Transforming Industries with MongoDB and AI: Healthcare
This is the sixth in a six-part series focusing on critical AI use cases across several industries. The series covers the manufacturing and motion, financial services, retail, telecommunications and media, insurance, and healthcare industries.
Retrieval Augmented Generation for Claim Processing: Combining MongoDB Atlas Vector Search and Large Language Models
Following up on our previous blog, AI, Vectors, and the Future of Claims Processing: Why Insurance Needs to Understand The Power of Vector Databases, we’ll pick up the conversation right where we left it. We discussed extensively how Atlas Vector Search can benefit the claim process in insurance and briefly covered Retrieval Augmented Generation (RAG) and Large Language Models (LLMs).
Transforming Industries with MongoDB and AI: Insurance
This is the fifth in a six-part series focusing on critical AI use cases across several industries. The series covers the manufacturing and motion, financial services, retail, telecommunications and media, insurance, and healthcare industries.
Transforming Industries with MongoDB and AI: Financial Services
This is the fourth in a six-part series focusing on critical AI use cases across several industries. The series covers the manufacturing and motion, financial services, retail, telecommunications and media, insurance, and healthcare industries.
Transforming Industries with MongoDB and AI: Retail
This is the third in a six-part series focusing on critical AI use cases across several industries. The series covers the manufacturing and motion, financial services, retail, telecommunications and media, insurance, and healthcare industries.
Fireworks AI and MongoDB: The Fastest AI Apps with the Best Models, Powered By Your Data
We’re happy to announce that Fireworks AI and MongoDB are now partnering to make innovating with generative AI faster, more efficient, and more secure. Fireworks AI was founded in late 2022 by industry veterans from Meta’s PyTorch team, where they focused on performance optimization, improving the developer experience, and running AI apps at scale.
Building AI With MongoDB: How DevRev is Redefining CRM for Product-Led Growth
OneCRM from DevRev is purpose-built for Software-as-a-Service (SaaS) companies. It brings together previously separate customer relationship management (CRM) suites for product management, support, and software development. Built on a foundation of customizable large language models (LLMs), data engineering, analytics, and MongoDB Atlas, it connects end users, sellers, support, product owners, and developers. OneCRM converges multiple discrete business apps and teams onto a common platform.
Transforming Industries with MongoDB and AI: Telecommunications and Media
This is the second in a six-part series focusing on critical AI use cases across the manufacturing and motion, financial services, retail, telecommunications and media, insurance, and healthcare industries. Read part one here.
Transforming Industries with MongoDB and AI: Manufacturing and Motion
This is the first in a six-part series focusing on critical AI use cases across several industries. The series covers the manufacturing and motion, financial services, retail, telecommunications and media, insurance, and healthcare industries.
Building AI With MongoDB: How GoBots AI for E-commerce Increases Retailer Sales Conversion by 40%
Major retail brands have long been using various forms of AI, for example statistical analysis and machine learning models, to better serve their customers. But with its high barriers to entry, one key channel has been slower to embrace the technology. By connecting large and small brands with customers, e-commerce marketplaces such as Amazon, Mercado Libre, and Shopify are among the fastest growing retail routes to market. Since 2016, GoBots has been working to extend the benefits of AI to any retailer on any marketplace. It uses AI, analytics, and MongoDB Atlas to make e-commerce easier, more convenient, and smarter for brands serving Latin America.
Building AI with MongoDB: Accelerating App Development With the Codeium AI Toolkit
Of the many use cases set to be transformed by generative AI (gen AI), the bleeding edge of this revolution is underway with software development. Developers are using gen AI to improve productivity by writing higher-quality code faster. Tasks include autocompleting code, writing docs, generating tests, and answering natural language queries across a code base. How does this translate to adoption? A recent survey showed 44% of new code being committed was written by an AI code assistant.
Together AI: Advancing the Frontier of AI With Open Source Embeddings, Inference, and MongoDB Atlas
Founded in San Francisco in 2022, Together AI is on a mission to create the fastest cloud platform for building and running generative AI (gen AI). The company has so far raised over $120 million, counting Nvidia, Kleiner Perkins, Lux, and NEA as investors.
Building AI with MongoDB: Putting Jina AI’s Breakthrough Open Source Embedding Model To Work
Founded in 2020 and based in Berlin, Germany, Jina AI has swiftly risen as a leader in multimodal AI, focusing on prompt engineering and embedding models. With its commitment to open-source and open research, Jina AI is bridging the gap between advanced AI theory and the real world AI-powered applications being built by developers and data scientists. Over 400,000 users are registered to use the Jina AI platform.
Building AI with MongoDB: Navigating the Path From Predictive to Generative AI
It should come as no surprise that the organizations unlocking the largest benefits from generative AI (gen AI) today have already been using predictive AI (a.k.a. classic, traditional, or analytical AI). McKinsey made this same observation back in June 2023 with its “Economic Potential of Generative AI1” research.
Building AI with MongoDB: How Flagler Health's AI-Powered Journey is Revolutionizing Patient Care
Flagler Health is dedicated to supporting patients with chronic diseases by matching them with the right physician for the right care. Typically, patients grappling with severe pain conditions face limited options, often relying on prolonged opioid use or exploring costly and invasive surgical interventions. Unfortunately, the latter approach is not only expensive but also has a long recovery period. Flagler finds these patients and triages them to the appropriate specialist for an advanced and comprehensive evaluation.
DocsGPT: Migrating One of the Industry’s Most Popular Open Source AI Assistants to Atlas Vector Search
Since its founding in 2019, Arc53 has focused on building predictive AI/ML solutions for its clients, with use cases ranging from recommendation engines to fraud detection. But it was with OpenAI’s launch of ChatGPT in November 2022 that the company saw AI rapidly take a new direction.
Spotlight on Two Aussie Start-Ups Building AI Services on MongoDB Atlas
Australian-based Eclipse AI and Pending AI are using the power of MongoDB Atlas to bring their AI ideas to life and blaze new trails in fields including pharmaceutical R&D and customer retention.
Building AI with MongoDB: How Patronus Automates LLM Evaluation to Boost Confidence in GenAI
It is hardly headline news that large language models can be unreliable. For some use cases, this can be inconvenient. For others — especially in regulated industries — the consequences are way more severe. Enter Patronus AI, the industry-first automated evaluation platform for LLMs.
Building AI With MongoDB: How Gradient Accelerator Blocks Take You From Zero To AI in Seconds
Founded by the former leaders of AI teams at Google, Netflix, and Splunk, Gradient enables businesses to create high-performing, cost-effective custom AI applications.
Building AI with MongoDB: How Devnagri Brings the Internet to 1.3 Billion People with Machine Translations
It was while on a trip to Japan that Himanshu Sharma — later to become CEO of Devnagri — made an observation that drew parallels with his native India. Despite the majority of Japan’s population not speaking English, they were still well served by an internet that was largely based on the English language. Key to doing this was translation, and specifically the early days of automated machine translation. And so the idea to found Devnagri, India’s first AI-powered translation platform, was born.
A Discussion with VISO TRUST: Expanding Atlas Vector Search to Provide Better-Informed Risk Decisions
We recently caught up with the team at VISO TRUST to check in and learn more about their use of MongoDB and their evolving search needs (if you missed our first story, read more about VISO TRUST’s AI use cases with MongoDB on our first blog).
Powering Vector Search Maturity in Retail with Pureinsights
In a competitive retail market, with customer demands higher than ever, retailers are on a constant journey toward search maturity. With the recent announcement of MongoDB’s Vector Search offering, retailers are implementing smarter search solutions to provide customers and staff with delightful experiences. Here we’ll explore how partners like Pureinsights are helping retailers to understand what true search maturity entails, and how to start their vector search journey on MongoDB Atlas.
Data Governance for Building Generative AI Applications with MongoDB
Generative AI (GenAI) has been evolving at a rapid pace. With the introduction of OpenAI’s ChatGPT powered by GPT-3.5 reaching 100 million monthly active users in just two months, other major large language models (LLMs) have followed in ChatGPT's footsteps. Cohere’s LLM supports more than 100 languages and is now available on their AI platform, Google’s Med-PaLM was designed to provide high-quality answers to medical questions, OpenAI introduced GPT-4 (a 40% improvement over GPT-3.5), Microsoft integrated GPT-4 within its Office 365 suite, and Amazon introduced Bedrock, a fully managed service that makes foundation models available via API. These are just a few advancements in the Generative AI market, and a lot of enterprises and startups are adopting AI tools to solve their specific use cases. The developer community and open-source models are also growing as companies adapt to the new technology paradigm shift in the market.
Building AI With MongoDB: Optimizing the Product Lifecycle with Real-Time Customer Data
Over the course of our Building AI with MongoDB blog post series, we’ve seen many organizations using AI to shape product development and support. Examples we’ve profiled so far include:
Building AI with MongoDB: Retrieval-Augmented Generation (RAG) Puts Power in Developers’ Hands
As recently as 12 months ago, any mention of retrieval-augmented generation (RAG) would have left most of us confused. However, with the explosion of generative AI, the RAG architectural pattern has now firmly established itself in the enterprise landscape.
Building AI with MongoDB: Giving Your Apps a Voice
In previous posts in this series, we covered how generative AI and MongoDB are being used to unlock value from data of any modality and in supercharging communications. Put those topics together, and we can start to harness the most powerful communications medium (arguably!) of them all: Voice.
Supercharging Edge-to-Cloud Strategy
The emergence of Big Data and the proliferation of AI/ML, is today more than ever, pushing enterprises' digital strategies to adopt more sophisticated systems that help them become data-driven organizations. This said the constant dependency on legacy systems makes it difficult for many enterprises to even access their edge data and make use of it in time to make operational/business decisions.
Building AI with MongoDB: Supercharging Three Communication Paradigms
Communication mediums are core to who we are as humans, from understanding each other to creating bonds and a shared purpose. The methods of communication have evolved over thousands of years, from cave drawings and scriptures to now being able to connect with anyone at any time via internet-enabled devices. The latest paradigm shift to supercharge communication is through the use and application of natural language processing and artificial intelligence.
AI, Vectors, and the Future of Claims Processing: Why Insurance Needs to Understand The Power of Vector Databases
We’re just under a year since OpenAI released ChatGPT, unleashing a wave of hype, investment, and media frenzy around the potential of generative AI to transform how we do business and interact with the world. But while the majority of the investment dollars and media attention zeroed in on the disruptive capabilities of large language models (LLMs), there’s a crucial component underpinning this breakthrough technology that hasn’t received the attention it deserves; the humble vector database.
Building AI with MongoDB: Unlocking Value from Multimodal Data
One of the most powerful capabilities of AI is its ability to learn, interpret, and create from input data of any shape and modality. This could be structured records stored in a database to unstructured text, computer code, video, images, and audio streams.
Building AI with MongoDB: From Compliance to Copilots
There has been a lot of recent reporting on the desire to regulate AI. But very little has been made of how AI itself can assist with regulatory compliance. In our latest round-up of qualifiers for the MongoDB AI Innovators Program, we feature a company who are doing just that in one of the world’s most heavily regulated industries.
Powerful Generative AI Innovation Accelerates Discovery of New Molecules
Since 2018, MongoDB and Google Cloud have collaborated to revolutionize the way companies interact with their data, providing an unrivaled experience in Google Cloud regions around the world through a strategic partnership. By delivering MongoDB's popular modern database and deep integrations with Google's data cloud to customers, the two companies are empowering businesses to create applications at scale with unprecedented data richness, all available through the Google Cloud Marketplace. This strategic partnership is bearing fruit. In the chemical industry, for example, users are now combining AI and data mining techniques using MongoDB Atlas with Google Clouds Foundation Models to accelerate the discovery of new molecules and make the process more environmentally friendly.
Building AI with MongoDB: Announcing the First Qualifiers for the Innovators Program
Artificial Intelligence is igniting so many brilliant ideas for new products and services. But turning those ideas into reality is a path that even the brightest minds struggle to navigate without some help along the way. That’s why we launched the MongoDB AI Innovators Program back in June this year. Access to expert technical advice, free MongoDB Atlas credits, co-marketing opportunities, and – for eligible startups, introductions to potential venture investors – come together to help you “build the next big thing” in AI.
Amplifying Retail Operations with Generative AI and Vector Search: The Unexplored Potential
In the hyper-competitive world of retail, industry leaders are continually looking for new ways to revolutionize the customer experience and optimize operations. That's where generative AI and vector search come into play. Both offer transformative potential in myriad retail use cases, from personalized marketing campaigns to efficient inventory management, making them indispensable for those aiming to stay at the industry's cutting edge.
MongoDB Partners with NCS to Drive Transformation for ASEAN Businesses and Build Innovative AI Tools
MongoDB, the modern database, has partnered with NCS, the market leader in IT services in Singapore and Southeast Asia*, to help drive digital transformation for some of APAC's largest enterprises. NCS's team has also used MongoDB Atlas to build an ultra-accurate and ultra-fast speech recognition tool.
Leveraging MongoDB to Build Cutting-Edge AI Solutions
Generative AI is captivating businesses and experts as the technology landscape rapidly evolves, paving the way for groundbreaking advancements in fields such as natural language processing, and strategic business problem-solving. AI foundation models like GPT-4 are expected to transform work dynamics, potentially impacting 40% of working hours. The extraordinary promise of AI has not gone unnoticed, as investors show significant interest in companies engaging in this cutting-edge technology.