MongoDB Builder Blog
Deep dives into technical concepts, architectures, and innovations with MongoDB.
Beyond Benchmarks: Selecting the Best Architecture for Vector Search In Production Workloads
Vector search needs more than similarity matching. AI engineering now demands context and memory engineering with complex infrastructure requirements. At a moderate scale (under 10 million vectors), the performance differences between well-tuned algorithm implementations are often marginal, because index configuration, hardware, and memory allocation tend to matter more than algorithm choice (ANN-Benchmarks). The performance gap between specialized and general-purpose databases has largely closed at moderate scale. The best vector database for production is usually the one that already holds the rest of your data.
Evolving APIs with Confidence at MongoDB Atlas
Delivering a great API experience requires more than just exposing functionality. It requires a consistent design and a scalable process for ongoing improvement. With teams relying more heavily on automation and programmatic integrations, the way an API is designed can make the difference between workflows that “just work” and workflows that are fragile or surprising. For MongoDB Atlas, our unified data platform, the programmatic interface is the Atlas Administration API. This API provides developers with programmatic access to the features across the Atlas platform to deploy, manage, and scale their databases in the cloud.
From Prompt to Production: MongoDB Atlas for Agentic Dev
Vibe coding and LLM-generated code have emerged as a new way for developers to build code. This trend is expected to accelerate over the next few years. With tools like GitHub Copilot, Claude Code, Emergent, Base44, Codex, and other Agentic coding platforms, we're moving into a new era of software development. Instead of just writing code line-by-line, we're guiding, prompting, and iterating with AI partners. According to the Stack Overflow 2025 Survey, 51% of professional developers use AI tools daily.
Why Every AI Workflow Is Really a Data Problem in Disguise
88% of enterprises are using AI in at least one business function. Fewer than 10% are seeing meaningful business impact. That gap isn't explained by model selection. It isn't explained by prompt quality. It's explained by what's underneath.
The Case Against Building Your Own Agent Platform
You know the meeting. The board wants an AI agent strategy by the end of the quarter. Someone on the leadership team has read a McKinsey report. You've been voluntold to build the platform. The slide deck says "AI-native." The acceptance criteria are vague. Somebody mentions LangGraph, and somebody else says, "We'll just wrap it ourselves."
Modernizing Enterprise Content Management with MongoDB
Enterprise Content Management (ECM) is mission-critical to almost every large organization. It underpins how contracts are signed, invoices are archived, citizen records are retained, and how billions of documents are searched and governed every day. Yet most ECM platforms still run on architectures designed decades ago, struggling to keep up with today’s scale, agility, and AI expectations.
Fighting Tool Sprawl: The Case for AI Tool Registries
As enterprise AI agent adoption scales, the absence of centralized, organization-level tool infrastructure is producing compounding costs. When adoption is built around optimizing for deployment speed, enterprises expose themselves to a combination of risks: duplicated engineering effort, security exposure, and operational opacity.
The 5 MongoDB Atlas Alerts You Should Actually Pay Attention To
MongoDB Atlas ships with a large set of built-in alerts, but many teams turn them on without being fully clear on what each one is actually telling them. The result is predictable: either alert fatigue or missed signals.
MoE & Shared Embedding Spaces: How Voyage-4 Scales Smarter
In the relentless race to build more powerful AI, the standard playbook has been simple: bigger is better. To make a model smarter, we’ve historically just made it larger by adding more layers, more neurons, and more parameters. But this dense approach hits a massive wall. If you scale a model to trillions of parameters, and every single one has to fire for every single token, you end up with a system that is prohibitively slow and expensive.
3 Lightbulb Moments for Performant Data Modeling and Indexing
When you begin your MongoDB journey, don't be surprised if it takes a few steps along the path before you’re struck by the power and flexibility of the document model. The real leaps in query performance and scalability happen when developers move beyond traditional relational thinking and start designing their data model to match their application’s access patterns.
How Columnar Storage in Time Series Collection Delivers Real Cost Savings
A sensor measuring temperatures once a second generates 86,400 readings each day. Normally, every reading is stored in a full document structure even when the temperature changes by a tenth of a degree, or the loss value shifts by 0.001. But for time series workloads—whether IoT sensors or AI training pipelines—it's quietly expensive. And it gets worse the more data you retain.
Breaking the Dense Ceiling: How voyage-4-large Uses MoE to Scale
Efficient scaling of embedding models has been a core research focus of Voyage AI by MongoDB: Rather than simply scaling up, we aim to improve the quality-cost trade-off—extending the Pareto frontier beyond what is possible with standard architectures. In the Voyage 3.5 series, we pushed the scaling trends of traditional dense embedding models to their practical limits. To further push the Pareto frontier, we introduced a mixture-of-experts (MoE) architecture in voyage-4-large.
Reduce AI Hallucinations with Tavily and MongoDB Hybrid Search
Artificial intelligence applications increasingly rely on retrieval‑augmented generation (RAG) to keep large language models grounded in trusted information. But not all RAG systems are created equal. Many rely solely on internal databases, while others depend exclusively on external APIs. Both approaches can introduce hallucinations, outdated information, or limited control over content sources.
Enhance Your In-IDE Data Browsing Experience With MongoDB
MongoDB is excited to announce the general availability of our enhanced data browsing experience in the MongoDB for Visual Studio (VS) Code extension. This new experience offers a unified workspace for developers to visually browse, query, and edit their data natively, streamlining workflows so they can manage their database right where they write their code. Evolving the developer workflow The modern developer’s workflow is incredibly fast-paced. With developers juggling an average of 14 different tools daily, the cognitive load of constantly jumping between applications can easily disrupt focus. When your application needs to evolve, working with your data shouldn’t force a break in your flow state. As the MongoDB for VS Code extension has grown to nearly 3 million downloads, we’ve seen firsthand how developers are pushing the boundaries of what an in-IDE (integrated development environment) database tool can do. While developers love accessing their data directly in the editor, we wanted to transform this experience to be even more visual, actionable, and seamless. Instead of switching to external terminals for quick tasks or taking the time to translate familiar MongoDB Shell commands into Extended JSON (EJSON), we are bringing a full-fledged, intuitive data management suite right to your VS Code sidebar. Exploring what’s new in the MongoDB for VS Code extension Here are the key improvements that transform the extension into a complete workflow solution: Paginated tree view and prescriptive titles Understanding complex data models at a glance is crucial for rapid development. We are transforming the document browsing experience by automatically detecting human-readable fields (like names or emails) to create prescriptive document titles, rather than just displaying standard _id hashes. Furthermore, you can now use a structured, paginated tree view to instantly browse collection data from the “Documents” tab, as well as interactively explore playground results when you run a script. This means you get the full context of your collections visually and instantly. Figure 1. Paginated tree view and prescriptive titles Powerful action menus and header controls Navigating your data should be inherently actionable. To give you full management capabilities without the need for you to write manual queries, we’ve added a new action header directly inside the tree view. This header equips you with buttons to instantly insert documents, refresh (to rerun the current query or playground script), sort ascending/descending by _id, paginate through results, and even bulk delete to empty a collection. Additionally, managing individual records is easier than ever. Simply hover over any document within the tree view to reveal a contextual action menu that allows you to instantly delete, copy, clone, and edit the document natively. Figure 2. Native action menus Native editing and shell syntax default We wanted to make interacting with your database as natural as possible. To remove the friction of translating your commands, we’ve added a setting that defaults to standard Shell syntax over EJSON for all insert, clone, edit, and clipboard functionalities. This guarantees that any document you copy or any quick fix you make in the extension is instantly compatible with your application code. Figure 3. Clone action. Stop context switching and start building Your database tools should adapt to your workflow, not disrupt it. By bringing native data editing, intelligent tree views, and standard Shell syntax directly into your sidebar, we’re bridging the gap between writing code and managing data. You no longer have to sacrifice your flow state just to make a quick database fix, verify a playground result, or translate verbose EJSON formats. This overhaul is another step in our commitment to making this MongoDB extension your ultimate command center—empowering you to spend less time wrestling with external tools and more time actually building your application.
Why MongoDB Atlas is the Native Home for ISO 20022 Compliance
For decades, global financial institutions relied on messaging standards defined by SWIFT to exchange information about cross-border payments. These legacy standards—aka MT messages designed in the 1970s—carried payment instructions in largely unstructured formats that required downstream systems to interpret free-text fields.
Modelence: A Complete Platform for Agentic App Development
As modern applications become increasingly data-driven and AI-powered, development teams face a growing challenge: how to move quickly from idea to production without stitching together multiple tools, managing complex infrastructure, or reinventing backend workflows. Modelence offers a new approach. It is a full‑stack, AI‑native development platform that brings together every core component needed to build, run, and scale modern applications in one unified system. Whether teams want to start a new project using a traditional development workflow or prefer a vibe‑coding approach powered by its AI-native App Builder, Modelence supports both seamlessly. To show you how this works in practice, we have included two examples for each workflow that you can explore in more detail later in this blog.
Automotive After Sales Diagnostics Using GraphRAG and Multimodal AI
Modern vehicles act as distributed computing systems and generate terabytes of telemetry. However, the majority of after-sales diagnostic and repair workflows still depend on static documentation and basic keyword search. In 2025, J.D. Power reported that 12% of repairs are not completed correctly on the first visit.1 These repeat repairs increase costs, reduce workshop throughput, and erode customer trust.
High vs Low Ingestion: A Practical Study of MongoDB Time Series Bucket Behavior
Time series data captures any signal, metric, or observation whose state changes continuously over time. Infrastructure metrics, IoT sensor readings, financial market data, observability signals, and distributed system telemetry all qualify. What they share is the need to record an ordered sequence of measurements efficiently.
db.youtube.insert(): Our Developer YouTube Channel is Officially Live
If you’ve spent any time learning MongoDB on YouTube, you’ve likely visited our main channel. It’s been the hub for all video content—from company news and keynote highlights to the tutorials that help you get your first cluster up and running.
Port Mapping for Google Private Service Connect on MongoDB Atlas
For organizations leveraging MongoDB Atlas on Google Cloud, network architecture is a critical component of performance and scalability. Today, we are excited to announce a significant architectural enhancement that simplifies the connection between these two platforms. This new feature, Port Mapping for Private Service Connect (PSC), reduces developer efforts and enables faster scaling by streamlining connection management and resource allocation.