Resources

Enhance Developer Agility and AI-Readiness with MongoDB Atlas on Azure

Our recent webinar, “Enhance Developer Agility and AI-Readiness with MongoDB Atlas on Azure,” is now available on demand. In this webinar, we discuss how MongoDB Atlas on Azure helps you reduce complexity and build on a unified database platform. Hear directly from the experts at MongoDB and Microsoft, plus watch until the end for a highly engaging question-and-answer session.

Watch presentation →

Automate Regulatory Compliance with Advanced AI and MongoDB

Our recent webinar, “Automate Regulatory Compliance with Advanced AI and MongoDB,” is now available on demand. In this webinar, we discuss how to use cutting-edge AI technologies and MongoDB's powerful database capabilities to create an AI-powered compliance monitoring system. Hear directly from the experts at MongoDB and our partner ADA, plus watch until the end for a highly engaging question-and-answer session.

Watch presentation →

AI Database Comparison: MongoDB vs. PostgreSQL and Pgvector

Large language models (LLMs) are rapidly reshaping how we build AI solutions. The database technology you choose to power these applications can significantly impact the performance, scalability, and success of your AI application. In this webinar, Staff Developer Advocate Richmond Alake compares two vector search solutions—PostgreSQL with pgvector and MongoDB Atlas Vector Search—and guides you through selecting the right option for your AI workloads. Whether you’re a data engineer, AI architect, or developer, you’ll understand how to think about and optimize critical metrics like latency and throughput to meet the demands of modern AI applications. What you’ll learn: How retrieval-augmented generation (RAG) boosts LLM-based applications by integrating external data in real time. How PostgreSQL/pgvector and MongoDB Atlas handle high-performance vector operations for tasks like semantic search and recommendation engines. How robust vector databases enable AI agents to reason, plan, and act autonomously, creating truly dynamic and interactive AI experiences. How a real-world application using a financial Q&A dataset illustrates practical deployment and optimization strategies. How key metrics like latency and throughput directly affect the success of LLM applications.

Watch presentation →

Intro to Memory Management in AI Agents

AI agents go beyond retrieval-augmented generation (RAG) to transform how intelligent systems learn, adapt — and remember. So managing how agents store, recall, and process remembered data is essential to delivering seamless, hyper-personalized, and context-rich interactions. Watch MongoDB Staff Developer Advocate Richmond Alake for this engaging webinar. It will equip you with the knowledge and practical tools to integrate advanced memory systems into your projects. We’ll break down key concepts and practical techniques to ensure your agents remember what matters, adapt to new information, and behave in ways that truly resonate with users. What You’ll Learn: How agentic RAG extends traditional RAG by integrating memory management into agent workflows. The essentials of memory management — how to design, build, and evolve an agent’s memory. The core components and building blocks of effective AI memory. RAG techniques and hybrid search approaches that combine lexical and vector methods for fast and accurate AI retrieval. Practical strategies for implementing memory management using MongoDB’s flexible document model, robust indexing, and native vector search capabilities.

Watch presentation →

Scaling Vector Database Operations with MongoDB and Voyage AI

The performance and scalability of your AI application depend on efficient vector storage and retrieval. In this webinar, we explore how MongoDB Atlas Vector Search and Voyage AI embeddings optimize these aspects through quantization—a technique that reduces the precision of vector embeddings (e.g., float32 to int8) to decrease storage costs and improve query performance while managing accuracy trade-offs. Vector embeddings are the foundation of AI-driven applications, along with powerful capabilities such as retrieval-augmented generation (RAG), semantic search, and agent-based workflows. However, as data volumes grow, the cost and complexity of storing and querying high-dimensional vectors increase. Senior Staff Developer Advocate Anant Srivastava covered practical strategies for converting embeddings to lower-bit representations, balancing performance with accuracy. In a step-by-step tutorial, he shows you how to apply these optimizations using Voyage AI embeddings to reduce both query latency and infrastructure costs. Key Takeaways: How quantization works to dramatically reduce the memory footprint of embeddings How MongoDB Atlas Vector Search integrates automatic quantization to efficiently manage millions of vector embeddings Real-world metrics for retrieval latency, resource utilization, and accuracy across float32, int8, and binary embeddings Combining binary quantization with a rescoring step yields near float32-level accuracy with a fraction of the computational overhead Best practices and tips for balancing speed, cost, and precision—especially at the 1M+ embedding scale essential for RAG, semantic search, and recommendation systems

Watch presentation →

Adopting AI-Driven Transformation with MongoDB, Capgemini and AWS

Our recent webinar, “Adopting AI-Driven Transformation with MongoDB, AWS, and Capgemini,” is now available on demand. In this webinar, presenters from MongoDB, AWS, and Capgemini discuss an AI-powered integration enhances customer engagement, streamlines operations, and drives growth across industries. Watch this webinar to learn how to: Seamlessly integrate AI-driven capabilities into operations and core applications. Move beyond legacy limitations and unify data across disparate, siloed systems. Accelerate application development and shrink time-to-market with prebuilt accelerators for industry-specific domains. Use AWS services, like Amazon Lex and AWS Lambda to enable personalized, scalable conversational AI across channels.

Watch presentation →

Building RAG Applications Using Multimodal Data

AI search must evolve beyond text-only approaches to handle the diverse, multimodal content found across the internet. To build truly effective retrieval-augmented generation (RAG) applications, you need strategies that process text, images, tables, and figures seamlessly. In this on-demand session, MongoDB Senior AI Developer Advocate Apoorva Joshi explores advanced techniques for integrating multimodal data into your RAG pipelines. Watch the session to learn: Multimodal embedding techniques for diverse data formats (text, images, tables, and figures) How Voyage AI's multimodal embedding models differ from competitors and drive more accurate retrievals Using Vision Language Models (VLMs) as an alternative to traditional chunking approaches Comparative evaluation of Voyage multimodal models against other solutions for mixed-modality data Advanced strategies for exploring and retrieving from multimodal datasets Discover how MongoDB and Voyage AI empower AI applications to retrieve and process information across multiple modalities. Watch now to take your multimodal AI search to the next level!

Watch presentation →

AI Database Comparison: MongoDB Atlas vs. Elasticsearch

Large language models (LLMs) are revolutionizing AI application development, from retrieval-augmented generation (RAG) to intelligent agentic systems that dynamically reason, learn, and adapt. The AI ecosystem offers a range of technologies to build these solutions—but one of the most critical elements is the database. In generative AI applications, your database directly impacts response latency, application performance, and output accuracy. This session compares two solutions for vector data storage, indexing, and retrieval: MongoDB Atlas and Elasticsearch. We break down how each handles semantic search, provide performance insights, and walk through best practices for implementing vector search in MongoDB Atlas. Watch MongoDB Staff Developer Advocate Richmond Alake as he guides you through: Common search patterns in AI workloads with concrete examples and detailed performance guidance for MongoDB Atlas Vector Search. Why database architecture matters in generative AI, illustrated through real-world implementation scenarios that showcase developer productivity and application capabilities. How to implement MongoDB Atlas Vector Search step-by-step, with live coding demonstrations that show how to enable semantic search for powerful RAG solutions through a unified developer experience. Practical walkthrough of building complete RAG pipelines that integrate real-time data, with working code examples you can adapt for your own dynamic LLM-driven applications. Actionable best practices for optimizing MongoDB Atlas for AI workloads, including live demonstrations of index configuration, efficient query patterns, and practical scaling strategies. Whether you're building AI chatbots, recommendation engines, or agentic systems, understanding how your database powers LLM-enabled applications is essential. Watch now to gain practical knowledge and working code examples that will help you design and optimize AI-powered solutions with MongoDB Atlas.

Watch presentation →

Application Modernisation: From Relational to NoSQL with Relational Migrator

We've heard time and time again that applications running on legacy relational databases cause technical and business pain, but there is a fear that modernizing them is too difficult and risky. MongoDB’s Relational Migrator significantly reduces the effort and risk of moving to a modern data architecture. In addition to data migration, it helps you model your schemas efficiently in MongoDB, update application code, and even convert existing code with the help of AI. The webinar will be presented by Cathlon Lau, Advisory Solutions Architect at MongoDB, who has decades of experience working with RDBMS, PostgreSQL, and document databases like MongoDB. Register now and find out why it’s essential to consider database platforms specifically designed to handle large, complex data structures to effectively support modern AI applications and learn how MongoDB’s Relational Migrator can significantly reduce the effort and risk of transitioning to a modern data architecture.

Watch presentation →

Intro to AI Agents and Agentic Systems

During this session, Staff Developer Advocate Richmond Alake explored the transformative impact of AI agents and agentic systems, providing invaluable insights and hands-on examples to help you build powerful AI-driven applications. Key topics included: Constructing AI Agents powered by LLMs Developing agentic systems for complex workflows Interacting with databases, including querying MongoDB Connecting to external tools and retrieving real-time data Optimizing systems for scalability and performance The webinar also featured an engaging question-and-answer session, where MongoDB experts shared guidance, offered pro tips, and discussed best practices for leveraging these emerging technologies.

Watch presentation →

Better Digital Banking Experiences through AI-Driven Interactions Powered by MongoDB

Interactive banking is revolutionizing the financial services industry by leveraging AI-driven technologies to create more intuitive, personalized, and efficient customer interactions. Whether you're already implementing AI solutions or just beginning your journey, this webinar will guide you in enhancing your digital banking experience using MongoDB. Watch this webinar where Wei You Pan, Financial Services Industry Principal at MongoDB explores how MongoDB's capabilities can empower you to build future-proof applications and upgrade business applications with features shaping the industry. Gain valuable insights that will help you to: Enhance self-service banking: Discover how AI-driven advisors can streamline customer interactions, providing instant, context-aware solutions Understand how MongoDB's flexible data model works seamlessly with leading AI frameworks, allowing you to integrate and scale quickly and efficiently Leverage MongoDB Atlas Vector Search capabilities to enable the AI to find precise answers within dense documents, enhancing the self-service experience Build AI-powered apps with MongoDB to analyze customer trends, prevent fraud, and deliver smarter financial services like budgeting and conversational banking Don't miss your chance to dive deep into the future of digital banking and see how MongoDB can empower you to build next-gen solutions.

Watch presentation →

Build AI-Ready Data Architectures with MongoDB and Hasura

“This is where we'll start to gain an appreciation for how Promptql is able to build with 100% accuracy. It's the supergraph layer. And this is the powerful thing that creates these experiences, and really the only reason that something like Promptql is able to be 100% accurate.” “We now have a reliable way to query the backend data source. We're not feeding things into AI—we're taking information and querying, using optimized queries.” “And this is where the benefit of taking an agentic approach comes in. By using a python runtime in collaboration with an LLM of your choice, you're starting to use a best of breed approach in exactly the same way that a human would run some of these queries.” — Adam Malone, Director of Worldwide Solutions Engineering for Hasura If you missed our webinar about building AI-Ready data architectures with Hasura and MongoDB—or just want to catch up on some of the key moments—the session is now available on-demand. Adam Malone, Director of Worldwide Solutions Engineering for Hasura and Sigfrido Narvaez, Executive Solutions Architect for MongoDB shared many key insights for developers to consider when designing AI-ready Architectures. Watch it now for a deep dive into AI-ready infrastructure followed by an equally technical question-and-answer period. Watch it on-demand now.

Watch presentation →