Artificial Intelligence
Building AI-powered Apps with MongoDB
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. Cohere offers both text generation and embedding models to its customers. Enterprises running mission-critical AI workloads select Cohere because its models offer the best performance-cost tradeoff and can be deployed in production at scale. Cohere’s platform is cloud-agnostic. Their models are accessible through their own API as well as popular cloud managed services, and can be deployed on a virtual private cloud (VPC) or even on-prem to meet companies where their data is, offering the highest levels of flexibility and control. Cohere’s leading Embed 3 and Rerank 3 models can be used with MongoDB Atlas Vector Search to convert MongoDB data to vectors and build a state-of-the-art semantic search system. Search results also can be passed to Cohere’s Command R family of models for retrieval augmented generation (RAG) with citations. Check out our AI resource page to learn more about building AI-powered apps with MongoDB. A new approach to vector embeddings It is in the realm of embedding where Cohere has made a host of recent advances. Described as “AI for language understanding,” Embed is Cohere’s leading text representation language model. Cohere offers both English and multilingual embedding models, and gives users the ability to specify the type of data they are computing an embedding for (e.g., search document, search query). The result is embeddings that improve the accuracy of search results for traditional enterprise search or retrieval-augmented generation. One challenge developers faced using Embed was that documents had to be passed one by one to the model endpoint, limiting throughput when dealing with larger data sets. To address that challenge and improve developer experience, Cohere has recently announced its new Embed Jobs endpoint . Now entire data sets can be passed in one operation to the model, and embedded outputs can be more easily ingested back into your storage systems. Additionally, with only a few lines of code, Rerank 3 can be added at the final stage of search systems to improve accuracy. It also works across 100+ languages and offers uniquely high accuracy on complex data such as JSON, code, and tabular structure. This is particularly useful for developers who rely on legacy dense retrieval systems. Demonstrating how developers can exploit this new endpoint, we have published the How to use Cohere embeddings and rerank modules with MongoDB Atlas tutorial . Readers will learn how to store, index, and search the embeddings from Cohere. They will also learn how to use the Cohere Rerank model to provide a powerful semantic boost to the quality of keyword and vector search results. Figure 1: Illustrating the embedding generation and search workflow shown in the tutorial Why MongoDB Atlas and Cohere? MongoDB Atlas provides a proven OLTP database handling high read and write throughput backed by transactional guarantees. Pairing these capabilities with Cohere’s batch embeddings is massively valuable to developers building sophisticated gen AI apps. Developers can be confident that Atlas Vector Search will handle high scale vector ingestion, making embeddings immediately available for accurate and reliable semantic search and RAG. Increasing the speed of experimentation, developers and data scientists can configure separate vector search indexes side by side to compare the performance of different parameters used in the creation of vector embeddings. In addition to batch embeddings, Atlas Triggers can also be used to embed new or updated source content in real time, as illustrated in the Cohere workflow shown in Figure 2. Figure 2: MongoDB Atlas Vector Search supports Cohere’s batch and real time workflows. (Image courtesy of Cohere) Supporting both batch and real-time embeddings from Cohere makes MongoDB Atlas well suited to highly dynamic gen AI-powered apps that need to be grounded in live, operational data. Developers can use MongoDB’s expressive query API to pre-filter query predicates against metadata, making it much faster to access and retrieve the more relevant vector embeddings. The unification and synchronization of source application data, metadata, and vector embeddings in a single platform, accessed by a single API, makes building gen AI apps faster, with lower cost and complexity. Those apps can be layered on top of the secure, resilient, and mature MongoDB Atlas developer data platform that is used today by over 45,000 customers spanning startups to enterprises and governments handling mission-critical workloads. What's next? To start your journey into gen AI and Atlas Vector Search, review our 10-minute Learning Byte . In the video, you’ll learn about use cases, benefits, and how to get started using Atlas Vector Search.
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. In healthcare, transforming data into actionable insights is vital for enhancing clinical outcomes and advancing patient care. From medical professionals improving care delivery to administrators optimizing workflows and researchers advancing knowledge, data is the lifeblood of the healthcare ecosystem. Today, AI emerges as a pivotal technology, with the potential to enhance decision-making, improve patient experiences, and streamline operations — and to do so more efficiently than traditional systems. Patient experience and engagement While they may not expect it based on past experiences, patients crave a seamless experience with healthcare providers. Ideally, patient data from healthcare services, including telehealth platforms, patient portals, wearable devices, and EHR, can be shared – securely – across interoperable channels. Unfortunately, disparate data sources, burdensome and time-consuming administrative work for providers, and overly complex and bloated solution stacks at the health system level all stand in the way of that friction-free experience. AI can synthesize vast amounts of data and provide actionable insights, leading to personalized and proactive patient care, automated administrative processes, and real-time health insights. AI technologies, such as machine learning algorithms, natural language processing, and chatbots, are being used to enhance and quantify interactions. Additionally, AI-powered systems can automatically schedule appointments, send notifications, and optimize clinic schedules, all reducing wait times for patients. AI-enabled chatbots and virtual health assistants provide 24/7 support, offering instant responses, medication reminders, and personalized health education. AI can even identify trends and predict health events, allowing for early intervention and reduction in adverse outcomes. MongoDB’s flexible data model can unify disparate data sources, providing a single view of the patient that integrates EHRs, wearable data, and patient-generated health data for personalized care and better patient outcomes. For wearables and medical devices, MongoDB is the ideal underlying data platform to house time series data, significantly cutting down on storage costs while enhancing performance. With Atlas for the Edge, synchronization with edge applications, including hospital-at-home setups, becomes seamless. On the patient care front, MongoDB can support AI-driven recommendations for personalized patient education and engagement based on the analysis of individual health records and engagement patterns, and Vector Search can power search functionalities within patient portals, allowing patients to easily find relevant information and resources, thereby improving the self-service experience. Enhanced clinical decision making Healthcare decision-making is critically dependent on the ability to aggregate, analyze, and act on an exponentially growing volume of data. From EHRs and imaging studies to genomic data and wearable device data, the challenge is not just the sheer volume but the diversity and complexity of data. Healthcare professionals need to synthesize information across various dimensions to make informed, real-time, accurate decisions. Interoperability issues, data silos, lack of data quality, and the manual effort required to integrate and interpret this data all stand in the way of better decision-making processes. The advent of AI technologies, particularly NLP and LLMs, offers transformative potential for healthcare decision-making by automating the extraction and analysis of data from disparate sources, including structured data in EHRs and unstructured text in medical literature or patient notes. By enabling the querying of databases using natural language, clinicians can access and integrate patient information more rapidly and accurately, enhancing diagnostic precision and personalizing treatment approaches. Moreover, AI can support real-time decision-making by analyzing streaming data from wearable devices, alerting healthcare providers to changes in patient conditions that require immediate attention. MongoDB, with its flexible data model and powerful data development platform, is uniquely positioned to support the complex data needs of healthcare decision-making applications. It can seamlessly integrate diverse data types, from FHIR-formatted clinical data to unstructured text and real-time sensor data, in a single platform. By integrating MongoDB with Large Language Models (LLMs), healthcare organizations can create intuitive, AI-enhanced interfaces for data retrieval and analysis. This integration not only reduces the cognitive load on clinicians but also enables them to access and interpret patient data more efficiently, focusing their efforts on patient care rather than navigating complex data systems. MongoDB's scalability ensures that healthcare organizations can manage growing data volumes efficiently, supporting the implementation of AI-driven decision support systems. These systems analyze patient data in real-time against extensive medical knowledge bases, providing clinicians with actionable insights and recommendations, thereby enhancing the quality and timeliness of care provided. MongoDB's Vector Search further enriches decision-making processes by enabling semantic search across vast datasets directly within the database. This integrated approach enables the application of pre-filters based on extensive metadata, enhancing the efficiency and relevance of search results without the need to synchronize with dedicated search engines or vector stores, meaning healthcare professionals can utilize previously undiscoverable insights, streamlining the identification of relevant information and patterns. Clinical trials and precision medicine The need for innovation and transformation isn’t just limited to the patient-provider-healthcare system experience. The challenges of conducting clinical trials and advancing precision medicine are significant, from identifying and enrolling suitable participants to data management practices are fraught with the potential for errors, compromising the accuracy and reliability of trial outcomes. Moreover, the traditional one-size-fits-all approach to treatment development fails to address the unique genetic makeup of individual patients, limiting the effectiveness of therapeutic interventions. AI can make clinical trials faster and treatments more personalized. It's like having a super-smart assistant that can quickly find the right people for studies, keep track of all the data without making mistakes, and even predict which medicines will work best for different people. This means doctors can create safe, efficient treatments that fit you perfectly, just like a tailor-made suit. Plus, with AI's help, these custom treatments can be developed quicker and be more affordable, bringing us closer to a future where everyone gets the care they need, designed just for them. It's a big step towards making medicine not just about treating sickness but about creating health plans that are as unique as patients are. MongoDB plays a pivotal role in modernizing clinical trials and advancing precision medicine by addressing complex data challenges. Its flexible data model excels in integrating diverse data types, from EHRs and genomic data to real-time patient monitoring streams. This capability is crucial for clinical trials and precision medicine, where combining various data sources is necessary, sometimes through a project purpose ODL, to develop a comprehensive understanding of patient health and treatment responses. For clinical trials, MongoDB can streamline participant selection by efficiently managing and querying vast datasets to identify candidates who meet specific criteria, significantly reducing the recruitment time. Its ability to handle large-scale, complex datasets in real-time also facilitates the dynamic monitoring of trial participants, enhancing the safety and accuracy of trials. Other notable use cases Patient Flow Optimization and Emergency Department Efficiency: AI algorithms can process historical and real-time data to forecast patient volumes, predict bed availability, and identify optimal staffing levels, enabling proactive resource allocation and patient routing. Virtual Health Assistants for Chronic Disease Management: Utilizing AI-powered virtual assistants to monitor patients' health status, provide personalized advice, and support medication adherence for chronic conditions such as diabetes and hypertension. AI-Enhanced Digital Pathology and Medical Imaging: Build modern VNA (Vendor Neutral Archive and Digital pathology solutions with innovative approaches, dealing with interoperable data, and manage extensive metadata associated with all your resources enabling fast findings and automated annotations. Operational Efficiency in Hospital Resource Management: Implementing AI to optimize hospital operations, from staff scheduling to inventory management, ensuring resources are used efficiently and patient care is prioritized. Learn more about AI use cases for top industries in our new ebook, How Leading Industries are Transforming with AI and MongoDB Atlas .
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). MongoDB.local NYC Join us in person on May 2, 2024 for our keynote address, announcements, and technical sessions to help you build and deploy mission-critical applications at scale. Use Code Web50 for 50% off your ticket! Learn More One of the biggest challenges for claim adjusters is pulling and aggregating information from disparate systems and diverse data formats. PDFs of policy guidelines might be stored in a content-sharing platform, customer information locked in a legacy CRM, and claim-related pictures and voice reports in yet another tool. All of this data is not just fragmented across siloed sources and hard to find but also in formats that have been historically nearly impossible to index with traditional methods. Over the years, insurance companies have accumulated terabytes of unstructured data in their data stores but have failed to capitalize on the possibility of accessing and leveraging it to uncover business insights, deliver better customer experiences, and streamline operations. Some of our customers even admit they’re not fully aware of all the data in their archives. There’s a tremendous opportunity to leverage this unstructured data to benefit the insurer and its customers. Our image search post covered part of the solution to these challenges, opening the door to working more easily with unstructured data. RAG takes it a step further, integrating Atlas Vector Search and LLMs, thus allowing insurers to go beyond the limitations of baseline foundational models, making them context-aware by feeding them proprietary data. Figure 1 shows how the interaction works in practice: through a chat prompt, we can ask questions to the system, and the LLM returns answers to the user and shows what references it used to retrieve the information contained in the response. Great! We’ve got a nice UI, but how can we build an RAG application? Let’s open the hood and see what’s in it! Figure 1: UI of the claim adjuster RAG-powered chatbot Architecture and flow Before we start building our application, we need to ensure that our data is easily accessible and in one secure place. Operational Data Layers (ODLs) are the recommended pattern for wrangling data to create single views. This post walks the reader through the process of modernizing insurance data models with Relational Migrator, helping insurers migrate off legacy systems to create ODLs. Once the data is organized in our MongoDB collections and ready to be consumed, we can start architecting our solution. Building upon the schema developed in the image search post , we augment our documents by adding a few fields that will allow adjusters to ask more complex questions about the data and solve harder business challenges, such as resolving a claim in a fraction of the time with increased accuracy. Figure 2 shows the resulting document with two highlighted fields, “claimDescription” and its vector representation, “claimDescriptionEmbedding” . We can now create a Vector Search index on this array, a key step to facilitate retrieving the information fed to the LLM. Figure 2: document schema of the claim collection, the highlighted fields are used to retrieve the data that will be passed as context to the LLM Having prepared our data, building the RAG interaction is straightforward; refer to this GitHub repository for the implementation details. Here, we’ll just discuss the high-level architecture and the data flow, as shown in Figure 3 below: The user enters the prompt, a question in natural language. The prompt is vectorized and sent to Atlas Vector Search; similar documents are retrieved. The prompt and the retrieved documents are passed to the LLM as context. The LLM produces an answer to the user (in natural language), considering the context and the prompt. Figure 3: RAG architecture and interaction flow It is important to note how the semantics of the question are preserved throughout the different steps. The reference to “adverse weather” related accidents in the prompt is captured and passed to Atlas Vector Search, which surfaces claim documents whose claim description relates to similar concepts (e.g., rain) without needing to mention them explicitly. Finally, the LLM consumes the relevant documents to produce a context-aware question referencing rain, hail, and fire, as we’d expect based on the user's initial question. So what? To sum it all up, what’s the benefit of combining Atlas Vector Search and LLMs in a Claim Processing RAG application? Speed and accuracy: Having the data centrally organized and ready to be consumed by LLMs, adjusters can find all the necessary information in a fraction of the time. Flexibility: LLMs can answer a wide spectrum of questions, meaning applications require less upfront system design. There is no need to build custom APIs for each piece of information you’re trying to retrieve; just ask the LLM to do it for you. Natural interaction: Applications can be interrogated in plain English without programming skills or system training. Data accessibility: Insurers can finally leverage and explore unstructured data that was previously hard to access. Not just claim processing The same data model and architecture can serve additional personas and use cases within the organization: Customer Service: Operators can quickly pull customer data and answer complex questions without navigating different systems. For example, “Summarize this customer's past interactions,” “What coverages does this customer have?” or “What coverages can I recommend to this customer?” Customer self-service: Simplify your members’ experience by enabling them to ask questions themselves. For example, “My apartment is flooded. Am I covered?” or “How long do windshield repairs take on average?” Underwriting: Underwriters can quickly aggregate and summarize information, providing quotes in a fraction of the time. For example, “Summarize this customer claim history.” “I Am renewing a customer policy. What are the customer's current coverages? Pull everything related to the policy entity/customer. I need to get baseline info. Find relevant underwriting guidelines.” If you would like to discover more about Converged AI and Application Data Stores with MongoDB, take a look at the following resources: RAG for claim processing GitHub repository From Relational Databases to AI: An Insurance Data Modernization Journey Modernize your insurance data models with MongoDB and Relational Migrator
VertexAI and MongoDB for Intelligent Retail Pricing
In today’s competitive retail environment, the ability to quickly adjust pricing in response to market trends, consumer demand, and competitors’ moves is not just an advantage — it's essential for survival. This is where dynamic pricing comes into play, serving as a strategic tool for businesses to pull in their quest for market dominance. Dynamic pricing goes beyond changing numbers; it’s a strategic approach that reflects the dynamic nature of the market, powered by data-driven insights that enable prices to be adjusted in real-time for maximum effectiveness. This shift towards a more agile, data-driven pricing strategy underscores a broader trend in the business world: the recognition of data as a foundational element in decision-making processes. By leveraging real-time data, businesses can ensure their pricing strategies are not only responsive to market fluctuations but also strategically aligned with their overall business objectives, thus driving retail competitiveness to new heights. Let’s uncover how integrating both platforms empowers developers when it comes to delivering best-in-class, data-driven applications. MongoDB.local NYC Join us in person on May 2, 2024 for our keynote address, announcements, and technical sessions to help you build and deploy mission-critical applications at scale. Use Code Web50 for 50% off your ticket! Learn More Google Cloud: A platform for real-time analytics and AI Google Cloud stands out as a powerhouse in real-time analytics and artificial intelligence (AI), offering the infrastructure necessary for dynamic pricing strategies and other data-driven business approaches. It's designed to facilitate big data analysis, machine learning, and operational agility. Built-in tools form the backbone of an effective dynamic pricing strategy. These include Vertex AI for advanced machine learning models following best- in- class MLOps practices, and Pub/Sub for real-time messaging to solve real- time data ingestion. By harnessing the power of Google Cloud, retailers can analyze vast quantities of data in real-time, from current market trends to customer behavior and competitor pricing. This enables businesses to make informed decisions swiftly, adjusting their pricing strategies to reflect the ever-changing market conditions. MongoDB: Flexible data modeling and rapid application development MongoDB complements Google Cloud by offering a high performance document- based database with a flexible data model that allows rapid application development. For pricing data in particular, where there may be different variants for different sizes of store or country, the flexibility allows for the ease of storage of complex or hierarchical data. In addition, polymorphic capabilities allow you to use a single interface to represent different types, making your system more flexible. It also supports scalability as new types can be easily integrated. Lastly, it enhances efficiency by allowing the same operation to behave differently based on the object, reducing code redundancy. This flexible schema also enables seamless integration with AI models. MongoDB Atlas supports workload isolation , ensuring dedicated resources for AI tasks and smooth operation alongside core application workloads. Additionally, change streams and triggers can be utilized to capture real-time updates in the pricing data, allowing the AI model to be called upon for immediate analysis and adaptation and enabling in-app analytics for retailers to gain a competitive edge. Figure 1: MongoDB replica set: Workload Isolation In the dynamic pricing reference architecture, Atlas collections function as an ML feature store. By leveraging the capabilities of MongoDB Atlas as a developer data platform, we are able to embed real-time automated decision-making into our e-commerce applications and reduce operational overhead for both business operations and MLOps model fine-tuning. This is achieved through implementing a streamlined approach to data management, incorporating real-time, automated decision making, workload isolation, change streams, triggers for immediate updates, and seamless integration with AI models. Dynamic prising microservice overview Building an event-driven AI architecture leveraging MongoDB Atlas in Google Cloud is straightforward. We can summarize our dynamic pricing microservice by first describing the different components of its architecture, what they are used for, and how they interact with each other: Figure 2: Description of the different technology components of a dynamic pricing microservice and what they are used for. Handling data sources The proposed solution uses Google Cloud Pub/Sub to ingest data sources like customer behavior events in JSON format. Using a technology like Pub/Sub allows for scaling to handle a large number of messages and efficiently distribute them to many subscribers. This is partly because it allows for parallel processing of messages and can be distributed across multiple servers or instances. It is often a fundamental pattern in event-driven architectures, where the flow of the program is determined by events or messages, supporting reactive programming and making the system more responsive and efficient. Data federation We’ll use Vertex AI Notebooks to clean the data and train a TensorFlow model. This model will learn the non-linear relation between customer events, products names, and prices, enabling it to calculate the optimal predicted price. Orchestrating Using Cloud Functions, we orchestrate the customer events coming from the Pub/Sub topic to be converted into tensors, which are then stored in a MongoDB Atlas collection. This collection acts as a feature store serving as a centralized repository designed to store, manage, and serve features for machine learning (ML) models. Features represent individual measurable properties or characteristics used by ML models to make predictions or decisions. MongoDB’s document model flexibility paired with the document versioning pattern will allow us to design time-sensitive chunks of events and granularly manage the training datasets for our models. Serving The Cloud Function will use the event tensor to invoke our trained model that is served in a Vertex AI endpoint. The model will provide a predicted price score that can then be inserted into our product catalog stored in MongoDB so our e-commerce application can read the price change in real time. Dynamic pricing architecture: Putting it all together In the following architecture diagram, the blue data flow illustrates how customer event data is ingested into a Pub/Sub topic. This allows us to make a push subscription to a Cloud Function from the topic. This function orchestrates the data transformation from raw event into a tensor and calls an endpoint to then update the predicted price into our MongoDB product catalog collection. By using this architectural approach, we can isolate raw events threads and build different services around them, reacting in real time for dynamic pricing or asynchronously for model training. With every component loosely coupled, we prevent the system from crashing completely. Moreover, publishers and subscribers can continue to process their logic without the need for the other components to receive or publish messages. Figure 3: Dynamic pricing architecture integrating different Google Cloud components and MongoDB Atlas as a Feature Store For businesses, this translates into more precise and responsive pricing strategies. In the model building and optimization phase, by utilizing TensorFlow within Google Cloud Vertex AI notebooks, retailers can harness the power of deep learning capabilities. The neural network model is capable of analyzing intricate patterns and relationships within large datasets. This is how businesses may capture nuanced market dynamics, customer behavior, and pricing elasticity with greater accuracy, leading to more optimized pricing decisions. But even the best of the models should be consistently optimized. Maintaining model effectiveness requires continuous adaptation. Regularly evaluating accuracy and performing feature engineering ensures your models stay sensitive to market changes. This underscores the importance of retraining as a core principle in a continuous improvement data science approach. Using MongoDB Atlas as your operational data layer means that your feature store is always accessible, reducing downtime and improving the efficiency of machine learning operations. On the other hand, cross-region deployments can bring features closer to where machine learning models are being trained or served, reducing latency and improving model performance. Get started The integration of Google Cloud and MongoDB presents an easy approach to modernizing dynamic pricing strategies. Leveraging real-time analytics, flexible data modeling, and reactive microservices architecture, it empowers businesses to achieve operational efficiencies and gain a competitive advantage in their pricing strategies. For retailers looking to elevate their pricing strategies, considering a strategic partnership with both technologies is essential. For a deeper dive into integrating the different components of this architecture, make sure to check our GitHub repository. Check out our AI resource page to learn more about building AI-powered apps with MongoDB.
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. With its ability to streamline processes, enhance decision-making, and improve customer experiences in far less time, resources, and staff than traditional IT systems, artificial intelligence offers insurers great promise. In an inherently information-driven industry, insurance companies ingest, analyze, and process massive amounts of data. Whether it’s agents and brokers selling more policies, underwriters adequately pricing, renewing and steering product portfolios, claim handlers adjudicating claims, or service representatives providing assurance and support, data is at the heart of it all. Given the volumes of data, and the amount of decision-making that needs to occur based on it, insurance companies have a myriad of technologies and IT support staff within their technology investment portfolios. It’s no surprise that AI is at the top of the list when it comes to current or prospective IT investments. With its ability to streamline processes, enhance decision-making, and improve customer experiences with far less time, resources, and staff than traditional IT systems, AI offers insurers great promise. Underwriting & risk management Few roles within insurance are as important as that of the underwriters who strike the right balance between profit and risk, bring real-world variables to the actuarial models at the heart of the insurer, and help steer product portfolios, markets, pricing, and coverages. Achieving equilibrium between exposures and premiums means constantly gathering and analyzing information from a myriad of sources to build a risk profile sufficient and detailed enough to make effective policy decisions. While many well-established insurers have access to a wealth of their own underwriting and claims experience data, integrating newer and real-time sources of information, keeping up with regulatory changes, and modeling out what-if risk scenarios still involve significant manual effort. Perhaps the single greatest advantage of AI will be its ability to quickly analyze more information with fewer people and resources. The long-term impact will likely be profound, and there is tremendous promise within underwriting. Advanced analytics: Traditional IT systems are slow to respond to changing formats and requirements surrounding data retrieval. The burden falls on the underwriter to summarize data and turn that into information and insight. Large Language Models are now being leveraged to help speed up the process of wrangling data sources and summarizing the results, helping underwriting teams make quicker decisions from that data. Workload and triage assistance: AI models are mitigating seasonal demands, market shifts, and even staff availability that impact the workload and productivity of underwriting teams, saving underwriting time for high-value accounts and customers where their expertise is truly needed. Amid high volumes for new and renewal underwriting, traditional AI models can help classify and triage risk, sending very low-risk policies to ‘touchless’ automated workflows, low to moderate risk to trained service center staff, and high-risk and high-value accounts to dedicated underwriters. Decision-making support: Determining if a quoted rate needs adjustment before binding and issuing can take significant time and manual effort. So can preparing and issuing renewals of existing policies, another large portion of the underwriters’ day-to-day responsibilities. Automated underwriting workflows leveraging AI are being employed to analyze and classify risk with far less manual effort. This frees up significant time and intellectual capital for the underwriter. Check out our machine learning solutions page to learn more about automated digital underwriting. Vast amounts of data analyzed by underwriters are kept on the underwriter's desktop rather than IT-managed databases. MongoDB offers an unparalleled ability to store data from a vast amount of sources and formats and deliver the ability to respond quickly to requests to ingest new data. As data and requirements change, the Document Model allows insurers to simply add more data and fields without the costly change cycle associated with databases that rely on single, fixed structures. For every major business entity found within the underwriting process, such as a broker, policy, account, and claim, there is a wealth of unstructured data sources, waiting to be leveraged by generative AI. MongoDB offers insurers a platform that consolidates complex data from legacy systems, builds new applications, and extends those same data assets to AI-augmented workflows. By eliminating the need for niche databases for these AI-specific workloads, MongoDB reduces technology evaluation and onboarding time, development time, and developer friction. Claim processing Efficient claim processing is critical for an insurer. Timely resolution of a claim and good communication and information transparency throughout the process is key to maintaining positive relationships and customer satisfaction. In addition, insurers are on the hook to pay and process claims according to jurisdictional regulations and requirements, which may include penalties for failing to comply with specific timelines and stipulations. To process a claim accurately, a wealth of information is needed. A typical automobile accident may include not only verbal and written descriptions from claimants and damage appraisers but also unstructured content from police reports, traffic and vehicle dashboard cameras, photos, and even vehicle telemetry data. Aligning the right technology and the right amount of your workforce in either single or multi-claimant scenarios is crucial to meeting the high demands of claim processing. Taming the flood of data: AI is helping insurers accelerate the process of making sense of a trove of data and allowing insurers to do so in real-time. From Natural Language Processing to image classification and vector embedding, all the pieces of the puzzle are now on the board for insurers to make a generation leap forward when it comes to transforming their IT systems and business workflows for faster information processing. Claims experience: Generating accurate impact assessments for catastrophic events in a timely fashion to inform the market of your exposure can now be done with far less time, and with far more accuracy, by cross-referencing real-time and historical claims experience data, thanks to the power of Generative AI and vector-embedding of unstructured data. Claim expediter: Using vector embeddings from photo, text, and voice sources, insurers are now able to decorate inbound claims with richer and more insightful metadata so that they can more quickly classify, triage, and route work. In addition, real-time insight into workload and staff skills and availability is allowing insurers to be even more prescriptive when it comes to work assignments, driving towards higher output and higher customer satisfaction. Litigation assistance: Claims details are not always black and white, parties do not always act in good faith, and insurers expend significant resources in the pursuit of resolving matters. AI is helping insurers drive to resolution faster and even avoid litigation and subrogation altogether, thanks to its ability to help us analyze more data more effectively and more quickly. Risk prevention: Many insurers provide risk-assessment services to customers using drones, sensors, or cameras, to capture and analyze data. This data offers the promise of preventing losses altogether for customers and lowering exposures, liability, and expenses for the insurer. This is possible thanks to a combination of vector-embedding, traditional, and generative AI models. Learn more about AI-enhanced claim adjustment for automotive insurance on our solutions page. Customer experience Accessing information consistently during a customer service interaction, and expecting the representative to quickly interpret it, are perennial challenges with any customer service desk. Add in the volume, variety, and complexity of information within insurance, and it’s easy to understand why many insurers are investing heavily in the transformation of their customer experience call center systems and processes. 24/7 virtual assistance: As with many AI-based chat agents, the advantage is that it can free up your call center staff to work on more complex and high-touch cases. Handling routine inquiries can now include far more complex scenarios than before, thanks to the power of vector-embedded content and Large Language Models. Claims assistance: Generative AI can deliver specific claim-handling guidelines to claim-handling staff in real time, while traditional ML models can interrogate real-time streams of collected information to alert either the customer or the claim-handler to issues with quality, content, or compliance. AI capabilities allow insurers to process more claims more quickly and significantly reduce errors or incomplete information. Customer profiles: Every interaction is an opportunity to learn more about your customers. Technologies such as voice-to-text streaming, vector embedding, and generative AI help insurers build out a more robust ‘social profile’ of their customers in near real-time. Real-time fraud detection: According to estimates from the Coalition Against Insurance Fraud , the U.S. insurance industry lost over $308 billion to fraud in 2022. With vector-embedding of unstructured data sources, semantic and similarity searches across both vector and structured metadata, and traditional machine learning models, insurers can detect and prevent fraud in ways that were simply not ever before possible. Other notable use cases Predictive Analytics: AI-powered predictive analytics can anticipate customer needs, preferences, and behaviors based on historical data and trends. By leveraging predictive models, insurers can identify at-risk customers, anticipate churn, and proactively engage with customers to prevent issues and enhance satisfaction. Crop Insurance and Precision Farming: AI is being used in agricultural insurance to assess crop health, predict yields, and mitigate risks associated with weather events and crop diseases, which helps insurers offer more accurate and tailored crop insurance products to farmers. Predictive Maintenance for Property Insurance: AI-powered predictive maintenance solutions, leveraging IoT sensors installed in buildings and infrastructure, are used in property insurance to prevent losses and minimize damage to insured properties. Usage-Based Insurance (UBI) for Commercial Fleets: AI-enabled telematics devices installed in commercial vehicles collect data on driving behavior, including speed, acceleration, braking, and location. Machine learning algorithms analyze this data to assess risk and determine insurance premiums for commercial fleets to help promote safer driving practices, reduce accidents, and lower insurance costs for businesses. Learn more about AI use cases for top industries in our new ebook, How Leading Industries are Transforming with AI and MongoDB Atlas. Read the full ebook here .
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. In the dynamic world of financial services, the partnership between artificial intelligence (AI) and banking services is reshaping traditional practices, offering innovative solutions across critical functions. MongoDB.local NYC Join us in person on May 2, 2024 for our keynote address, announcements, and technical sessions to help you build and deploy mission-critical applications at scale. Use Code Web50 for 50% off your ticket! Learn More Relationship management support with chatbots One key service that relationship managers provide to their private banking customers is aggregating and condensing information. Because banks typically operate on fragmented infrastructure with information spread across different departments, solutions, and applications, this can require a lot of detailed knowledge about this infrastructure and how to source information such as: When are the next coupon dates for bonds in the portfolio? What has been the cost of transactions for a given portfolio? What would be a summary of our latest research? Please generate a summary of my conversation with the client. Until now, these activities would be highly manual and exploratory. For example, a relationship manager (RM) looking for the next coupon dates would likely have to go into each of the clients' individual positions and manually look up the coupon dates. If this is a frequent enough activity, the RM could raise a request for change with the product manager of the portfolio management software to add this as a standardized report. But even if such a standardized report existed, the RM might struggle to find the report quickly. Overall, the process is time-consuming. Generative AI systems can facilitate such tasks. Even without specifically trained models, RAG can be used to have the AI generate the correct answers, provide the inquirer with a detailed explanation of how to get to the data, and, in the same cases directly execute the query against the system and report back the results. Similar to a human, it is critical that the algorithm has access to not only the primary business data, e.g. the portfolio data of the customer, but also user manuals and static data. Detailed customer data, in machine-readable format and as text documents, is used to personalize the output for the individual customer. In an interactive process, the RM can instruct the AI to add more information about specific topics, tweak the text, or make any other necessary changes. Ultimately, the RM will be the quality control for the AI’s output to mitigate hallucinations or information gaps. As outlined above, not only will the AI need highly heterogeneous data from highly structured portfolio information to text documents and system manuals to provide a flexible natural language interface for the RMs, it will also have to have timely processing information about a customer's transactions, positions, and investment objectives. Providing transactional database capabilities as well as vector search makes it easy to build RAG-based applications using MongoDB’s developer data platform. Risk management and regulatory compliance Risk and fraud prevention Banks are tasked with safeguarding customer assets and detecting fraud , verifying customer identities, supporting sanctions regimes (Sanctions), and preventing various illegal activities (AML). The challenge is magnified by the sheer volume and complexity of regulations, making the integration of new rules into bank infrastructure costly, time-consuming, and often inadequate. For instance, when the EU's Fifth Anti-Money Laundering Directive was implemented, it broadened regulations to cover virtual currencies and prepaid cards . Banks had to update their onboarding processes swiftly, and software, train staff, and possibly update their customer interfaces to comply with these new requirements. AI offers a transformative approach to fraud detection and risk management by automating the interpretation of regulations, supporting data cleansing, and enhancing the efficacy of surveillance systems. Unlike static, rules-based frameworks that may miss or misidentify fraud due to narrow scope or limited data, AI can adaptively learn and analyze vast datasets to identify suspicious activities more accurately. Machine learning, in particular, has shown promise in trade surveillance, offering a more dynamic and comprehensive approach to fraud prevention. Regulatory compliance and code change assistance The regulatory landscape for banks has grown increasingly complex, demanding significant resources for the implementation of numerous regulations. Traditionally, adapting to new regulations has required the manual translation of legal text into code, provisioning of data, and thorough quality control—a process that is both costly and time-consuming, often leading to incomplete or insufficient compliance. For instance, to comply with the Basel III international banking regulations , developers must undertake extensive coding changes to accommodate the requirements laid out in thousands of pages of documentation. AI has the capacity to revolutionize compliance by automating the translation of regulatory texts into actionable data requirements and validating compliance through intelligent analysis. This approach is not without its challenges, as AI-based systems may produce non-deterministic outcomes and unexpected errors. However, the ability to rapidly adapt to new regulations and provide detailed records of compliance processes can significantly enhance regulatory adherence. Financial document search and summarization Financial institutions, encompassing both retail banks and capital market firms, handle a broad spectrum of documents critical to their operations. Retail banks focus on contracts, policies, credit memos, underwriting documents, and regulatory filings, which are pivotal for daily banking services. On the other hand, capital market firms delve into company filings, transcripts, reports, and intricate data sets to grasp global market dynamics and risk assessments. These documents often arrive in unstructured formats, presenting challenges in efficiently locating and synthesizing the necessary information. While retail banks aim to streamline customer and internal operations, capital market firms prioritize the rapid and effective analysis of diverse data to inform their investment strategies. Both retail banks and capital market firms allocate considerable time to searching for and condensing information from documents internally, resulting in reduced direct engagement with their clients. Generative AI can streamline the process of finding and integrating information from documents by using NLP and machine learning to understand and summarize content. This reduces the need for manual searches, allowing bank staff to access relevant information more quickly. MongoDB can store vast amounts of both live and historical data, regardless of its format which is typically needed for AI applications. It offers Vector Search capabilities essential for retrieval-augmented generation (RAG). MongoDB supports transactions, ensuring data accuracy and consistency for AI model retraining with live data. It facilitates data access for both deterministic algorithms and AI-driven rules through a single interface. MongoDB boasts a strong partnership ecosystem , including companies like Radiant AI and Mistral AI, to speed solution development. ESG analysis Environmental, social, and governance (ESG) considerations can have a profound impact on organizations. For example, regulatory changes—especially in Europe—have compelled financial institutions to integrate ESG into investment and lending decisions. Regulations such as the EU Sustainable Finance Disclosure Regulation (SFDR) and the EU Taxonomy Regulation are examples of such directives that require financial institutions to consider environmental sustainability in their operations and investment products. Investors' demand for sustainable options has surged, leading to increased ESG-focused funds. The regulatory and commercial requirements, in turn, drive banks to also improve their green lending practices . This shift is strategic for financial institutions, attracting clients, managing risks, and creating long-term value. However, financial institutions face many challenges in managing different aspects of improving their ESG analysis. The key challenges include defining and aligning standards, and processes and managing the flood of rapidly changing and varied data to be included for ESG analysis purposes. AI can help to address these key challenges in not only an automatic but also adaptive manner via techniques like machine learning. Financial institutions and ESG solution providers have already leveraged AI to extract insights from corporate reports, social media, and environmental data, improving the accuracy and depth of ESG analysis. As the market demands a more sustainable and equitable society, predictive AI combined with generative AI can also help to reduce bias in lending to create fairer and more inclusive financing while improving the predictive powers. The power of AI can help facilitate the development of sophisticated sustainability models and strategies, marking a leap forward in integrating ESG into broader financial and corporate practices. Credit scoring The convergence of alternative data, artificial intelligence, and generative AI is reshaping the foundations of credit scoring, marking a pivotal moment in the financial industry. The challenges of traditional models are being overcome by adopting alternative credit scoring methods, offering a more inclusive and nuanced assessment. Generative AI, while introducing the potential challenge of hallucination, represents the forefront of innovation, not only revolutionizing technological capabilities but fundamentally redefining how credit is evaluated, fostering a new era of financial inclusivity, efficiency, and fairness. The use of artificial intelligence, in particular generative artificial intelligence, as an alternative method to credit scoring has emerged as a transformative force to address the challenges of traditional credit scoring methods for several reasons: Alternative data analysis: AI models can process a myriad of information, including alternative data such as utility payments and rental history, to create a more comprehensive assessment of an individual's creditworthiness. AI offers unparalleled adaptability : As economic conditions change and consumer behaviors evolve, AI-powered models can quickly adjust. Fraud detection: AI algorithms can detect fraudulent behavior by identifying anomalies and suspicious patterns in credit applications and transaction data. Predictive analysts: AI algorithms, particularly ML techniques, can be used to build predictive models that identify patterns and correlations in historical credit data. Behavioral analysis: AI algorithms can analyze behavioral data sets to understand financial habits and risk propensity. By harnessing the power of artificial intelligence, lenders can make more informed lending decisions, expand access to credit, and better serve consumers (especially those with limited credit history). However, to mitigate potential biases and ensure consumer trust, it's crucial to ensure transparency, fairness, and regulatory compliance when deploying artificial intelligence in credit scoring. AI in payments A lack of developer capacity is one of the biggest challenges for banks when delivering payment product innovation. Banks believe the product enhancements they could not deliver in the past two years due to resource constraints would have supported a 5.3% growth in payments revenues . With this in mind and the revolutionary transformation with the integration of AI, it is imperative to consider how to free up developer resources to make the most of these opportunities. There are several areas in which banks can apply AI to unlock new revenue streams and efficiency gains. The image below provides a high-level view of eight of the principal themes and areas. This is not an exhaustive view but does demonstrate the depth and breadth of current opportunities. In each example, there are already banks that have begun to bring services or enhancements to the market using AI technologies or are otherwise experimenting with the technology. Learn more about AI use cases for top industries in our new ebook, How Leading Industries are Transforming with AI and MongoDB Atlas .
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. With generative AI, retailers can create new products and offerings, define and implement upsell strategies, generate marketing materials based on market conditions, and enhance customer experiences. One of the most creative uses of gen AI help retailers understand customer needs and choices that change continually with seasons, trends, and socio-economic shifts. By analyzing customer data and behavior, gen AI can also create personalized product recommendations, customized marketing materials, and unique shopping experiences that are tailored to individual preferences. AI plays a critical role in decision-making at retail enterprises; product decisions such as design, pricing, demand forecasting, and distribution strategies require a complex understanding of a vast array of information from across the organization. To ensure that the right products in the right quantities are in the right place at the right time, back-office teams leverage machine learning arithmetic algorithms. As technology has advanced and the barrier to adopting AI has lowered, retailers are moving towards data-driven decision-making where AI is leveraged in real-time. generative AI is used to consolidate information and provide dramatic insights that could be immediately utilized across the enterprise. MongoDB.local NYC Join us in person on May 2, 2024 for our keynote address, announcements, and technical sessions to help you build and deploy mission-critical applications at scale. Use Code Web50 for 50% off your ticket! Learn More AI-augmented search and vector search Modern retail is a customer-centric business, and customers have more choice than ever in where they purchase a product. To retain and grow their customer base, retailers are working to offer compelling, personalized experiences to customers. To do this, it is necessary to capture a large amount of data on the customers themselves—like their buying patterns, interests, and interactions—and to quickly use that data to make complex decisions. One of the key interactions in an ecommerce experience is search. With full-text search engines, customers can easily find items that match their search, and retailers can rank those results in a way that will give the customer the best option. In previous iterations of personalization, decisions on how to rank search results in a personalized way were made by segmentation of customers through data acquisition from various operational systems, moving it all into a data warehouse, and then running machine learning algorithms on the data. Typically, this would run every 24 hours or a few days, in batches, so that the next time a customer logged in, they’d have a personalized experience. This did not, however, capture the customer intent in real-time, as intent evolves as the customer gathers more information. These days, modern retailers augment search ranking with data from real-time responses and analytics from AI algorithms. It's also now possible to incorporate factors like the current shopping cart/basket and customer clickstream or trending purchases across shoppers. The first step in truly understanding the customer is to build a customer data platform that combines data from disparate systems and silos across an organization: support, ecommerce transactions, in-store interactions, wish lists, reviews, and more. MongoDB’s flexible document model allows for the easy combination of data of different types and formats with the ability to embed sub-documents to get a clear view of the customer in one place. As the retailer captures more data points about the customer, they can easily add fields without the need for downtime in schema change. Next, the capability to run analytics in real-time rather than retroactively in another separate system is built. MongoDB’s architecture allows for workload isolation, meaning the operational workload (the customer's actions on the ecommerce site) and the analytical or AI workload (calculating what the next best offer should be) can be run simultaneously without interrupting the other. Then using MognoDB’s aggregation framework for advanced analytical queries or triggering an AI model in real time to give an answer that can be embedded into the search ranking in real time. Then comes the ability to easily update the search indexing to incorporate your AI augmentation. As MongoDB has Search built in, this whole flow can be completed in one data platform- as your data is being augmented with AI results, the search indexing will sync to match. MongoDB Atlas Vector Search brings the next generation of search capability. By using LLMs to create vector embeddings for each product and then turning on a vector index, retailers can offer semantic search to their customers. AI will calculate the complex similarities between items in vector space and give the customer a unique set of results matched to their true desire. Figure 1: The architecture of an AI-enhanced search engine explaining the different MongoDB Atlas components and Databricks notebooks and workflows used for data cleaning and preparation, product scoring, dynamic pricing, and vector search Figure 2: The architecture of a vector search solution showcasing how the data flows through the different integrated components of MongoDB Atlas and Databricks Demand forecasting and predictive analytics Retailers either develop homegrown applications for demand prediction using traditional machine learning models or buy specialized products designed to provide these insights across the segments for demand prediction and forecasting. The homegrown systems require significant infrastructure for data and machine learning implementation and dedicated technical expertise to develop, manage, and maintain them. More often than not, these systems require constant care to ensure optimal performance and provide value to the businesses. Generative AI already delivers several solutions for demand prediction for retailers by enhancing the accuracy and granularity of forecasts. The application of retrieval augmented generation utilizing large language models (LLMs) enables retailers to generate specific product demand and dig deeper to go to product categories and individual store levels. This not only streamlines distribution but also contributes to a more tailored fulfillment at a store level. The integration of gen AI in demand forecasting not only optimizes inventory management but also fosters a more dynamic and customer-centric approach in the retail industry. Generative AI can be used to enhance supply chain efficiency by accurately predicting demand for products, optimizing/coordinating with production schedules, and ensuring adequate inventory levels in warehouses or distribution centers. Data requirements for such endeavors include historical sales data, customer orders, and current multichannel sales data and trends. This information can be integrated with external datasets, such as weather patterns and events that could impact demand. This data must be consolidated in an operational data layer that is cleansed for obvious reasons of avoiding wrong predictions. Subsequently, feature engineering to extract seasonality, promotions impact, and general economic indicators. A retrieval augmented generation model can be incorporated to improve demand forecasting predictions and avoid hallucinations. The same datasets could be utilized from historical data to train and fine-tune the model for improved accuracy. Such efforts lead to the following business benefits: Precision in demand forecasting Optimized product and supply planning Efficiency improvement Enhanced customer satisfaction Across the retail industry, AI has captured the imaginations of executives and consumers alike. Whether you’re a customer of a grocer, ecommerce site, or retail conglomerate, AI has and will continue to transform and enhance how you do business with corporations. For the retailers that matter most globally, AI has created opportunities to minimize risk and fraud, perfect user experiences, and save companies from wasting labor and resources. From creation to launch, MongoDB Atlas guarantees that AI applications are cemented in accurate operational data and that they deliver the scalability, security, and performance demanded by developers and consumers alike. Learn more about AI use cases for top industries in our new ebook, Enhancing Retail Operations with AI and Vector Search: The Business Case for Adoption .
Workload Isolation for More Scalability and Availability: Search Nodes Now on Google Cloud
Today we’re excited to take the next step in bringing scalable, dedicated architecture to your search experiences with the introduction of Atlas Search Nodes, now in general availability for Google Cloud. This post is also available in: Deutsch , Français , Español , Português , Italiano , 한국어 , 简体中文 . Since our initial announcement of Search Nodes in June of 2023, we’ve been rapidly accelerating access to the most scalable dedicated architecture, starting with general availability on AWS and now expanding to general availability on Google Cloud. We'd like to give you a bit more context on what Search Nodes are and why they're important to any search experience running at scale. Search Nodes provide dedicated infrastructure for Atlas Search and Vector Search workloads to enable even greater control over search workloads. They also allow you to isolate and optimize compute resources to scale search and database needs independently, delivering better performance at scale and higher availability. One of the last things developers want to deal with when building and scaling apps is having to worry about infrastructure problems. Any downtime or poor user experiences can result in lost users or revenue, especially when it comes to your database and search experience. This is one of the reasons developers turn to MongoDB, given the ease of use of having one unified system for your database and search solution. With the introduction of Atlas Search Nodes, we’ve taken the next step in providing our builders with ultimate control, giving them the ability to remain flexible by scaling search workloads without the need to over-provision the database. By isolating your search and database workloads while at the same time automatically keeping your search cluster data synchronized with operational data, Atlas Search and Atlas Vector Search eliminate the need to run a separate ETL tool, which takes time and effort to set up and is yet another fail point for your scaling app. This provides superior performance and higher availability while reducing architectural complexity and wasted engineering time recovering from sync failures. In fact, we’ve seen a 40% to 60% decrease in query time for many complex queries, while eliminating the chances of any resource contention or downtime. With just a quick button click, Search Nodes on Google Cloud offer our existing Atlas Search and Vector Search users the following benefits: Higher availability Increased scalability Workload isolation Better performance at scale Improved query performance We offer both compute-heavy search-specific nodes for relevance-based text search, as well as a memory-optimized option that is optimal for semantic and retrieval augmented generation (RAG) production use cases with Atlas Vector Search. This makes resource contention or availability issues a thing of the past. Search Nodes are easy to opt into and set up — to start, jump on into the MongoDB UI and follow the steps do the following: Navigate to your “Database Deployments” section in the MongoDB UI Click the green “+Create” button On the “Create New Cluster” page, change the radio button for Google Cloud for “Multi-cloud, multi-region & workload isolation” to enable Toggle the radio button for “Search Nodes for workload isolation” to enable. Select the number of nodes in the text box Check the agreement box Click “Create cluster” For existing Atlas Search users, click “Edit Configuration” in the MongoDB Atlas Search UI and enable the toggle for workload isolation. Then the steps are the same as noted above. Jump straight into our docs to learn more! MongoDB.local NYC Join us in person on May 2, 2024 for our keynote address, announcements, and technical sessions to help you build and deploy mission-critical applications at scale. Use Code Web50 for 50% off your ticket! Learn More
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. As the company states on its website “Our mission is to connect makers (Dev) to customers (Rev) . When every employee adopts a “product-thinking” mindset, customer-centricity transcends from a department to become a culture.” DevRev was founded in October 2020 and raised over $85 million in seed funding from investors such as Khosla Ventures and Mayfield. At the time, this made it the largest seed in the history of Silicon Valley. The company is led by its co-founder and CEO, Dheeraj Pandey, who was previously the co-founder and CEO of Nutanix, and by Manoj Agarwal, DevRev's co-founder and former SVP of Engineering at Nutanix. DevRev is headquartered in Palo Alto and has offices in seven global locations. Check out our AI resource page to learn more about building AI-powered apps with MongoDB. CRM + AI: Digging into the stack DevRev’s Support and Product CRM serve over 4,500 customers: Support CRM brings support staff, product managers, and developers onto an AI-native platform to automate Level 1 (L1), assist L2, and elevate L3 to become true collaborators. Product CRM brings product planning, software work management, and product 360 together so product teams can assimilate the voice of the customer in real-time. Figure 1: DevRev’s real-time dashboards empower product teams to detect at-risk customers, monitor product health, track development velocity, and more. AI is central to both the Support and Product CRMs. The company’s engineers build and run their own neural networks, fine-tuned with application data managed by MongoDB Atlas. This data is also encoded by open-source embedding models where it is used alongside OpenAI models for customer support chatbots and question-answering tasks orchestrated by autonomous agents. MongoDB partner LangChain is used to call the models, while also providing a layer of abstraction that frees DevRev engineers to effortlessly switch between different generative AI models as needed. Data flows across DevRev’s distributed microservices estate and into its AI models are powered by MongoDB change streams . Downstream services are notified in real-time of any data changes using a fully reactive, event-driven architecture. MongoDB Atlas: AI-powered CRM on an agile and trusted data platform MongoDB is the primary database backing OneCRM, managing users, customer and product data, tickets, and more. DevRev selected MongoDB Atlas from the very outset of the company. The flexibility of its data model, freedom to run anywhere, reliability and compliance, and operational efficiency of the Atlas managed service all impact how quickly DevRev can build and ship high-quality features to its customers. The flexibility of the document data model enables DevRev’s engineers to handle the massive variety of data structures their microservices need to work with. Documents are large, and each can have many custom fields. To efficiently store, index, and query this data, developers use MongoDB’s Attribute pattern and have the flexibility to add, modify, and remove fields at any time. The freedom to run MongoDB anywhere helps the engineering team develop, test, and release faster. Developers can experiment locally, then move to integration testing, and then production — all running in different environments — without changing a single line of code. This is core to DevRev’s velocity in handling over 4,000 pull requests per month: Developers can experiment and test with MongoDB on local instances — for example adding indexes or evaluating new query operators, enabling them to catch issues earlier in the development cycle. Once unit tests are complete, developers can move to temporary instances in Docker containers for end-to-end integration testing. When ready, teams can deploy to production in MongoDB Atlas. The multi-cloud architecture of Atlas provides flexibility and choice that proprietary offerings from the hyperscalers can’t match. While DevRev today runs on AWS, in the early days of the company, they evaluated multiple cloud vendors. Knowing that MongoDB Atlas could run anywhere gave them the confidence to make a choice on the platform, knowing they would not be locked into that choice in the future. With MongoDB Atlas, our development velocity is 3-4x higher than if we used alternative databases. We can get our innovations to market faster, providing our customers with even more modern and useful CRM solutions. Anshu Avinash, Founding Engineer, DevRev The HashiCorp Terraform MongoDB Atlas Provider automates infrastructure deployments by making it easy to provision, manage, and control Atlas configurations as code. “The automation provided by Atlas and Terraform means we’ve avoided having to hire a dedicated infrastructure engineer for our database layer,” says Anshu. “This is a savings we can redirect into adding developers to work on customer-facing features.” Figure 2: The reactive, event-driven microservices architecture underpinning DevRev’s AI-powered CRM platform Anshu goes on to say, “We have a microservices architecture where each microservice manages its own database and collections. By using MongoDB Atlas, we have little to no management overhead. We never even look at minor version upgrades, which Atlas does for us in the background with zero downtime. Even the major version upgrades do not require any downtime, which is pretty unique for database systems.” Discussing scalability, Anshu says, “As the business has grown, we have been able to scale Atlas, again without downtime. We can move between instance and cluster sizes as our workloads expand, and with auto-storage scaling, we don’t need to worry about disks getting full.” DevRev manages critical customer data, and so relies on MongoDB Atlas’ native encryption and backup for data protection and regulatory compliance. The ability to provide multi-region databases in Atlas means global customers get further control over data residency, latency, and high availability requirements. Anshu goes on to say, “We also have the flexibility to use MongoDB’s native sharding to scale-out the workloads of our largest customers with complete tenant isolation.” DevRev is redefining the CRM market through AI, with MongoDB Atlas playing a critical role as the company’s data foundation. You can learn more about how innovators across the world are using MongoDB by reviewing our Building AI case studies . If your team is building AI apps, sign up for the AI Innovators Program . Successful companies get access to free Atlas credits and technical enablement, as well as connections into the broader AI ecosystem.
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. This post is also available in: Deutsch , Français , Español , Português , Italiano , 한국어 , 简体中文 . It’s this expertise that Fireworks AI brings to its production AI platform, curating and optimizing the industry's leading open models. Benchmarking by the company shows gen AI models running on Fireworks AI deliver up to 4x faster inference speeds than alternative platforms, with up to 8x higher throughput and scale. Models are one part of the application stack. But for developers to unlock the power of gen AI, they also need to bring enterprise data to those models. That’s why Fireworks AI has partnered with MongoDB, addressing one of the toughest challenges to adopting AI. With MongoDB Atlas , developers can securely unify operational data, unstructured data, and vector embeddings to safely build consistent, correct, and differentiated AI applications and experiences. Jointly, Fireworks AI and MongoDB provide a solution for developers who want to leverage highly curated and optimized open-source models, and combine these with their organization’s own proprietary data — and to do it all with unparalleled speed and security. Lightning-fast models from Fireworks AI: Enabling speed, efficiency, and value Developers can choose from many different models to build their gen AI-powered apps. Navigating the AI landscape to identify the most suitable models for specific tasks — and tuning them to achieve the best levels of price and performance — is complex and creates friction in building and running gen AI apps. This is one of the key pain points that Fireworks AI alleviates. With its lightning-fast inference platform, Fireworks AI curates, optimizes, and deploys 40+ different AI models. These optimizations can simultaneously result in significant cost savings , reduced latency , and improved throughput. Their platform delivers this via: Off-the-shelf models, optimized models, and add-ons: Fireworks AI provides a collection of top-quality text, embedding, and image foundation models . Developers can leverage these models or fine-tune and deploy their own, pairing them with their own proprietary data using MongoDB Atlas. Fine-tuning capabilities : To further improve model accuracy and speed, Fireworks AI also offers a fine-tuning service using its CLI to ingest JSON-formatted objects from databases such as MongoDB Atlas. Simple interfaces and APIs for development and production: The Fireworks AI playground allows developers to interact with models right in a browser. It can also be accessed programmatically via a convenient REST API. This is OpenAI API-compatible and thus interoperates with the broader LLM ecosystem. Cookbook: A simple and easy-to-use cookbook provides a comprehensive set of ready-to-use recipes that can be adapted for various use cases, including fine-tuning, generation, and evaluation. Fireworks AI and MongoDB: Setting the standard for AI with curated, optimized, and fast models With Fireworks AI and MongoDB Atlas, apps run in isolated environments ensuring uptime and privacy, protected by sophisticated security controls that meet the toughest regulatory standards: As one of the top open-source model API providers, Fireworks AI serves 66 billion tokens per day (and growing). With Atlas, you run your apps on a proven platform that serves tens of thousands of customers, from high-growth startups to the largest enterprises and governments. Together, the Fireworks AI and MongoDB joint solution enables: Retrieval-augmented generation (RAG) or Q&A from a vast pool of documents: Ingest a large number of documents to produce summaries and structured data that can then power conversational AI. Classification through semantic/similarity search: Classify and analyze concepts and emotions from sales calls, video conferences, and more to provide better intelligence and strategies. Or, organize and classify a product catalog using product images and text. Images to structured data extraction: Extract meaning from images to produce structured data that can be processed and searched in a range of vision apps — from stock photos, to fashion, to object detection, to medical diagnostics. Alert intelligence: Process large amounts of data in real-time to automatically detect and alert on instances of fraud, cybersecurity threats, and more. Figure 1: The Fireworks tutorial showcases how to bring your own data to LLMs with retrieval-augmented generation (RAG) and MongoDB Atlas Getting started with Fireworks AI and MongoDB Atlas To help you get started, review the Optimizing RAG with MongoDB Atlas and Fireworks AI tutorial, which shows you how to build a movie recommendation app and involves: MongoDB Atlas Database that indexes movies using embeddings. (Vector Store) A system for document embedding generation. We'll use the Fireworks embedding API to create embeddings from text data. (Vectorisation) MongoDB Atlas Vector Search responds to user queries by converting the query to an embedding, fetching the corresponding movies. (Retrieval Engine) The Mixtral model uses the Fireworks inference API to generate the recommendations. You can also use Llama, Gemma, and other great OSS models if you like. (LLM) Loading MongoDB Atlas Sample Mflix Dataset to generate embeddings (Dataset) We can also help you design the best architecture for your organization’s needs. Feel free to connect with your account team or contact us here to schedule a collaborative session and explore how Fireworks AI and MongoDB can optimize your AI development process.
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. The telecommunications industry operates in a landscape characterized by tight profit margins, particularly in commoditized communication and connectivity services where differentiation is minimal. With offerings such as voice, data, and internet access being largely homogeneous, telecom companies need to differentiate and diversify revenue streams to create value and stand out in the market. As digital natives disrupt traditional business models with agile and innovative approaches, established companies are not only competing among themselves but also with newcomers to deliver enhanced customer experiences and adapt to evolving consumer demands. To thrive in an environment where advanced connectivity is increasingly expected, telecom operators must prioritize cost efficiency in their Operations Support Systems (OSS) and Business Support Systems (BSS), elevate customer service standards, and enhance overall customer experiences to secure market share and gain a competitive edge. They’re not alone — media publishers, too, must streamline operations through automation while strengthening reader relationships to foster a willingness to pay for personalized and relevant content. MongoDB.local NYC Join us in person on May 2, 2024 for our keynote address, announcements, and technical sessions to help you build and deploy mission-critical applications at scale. Use Code Web50 for 50% off your ticket! Learn More Service assurance Telecommunications providers need to deliver network services at optimal quality and performance levels to meet customer expectations and service level agreements. Key aspects of service assurance include performance monitoring, quality of service (QoS) management, and predictive analytics to anticipate potential service degradation or network failures before they occur. With the increasing complexity of telecommunications networks and the growing expectations of customers for high-quality, always-on services, a new bar has been set for service assurance, requiring companies to invest heavily in solutions that can automate and optimize these processes and maintain a competitive edge. Service assurance is revolutionized by artificial intelligence (AI) through several key capabilities: Machine learning (ML) can be a powerful foundation for predictive maintenance, analyzing patterns, and predicting network failures before they occur, allowing for preemptive maintenance and significantly reducing downtime; AI techniques can also sift through complex network systems to accurately identify the root causes of issues, improving the effectiveness of troubleshooting efforts; and, with network optimization, analyzing log data to identify opportunities for improvement, raising efficiency and thus reducing operational costs and optimizing network performance in real-time. MongoDB Atlas ’s JSON-based document model is the ideal data foundation to underpin intelligent applications. It enables developers to store log data from various systems without the need for time-intensive upfront data normalization efforts and with the flexibility to deal with a wide variety of different data structures, even as they change over time. By vectorizing the data with an appropriate ML model, it's possible to reflect the healthy system state and identify log information that shows abnormal system behavior. Atlas Vector Search allows for conducting the required K-Nearest Neighbors (KNN) search in an effective way and as a fully included service of the MongoDB Atlas developer data platform . Finally, using LLM, information about the error, including the analysis of the root cause, can be expressed in natural language, making the job of understanding and fixing the problem much easier for the staff who are in charge of maintenance. Fraud detection and prevention Telecom providers today are utilizing an advanced array of techniques for detecting and preventing fraud, constantly adjusting to the dynamic nature of threat actors. Routine activities for detecting fraud consist of tracking unusual call trends and data usage, along with safeguarding against SIM swap incidents, a method frequently used for identity theft. To prevent fraud, strategies are applied at various levels, starting with stringent verification for new customers during SIM swaps or for transactions with elevated risk, taking into account the unique risk profile of each customer. Machine learning offers telecommunications companies a powerful tool to enhance their fraud detection and prevention capabilities by training ML models on historical data like call detail records (CDR). Moreover, these algorithms can assess the individual risk profile of each customer, tailoring detection and prevention strategies to their specific patterns of use. The models can adapt over time, learning from new data and emerging fraud tactics, thus enabling real-time detection and the automation of fraud prevention measures, reducing manual checks, and speeding up response times. To succeed in fraud detection, many data dimensions need to be considered, making the reaction time a critical factor in preventing the worst things from happening. So, the solution must also support fast, sub-second decisions. By vectorizing the data with an appropriate ML model, normal (healthy) business can be defined, and in turn, deviations from the norm identified, such as suspicious user activities. In addition to Atlas Vector Search, the MongoDB Query API supports stream processing , simplifying data ingestion from various sources and detecting fraud in real-time. Content discovery Today’s media organizations are expected to offer a high degree of content personalization, from streaming services to online publications and more. Viewers want intelligently selected and suggested content tailored to their interests. Using AI can significantly enhance the process of suggesting the next best article to read or show to stream. The most powerful implementations of content personalization track the behavior of the user, such as what content was searched for, how long was content displayed before the next click happened, and the categories the search falls under. Based on these parameters, similar content can be presented, or, as an alternative strategy, content from unseen areas of the portal so the user may discover new types of media and decide if they like it. To bring the right content to the right people at the right time, an automated system needs to maintain a multitude of information facets, which will lay the foundation for proper suggestions. With MongoDB and its document model, all required data points can be easily and flexibly stored in a user’s profile, in content, and in media. Ultimately, by vectorizing the content, an even more powerful system of content suggestions can be built with Atlas Vector Search, which allows for a similarity search that goes well beyond comparing just keywords or a list of attributes. Other notable use cases Differential Pricing: Gather insights into what customers are willing to spend on content or a service by conducting A/B tests and analyzing the data with an ML algorithm. This method facilitates the adoption of dynamic pricing models instead of sticking to a standard price list, thereby enhancing revenue and increasing the paying customer base. Content Summarization and Reformatting: Design a smart assistant tailored for writers, capable of providing automatic suggestions for content summaries, identifying suitable SEO keywords, and adapting articles for various specific audiences. Search Generative Experiences (SGE): Provide more dynamic, personalized, and contextually relevant search results, thus making information retrieval not only more efficient but also more engaging and useful. This can include personalization and summarization elements, as well. In conclusion, the telecommunications industry faces challenges of differentiation and revenue diversification amidst commoditized services and disruptive market forces. To thrive, telecom operators must prioritize cost efficiency, elevate customer service, and enhance experiences. Leveraging AI, MongoDB Atlas offers solutions like service assurance, fraud detection, and content discovery, empowering companies to navigate the complexities of the digital landscape, innovate, and deliver value-added services. From predictive maintenance to personalized content recommendations, MongoDB Atlas stands as a foundational tool for telecom and media companies, driving efficiency, agility, and competitiveness in a rapidly evolving market. Learn more about AI use cases for top industries in our new white paper, “ How Leading Industries are Transforming with AI and MongoDB Atlas .”
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. The integration of artificial intelligence (AI) within the manufacturing and automotive industries has transformed the conventional value chain, presenting a spectrum of opportunities. Leveraging Industrial IoT, companies now collect extensive data from assets, paving the way for analytical insights and unlocking novel AI use cases, including enhanced inventory management and predictive maintenance. MongoDB.local NYC Join us in person on May 2, 2024 for our keynote address, announcements, and technical sessions to help you build and deploy mission-critical applications at scale. Use Code Web50 for 50% off your ticket! Learn More Inventory management Efficient supply chains can control operational costs and ensure on-time delivery to their customers. Inventory optimization and management is a key component in achieving these goals. Managing and optimizing inventory levels, planning for fluctuations in demand, and of course, cutting costs are all imperative goals. However, efficient inventory management for manufacturers presents complex data challenges too, primarily in forecasting demand accurately and optimizing stock levels. This is where AI can help. Figure 1: Gen AI-enabled demand forecasting with MongoDB Atlas AI algorithms can be used to analyze complex datasets to predict future demand for products or parts. Improvement in demand forecasting accuracy is crucial for maintaining optimal inventory levels. AI-based time series forecasting can assist in adapting to rapid changes in customer demand. Once the demand is known, AI can play a pivotal role in stock optimization. By analyzing historical sales data and market trends, manufacturers can determine the most efficient stock levels and even reduce human error. On top of all this existing potential, generative AI can help with generating synthetic inventory data and seasonally adjusted demand patterns. It can also help with creating scenarios to simulate supply chain disruptions. MongoDB Atlas makes this process simple. At the warehouse, the inventory can be scanned using a mobile device. This data is persisted in Atlas Device SDK and synced with Atlas using Device Sync, which is used by MongoDB customers like Grainger . Atlas Device Sync provides an offline-first seamless mobile experience for inventory tracking, making sure that inventory data is always accurate in Atlas. Once data is in Atlas, it can serve as the central repository for all inventory-related data. This repository becomes the source of data for inventory management AI applications, eliminating data silos and improving visibility into overall inventory levels and movements. Using Atlas Vector Search and generative AI, manufacturers can easily categorize products based on their seasonal attributes, cluster products with similar seasonal demand patterns, and provide context to the foundation model to improve the accuracy of synthetic inventory data generation. Predictive maintenance The most basic approach to maintenance today is reactive — assets are deliberately allowed to operate until failures actually occur. The assets are maintained as needed, making it challenging to anticipate repairs. Preventive maintenance, however, allows systems or components to be replaced based on a conservative schedule to prevent commonly occurring failures — although predictive maintenance is expensive to implement due to frequent replacement of parts before end-of-life. Figure 2: Audio-based anomaly detection with MongoDB Atlas. Scan the QR code to try it out yourself. AI offers a chance to efficiently implement predictive maintenance using data collected from IoT sensors on machinery trained to detect anomalies. ML/AI algorithms like regression models or decision trees are trained on the preprocessed data, deployed on-site for inference, and continuously analyzed sensor data. When anomalies are detected, alerts are generated to notify maintenance personnel, enabling proactive planning and execution of maintenance actions to minimize downtime and optimize equipment reliability and performance. A retrieval-augmented generation (RAG) architecture can be deployed to generate or curate the data preprocessor removing the need for specialized data science knowledge. The domain expert can provide the right prompts for the large language model. Once the maintenance alert is generated by an AI model, generative AI can come in again to suggest a repair strategy, taking spare parts inventory data, maintenance budget, and personal availability into consideration. Finally, the repair manuals can be vectorized and used to power a chatbot application that guides the technician in performing the actual repair. MongoDB documents are inherently flexible while allowing data governance when required. Since machine health prediction models require not just sensor data but also maintenance history and inventory data, the document model is a perfect fit to model such disparate data sources. During the maintenance and support process of a physical product, information such as product information and replacement parts documentation must be available and easily accessible to support staff. Full-text search capabilities provided by Atlas Search can be integrated with the support portal and help staff retrieve information from Atlas clusters with ease. Atlas Vector Search is a foundational element for effective and efficiently powered predictive maintenance models. Manufacturers can use MongoDB Atlas to explore ways of simplifying machine diagnostics. Audio files can be recorded from machines, which can then be vectorized and searched to retrieve similar cases. Once the cause is identified, they can use RAG to implement a chatbot interface that the technician can interact with and get context-aware, step-by-step guidance on how to perform the repair. Autonomous driving With the rise of connected vehicles, automotive manufacturers have been compelled to transform their business models into software-first organizations. The data generated by connected vehicles is used to create better driver assistance systems, paving the way for autonomous driving applications. However, it is challenging to create fully autonomous vehicles that can drive safer than humans. Some experts estimate that the technology to achieve level 5 autonomy is about 80% developed — but the remaining 20% will be extremely hard to achieve and will take a lot of time to perfect. Figure 3: MongoDB Atlas’s Role in Autonomous Driving AI-based image and object recognition in automotive applications face uncertainties, but manufacturers must utilize data from radar, LiDAR, cameras, and vehicle telemetry to improve AI model training. Modern vehicles act as data powerhouses, constantly gathering and processing information from onboard sensors and cameras, generating significant Big Data. Robust storage and analysis capabilities are essential to manage this data, while real-time analysis is crucial for making instantaneous decisions to ensure safe navigation. MongoDB can play a significant role in addressing these challenges. The document model is an excellent way to accommodate diverse data types such as sensor readings, telematics, maps, and model results. New fields to the documents can be added at run time, enabling the developers to easily add context to the raw telemetry data. MongoDB’s ability to handle large volumes of unstructured data makes it suitable for the constant influx of vehicle-generated information. Atlas Search provides a performant search engine to allow data scientists to iterate their perception AI models. Finally, Atlas Device Sync can be used to send configuration updates to the vehicle's advanced driving assistance system Other notable use cases AI plays a critical role in fulfilling the promise of Industry 4.0. Numerous other use cases of AI can be enabled by MongoDB Atlas, some of which include: Logistics Optimization: AI can help optimize routes resulting in reduced delays and enhanced efficiency in day-to-day delivery operations. Quality Control and Defect Detection: Computer or machine vision can be used to identify irregularities in the products as they are manufactured. This ensures that product standards are met with precision. Production Optimization: By analyzing time series data from sensors installed on production lines, waste can be identified and reduced, thereby improving throughput and efficiency. Smart After Sales Support: Manufacturers can utilize AI-driven chatbots and predictive analytics to offer proactive maintenance, troubleshooting, and personalized assistance to customers. Personalized Product Recommendations: AI can be used to analyze user behavior and preferences to deliver personalized product recommendations via a mobile or web app, enhancing customer satisfaction and driving sales. The integration of AI in manufacturing and automotive industries has revolutionized traditional processes, offering a plethora of opportunities for efficiency and innovation. With industrial IoT and advanced analytics, companies can now harness vast amounts of data to enhance inventory management and predictive maintenance. AI-driven demand forecasting ensures optimal stock levels, while predictive maintenance techniques minimize downtime and optimize equipment performance. Moreover, as automotive manufacturers work toward autonomous driving, AI-powered image recognition and real-time data analysis become paramount. MongoDB Atlas emerges as a pivotal solution, providing flexible document modeling and robust storage capabilities to handle the complexities of Industry 4.0. Beyond the manufacturing and automotive sectors, the potential of AI-enabled by MongoDB Atlas extends to logistics optimization, quality control, production efficiency, smart after-sales support, and personalized customer experiences, shaping the future of Industry 4.0 and beyond. Learn more about AI use cases for top industries in our new white paper, “ How Leading Industries are Transforming with AI and MongoDB Atlas .”