Reflections On Our Recent AI "Think-A-Thon"

Veronica Cooley-Perry
October 23, 2024
#genAI

Interesting ideas are bound to emerge when great minds come together, so there was no shortage of interesting ideas on October 2nd, when MongoDB’s Developer Relations team hosted our second-ever AI Build Together event at MongoDB.local London.

In some ways, the event is similar to a hackathon: a group of developers come together to solve a problem. But in other ways, the event is quite different. While hackathons normally take an entire day and involve intensive coding, the AI Build Together events are organized to take place over just a few hours and don't involve any coding at all. Instead, it’s all based around discussion and ideation. For these reasons, MongoDB’s Developer Relations team likes to dub them “think-a-thons.”

Our first AI Build Together event was held earlier this year at .local NYC. After seeing the energy in the room and the excitement from attendees, our Developer Relations team knew it wanted to host another one.

The .local London event’s fifty attendees—which included developers from numerous industries and leading AI innovators who served as mentors—came together to brainstorm and discuss AI-based solutions to common industry problems.

Photo of .local London AI Build Together attendees brainstorming AI solutions for the healthcare industry. The group is sitting around a table and writing down ideas on a giant notepad. The room is filled with more tables of other groups doing the same thing. — .local London AI Build Together attendees brainstorming AI solutions for the healthcare industry

The AI mentors included: Loghman Zadeh (gravity9), Ben Gutkovich (Superlinked), Jesse Martin (Hasura), Marlene Mhangami (Microsoft), Igor Alekseev (AWS), and John Willis and Patrick Debois (co-founders of DevOps).

Upon arrival, participants joined a workflow group best aligned with their industry and/or area of interest—AI for Education, AI for DevOps, AI for Healthcare, AI for Optimizing Travel, AI for Supply Chain, and AI for Productivity.

Photo of the AI for Productivity group collaborating on their workflow. The group is siting around a table and writing down ideas on a giant notepad. — The AI for Productivity group collaborating on their workflow

The discussions were lively, and it was amazing to see how much energy these attendees brought to their discussions.

For example, the AI for Education workflow group vigorously discussed developing a personalized AI education coach to help students develop their educational plans and support them with career advice.

Meanwhile, the AI for Healthcare workflow group focused on the idea of creating an AI drive tool to provide personalized healthcare to patients and real-time insights to their providers.

The AI for Productivity team came up with a clever product that helps you read, digest, and identify the key aspects of long legal documents.

The AI for Optimizing Travel group seeking advice from AI mentor Marlene. The group is at a table discussing what the team had written down on the notepad. — The AI for Optimizing Travel group seeking advice from AI mentor Marlene

A talented artist was also brought in to visualize each workflow group’s problem statements and potential solutions—literally and figuratively illustrating their innovative ideas.

Photograph of graphic recorder Maria Foulquie putting the final touches on an illustration. She is kneeling on the ground drawing on a big board with a crowd around her watching. — Graphic recorder Maria Foulquié putting the final touches on the illustration

Final illustration documenting the 2024 MongoDB.local London AI Build Together event

All in all, our second time hosting this event was deemed a success by everyone involved.

“It was impressive to see how attendees, regardless of their technical background, found ways to contribute to complex AI solutions,” says Loghman Zadeh, AI Director at gravity9, who served as one of the event’s advisors. “Engaging with so many creative and forward-thinking individuals, all eager to push the boundaries of AI innovation was refreshing. The collaborative atmosphere fostered dynamic discussions and allowed participants to explore new ideas in a supportive environment.”

If you’re interested in taking part in events like these—which offer a range of networking opportunities—there are three more MongoDB.local events slated for 2024—Sao Paulo, Paris, and Stockholm. Additionally, you can join your local MongoDB user group to learn from and connect with other MongoDB developers in your area.

← Previous

Empower Innovation in Insurance with MongoDB and Informatica

For insurance companies, determining the right technology investments can be difficult, especially in today's climate where technology options are abundant but their future is uncertain. As is the case with many large insurers, there is a need to consolidate complex and overlapping technology portfolios. At the same time, insurers want to make strategic, future-proof investments to maximize their IT expenditures. What does the future hold, however? Enter scenario planning. Using the art of scenario planning, we can find some constants in a sea of uncertain variables, and we can more wisely steer the organization when it comes to technology choices. Consider the following scenarios: Regulatory disruption: A sudden regulatory change forces re-evaluation of an entire market or offering. Market disruption: Vendor and industry alliances and partnerships create disruption and opportunity. Tech disruption: A new CTO directs a shift in the organization's cloud and AI investments, aligning with a revised business strategy. What if you knew that one of these three scenarios was going to play itself out in your company but weren’t sure which one? How would you invest now to prepare for one of the three? At the same time that insurers are grappling with technology choices, they’re also facing clashing priorities: Running the enterprise: supporting business imperatives and maintaining health and security of systems. Innovating with AI: maintaining a competitive position by investing in AI technologies. Optimizing spend: minimizing technology sprawl, technical debt, and maximizing business outcomes. Data modernization What is the common thread among all these plausible future scenarios? How can insurers apply scenario planning principles while bringing diverging forces into alignment? There is one constant in each scenario, and that’s the organization’s data—if it’s hard to work with, any future scenario will be burdened by this fact. One of the most critical strategic investments an organization can make is to ensure data is easy to work with. Today, we refer to this as data modernization, which involves removing the friction that manifests itself in data processing, ensuring data is current, secure, and adaptable. For developers, who are closest to the data, this means enabling them with a seamless and fully integrated developer data platform along with a flexible data model. In the past, data models and databases would remain unchanged for long periods. Today, this approach is outdated. Consolidation creates a data model problem, resulting in a portfolio with relational, hierarchical, and file-based data models—or, worst of all, a combination of all three. Add to this the increased complexity that comes with relational models, including supertype-subtype conditional joins and numerous data objects, and you can see how organizations wind up with a patchwork of data models and overly complicated data architecture. A document database, like MongoDB Atlas , stores data in documents and is often referred to as a non-relational (or NoSQL) database. The document model offers a variety of advantages and specifically excels in data consolidation and agility: Serves as the superset of all other data model types (relational, hierarchical, file-based, etc.) Consolidates data assets into elegant single-views, capable of accommodating any data structure, format, or source Supports agile development, allowing for quick incorporation of new and existing data Eliminates the lengthy change cycles associated with rigid, single-schema relational approaches Makes data easier to work with, promoting faster application development By adopting the document model, insurers can streamline their data operations, making their technology investments more efficient and future-proof. The challenges of making data easier to work with include data quality. One significant hurdle insurers continue to face is the lack of a unified view of customers, products, and suppliers across various applications and regions. Data is often scattered across multiple systems and sources, leading to discrepancies and fragmented information. Even with centralized data, inconsistencies may persist, hindering the creation of a single, reliable record. For insurers to drive better reporting, analytics, and AI, there's a need for a shared data source that is accurate, complete, and up-to-date. Centralized data is not enough; it must be managed, reconciled, standardized, cleansed, and enriched to maintain its integrity for decision-making. Mastering data management across countless applications and sources is complex and time-consuming. Success in master data management (MDM) requires business commitment and a suite of tools for data profiling, quality, and integration. Aligning these tools with business use cases is essential to extract the full value from MDM solutions, although the process can be lengthy. Informatica’s MDM solution and MongoDB Informatica’s MDM solution has been developed to answer the key questions organizations face when working with their customer data: “How do I get a 360-degree view of my customer, partner and & supplier data?” “How do I make sure that my data is of the highest quality?” The Informatica MDM platform helps ensure that organizations around the world can confidently use their data and make business decisions based on it. Informatica’s entire MDM solution is built on MongoDB Atlas , including its AI engine, Claire. Figure 1: Everything you need to modernize the practice of master data management. Informatica MDM solves the following challenges: Consolidates data from overlapping and conflicting data sources. Identifies data quality issues and cleanses data. Provides governance and traceability of data to ensure transparency and trust. Insurance companies typically have several claim systems that they’ve amassed over the years through acquisitions, with each one containing customer data. The ability to relate that data together and ensure it’s of the highest quality enables insurers to overcome data challenges. MDM capabilities are essential for insurers who want to make informed decisions based on accurate and complete data. Below are some of the different use cases for MDM: Modernize legacy systems and processes (e.g. claims or underwriting) by effectively collecting, storing, organizing, and maintaining critical data Improve data security and improve fraud detection and prevention Effective customer data management for omni-channel engagement and cross- or up-sell Data management for compliance, avoiding or predicting in advance any possible regulatory issues Given we already leverage the performance and scale of MongoDB Atlas within our cloud-native MDM SaaS solution and share a common focus on high-value, industry solutions, this partnership was a natural next step. Now, as a strategic MDM partner of MongoDB, we can help customers rapidly consolidate and sunset multiple legacy applications for cloud-native ones built on a trusted data foundation that fuels their mission-critical use cases. Rik Tamm-Daniels, VP of Strategic Ecosystems and Technology at Informatica Taking the next step For insurance companies navigating the complexities of modern technology and data management, MDM combined with powerful tools like MongoDB and Informatica provide a strategic advantage. As insurers face an uncertain future with potential regulatory, market, and technological disruptions, investing in a robust data infrastructure becomes essential. MDM ensures that insurers can consolidate and cleanse their data, enabling accurate, trustworthy insights for decision-making. By embracing data modernization and the flexibility of document databases like MongoDB, insurers can future-proof their operations, streamline their technology portfolios, and remain agile in an ever-changing landscape. Informatica’s MDM solution, underpinned by MongoDB Atlas, offers the tools needed to master data across disparate systems, ensuring high-quality, integrated data that drives better reporting, analytics, and AI capabilities. If you would like to discover more about how MongoDB and Informatica can help you on your modernization journey, take a look at the following resources: Unify data across the enterprise for a contextual 360-degree view and AI-powered insights with Informatica’s MDM solution Automating digital underwriting with machine learning Claim management using LLMs and vector search for RAG

October 22, 2024

Next →

Gamuda Puts AI in Construction with MongoDB Atlas

Gamuda Berhad is a leading Malaysian engineering and construction company with operations across the world, including in Australia, Taiwan, Singapore, Vietnam, the United Kingdom, and more. The company is known for its innovative approach to construction through the use of cutting-edge technology. Speaking at MongoDB.local Kuala Lumpur in August 2024 , John Lim, Chief Digital Officer at Gamuda said: “In the construction industry, AI is increasingly being used to analyze vast amounts of data, from sensor readings on construction equipment to environmental data that impacts project timelines.” One of Gamuda’s priorities is determining how AI and other tools can impact the company’s methods for building large projects across the world. For that, the Gamuda team needed the right infrastructure, with a database equipped to handle the demands of modern AI-driven applications. MongoDB Atlas fulfilled all the requirements and enabled Gamuda to deliver on its AI-driven goals. Why Gamuda chose MongoDB Atlas “Before MongoDB, we were dealing with a lot of different databases and we were struggling to do even simple things such as full-text search,” said Lim. “How can we have a tool that's developer-friendly, helps us scale across the world, and at the same time helps us to build really cool AI use cases, where we're not thinking about the infrastructure or worrying too much about how things work but are able to just focus on the use case?” After some initial conversations with MongoDB, Lim’s team saw that MongoDB Atlas could help it streamline its technology stack, which was becoming very complex and time consuming to manage. MongoDB Atlas provided the optimal balance between ease of use and powerful functionality, enabling the company to focus on innovation rather than database administration. “I think the advantage that we see is really the speed to market. We are able to build something quickly. We are fast to meet the requirements to push something out,” said Lim. Chi Keen Tan, Senior Software Engineer at Gamuda, added, “The team was able to use a lot of developer tools like MongoDB Compass , and we were quite amazed by what we can do. This [ability to search the items within the database easily] is just something that’s missing from other technologies.” Being able to operate MongoDB on Google Cloud was also a key selling point for Gamuda: “We were able to start on MongoDB without any friction of having to deal with a lot of contractual problems and billing and setting all of that up,” said Lim. How MongoDB is powering more AI use cases Gamuda uses MongoDB Atlas and functionalities such as Atlas Search and Vector Search to bring a number of AI use cases to life. This includes work implemented on Gamuda’s Bot Unify platform, which Gamuda built in-house using MongoDB Atlas as the database. By using documents stored in SharePoint and other systems, this platform helps users write tenders quicker, find out about employee benefits more easily, or discover ways to improve design briefs. “It’s quite incredible. We have about 87 different bots now that people across the company have developed,” Lim said. Additionally, the team has developed Gamuda Digital Operating System (GDOS), which can optimize various aspects of construction, such as predictive maintenance, resource allocation, and quality control. MongoDB’s ability to handle large volumes of data in real-time is crucial for these applications, enabling Gamuda to make data-driven decisions that improve efficiency and reduce costs. Specifically, MongoDB Atlas Vector Search enables Gamuda’s AI models to quickly and accurately retrieve relevant data, improving the speed and accuracy of decision-making. It also helps the Gamuda team find patterns and correlations in the data that might otherwise go unnoticed. Gamuda’s journey with MongoDB Atlas is just beginning as the company continues to explore new ways to integrate technology into its operations and expand to other markets. To learn more and get started with MongoDB Vector Search, visit our Vector Search Quick Start page.

October 22, 2024