Meet the MongoDB Europe 2016 Diversity Scholars

Danielle James
December 20, 2016 | Updated: October 5, 2022
#Community#Company

In November, a group of rising tech stars attended the first annual MongoDB Europe as part of the MongoDB Diversity Scholarship program.

The MongoDB Diversity Scholarship is one of our initiatives to change the ratio in technology. At MongoDB Europe, the Diversity Scholars got complimentary admission to the conference, a lunch sessions with other Scholars, and speed mentoring with MongoDB speakers. Additionally, they received a MongoDB certification voucher and three-month access to on-demand MongoDB University courses.

Read on to meet the MongoDB Europe 2016 Diversity Scholars, and to find out how you can apply to the scholarship at MongoDB World in Chicago, June 20-21, 2017.

Ousmane Barry, Software Developer, Novencia

I’m originally from Senegal and came to France to pursue my higher education. Currently, I’m a Software Engineer at a consulting company, where I help the teams to develop their technical level through Software Craftsmanship.

How I started using MongoDB: Like the majority of developers, I come from the world of SQL. I discovered MongoDB through a discussion with a colleague. At the same time, my company wanted to build skills in the field of NoSQL, so I registered on MongoDB University to learn the technology. After that, I passed the DEV certification, followed by the DBA certification.

My giant idea: I would like to work on a Big Data project where you can use all the power and flexibility offered by MongoDB. It would be interesting to work on use cases such as IoT or Single View. -- @EnamsuoBarry

Quynh Tran Thanh, Quant Analyst, Commerzbank

I’m currently a Quant Analyst working at Commerzbank. In my free time, I love assembling IKEA furniture.

How I started using MongoDB: I started using MongoDB at a hackathon, where I had to build an app with my team within 48 hours. MongoDB was the best choice for a user friendly database, and perfect for our app as we used JSON data.

My giant idea: Recently, I’ve become very interested in cryptocurrencies such as Bitcoin. I’d like to analyze transactions on the blockchain. For that, I’d like to use MongoDB to easily query for transactions.

Soyini Taylor, Database Analyst/Data Architect, Reed Business Information

I’m a Database Analyst living in London, currently on a 6-month secondment as a Data Architect.

How I started using MongoDB: I wanted to learn MongoDB and got started with the free M102 course on MongoDB University. M102 was a good introduction to how the database works.

My giant idea: My goal is to complete the next MongoDB University course, M202. I’m looking forward to MongoDB releasing a sandbox area for those working in operations that are charged only with maintenance of the database.

I also love the fact that MongoDB provides a Diversity Scholarship to encourage more involvement in technology by underrepresented groups, and hope to be able to contribute back to the community one day.

Want to attend MongoDB World on a Diversity Scholarship?

The Diversity Scholarship is now open for [MongoDB World](https://www.mongodb.com/world17 "MongoDB World"). If you’re a member of an underrepresented group in technology, you can apply today!
Apply Now


← Previous

Recap: MongoDB Power Heels Holiday Party

In July 2016, Sarah Branfman , Amie Darboe , and Sarah Dart , members of the sales team at MongoDB, brainstormed ways to help fill the gender gap in sales and technology roles. The result was Power Heels, an organization that empowers women to maximize their potential, professionally and personally, in a safe environment. Since its inception, PowerHeels has partnered with organizations like Dress for Success and Safe Place. Members include technology and business professionals, university students, and women looking to change careers. On December 6, 2016, Power Heels hosted its first annual holiday party at IBM Design Studio in Austin. More than just a networking event, the event featured the following career building activities: Build Your Profile : Resume writing and building a stunning LinkedIn profile Look the Part : Hair styling, makeup, and professional headshots Talk the Talk : Mock interviews and feedback led by business leaders from some of Austin’s hottest companies Additionally, attendees were encouraged to bring donations for Dress for Success. Over 85 items were donated over the course of the event. ![MongoDB Power Heels](https://webassets.mongodb.com/_com_assets/cms/MongoDB_PowerHeels_Team-5u4v97yc1m.png "MongoDB Power Heels") *The Power Heels team* The event was as much fun as it was valuable. Joanne Kim , a college senior whose job search hadn’t been as successful as she expected it to be, came to the event to get interview advice from experts. She said, “my favorite part of the event was the mock interview. I was able to hear what recruiters think and understand what they look for in a candidate. The party setting made it casual, yet I was able to get useful advice from HR professionals.” Joanne left the holiday party feeling more confident about her job search process. ![MongoDB Power Heels interviews with attendees](https://webassets.mongodb.com/_com_assets/cms/MongoDB_PowerHeels_Interview-jxu2tzqwlb.png "Power Heels interviews with attendee") *MongoDB’s [Emily Friedman](https://www.linkedin.com/in/emilywilliamson1?authType=NAME_SEARCH&authToken=gP5L&locale=en_US&trk=tyah&trkInfo=clickedVertical%3Amynetwork%2CclickedEntityId%3A27252290%2CauthType%3ANAME_SEARCH%2Cidx%3A1-1-1%2CtarId%3A1481734465381%2Ctas%3Aemily%20fried "Emily Friedman") conducting a mock interview with an attendee* According to Amie, Power Heels is about building a sisterhood of fierce women – and men, “because #allies” – who want to go far in their careers. It’s a group of people who work together to bring other women up and who are open to receiving support. MongoDB’s Taelen Lewis is one of those allies. During the event, attendees could purchase raffle tickets. The grand prize was a two-hour photo shoot by The Perfect Headshot . Taelen won the grand prize, but chose to auction it off to highest bidder and donated the proceeds to Power Heels. His reasoning? “As an oldest brother to three younger sisters, I love to see an organization empowering women to realize their potential and to be given equal opportunities,” he said. “I’m a big fan of Power Heels, so I’m happy to support.” Taelen won’t be getting an updated headshot soon, but thanks to the Look the Part station at the event, almost all of the women who attended got a brand new photo for their LinkedIn profiles. ![MongoDB Power Heels Look the Part station](https://webassets.mongodb.com/_com_assets/cms/MongoDB_PowerHeels_LookthePart_Station-zymz1n5hx0.png "Look the Part station") *An attendee getting her hair done at the Look the Part station* At the Look the Part station, attendees could also get their hair and makeup done. Nina, a team member at Naava - who provided the glam services at the event - said she learned about Power Heels when she was going through a challenging time. Recently divorced and jobless, Nina went to Dress for Success, where she received the resume and interview help that led to her current role. When she heard about the opportunity to give back through Power Heels, she jumped on it. She stated, “You never know how much you’re impacting someone’s life by offering resume help or giving them business attire. It might seem like a small thing to do, but enabling someone to perform well in an interview can turn someone’s life around.” Her staff had been working since 8am that morning, but insisted they come to contribute to the event. ![MongoDB Power Heels networking](https://webassets.mongodb.com/_com_assets/cms/MongoDB_PowerHeels_Networking-d3g595wef6.png "Power Heels attendees networking") *Power Heels attendees networking* Throughout the evening, attendees made new connections, edited their resumes, improved their online presence, and explored different ways to respond in an interview. This experience is what the women of MongoDB had in mind when they created Power Heels. Sarah B. didn’t want the holiday party to be just that, a gathering where attendees hand out business cards, take advantage of free food and drink, and go home with nothing actionable. “These events can rob you of your time and leave you unfulfilled,” she said. “While the Power Heels holiday party had its fair share of drinks, food and merriment, nobody left empty handed and without a next step to improve their career.” See the Power Heels holiday party photo recap . The MongoDB Power Heels team will soon expand in other states. Want to get involved by becoming a member or sponsoring an event? Let us know! You won’t regret it. In Sarah B.’s words, “We don't just shmooze, we get [things] done.” Thank you to the MongoDB Power Heels advocates, who sponsored the event : **|** [Safe Place](http://www.safeaustin.org/safeplace/ "Safe Place") **|** [The Perfect Headshot](http://www.theperfectheadshot.com/ "The Perfect Headshot") **|** **|** [Breaking the Glass](https://www.meetup.com/Breaking-the-Glass-Womens-Networking-Group/ "Breaking the Glass") **|** DJ Chido Machine **|** **|** [IBM Design Studio](https://www.ibm.com/design/studio.shtml "IBM Design Studio") **|** [Moojo](http://moojo.net/ "Moojo") **|** **|** [OwnYourSpot](https://www.yallzi.com/ownyourspot/#/shared/5847a3f6e4b0088800c78c6a "OwnYourSpot") **|** [Kendra Scott](http://www.kendrascott.com/ "Kendra Scott") **|** **|** [NAAVA](http://www.naava.com/ "NAAVA") **|** [Nothing Bundt Cakes](http://www.nothingbundtcakes.com/bakery/tx/austin-westlake "Nothing Bundt Cakes") **|** **|** [Jet’s Pizza](https://online.jetspizza.com/r/jetspizzatx004.html "Jet's Pizza") **|** [Topo Chico](http://www.topochicousa.net/#default "Topo Chico") **|** **|** [JuiceLand](http://www.juiceland.com/ "Juice Land") **|** [Lick Honest Ice Creams](http://www.ilikelick.com/ "Lick Honest Ice Cream") **|** **|** [Tito's Handmade Vodka](http://www.titosvodka.com/ "Tito's Handmake Vodka") **|** [Big Frog Custom T-Shirts](http://www.bigfrog.com/southaustin/ "Big Frog Custom T-Shirts")**|**

December 19, 2016
Next →

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

April 18, 2024