Spotlight on Two Aussie Start-Ups Building AI Services on MongoDB Atlas

Australian-based Eclipse AI and Pending AI are using the power of MongoDB Atlas to bring their AI ideas to life and blaze new trails in fields including pharmaceutical R&D and customer retention.

With the recent advancements in the fields of AI and generative AI, innovation has been unleashed to new heights. Many organisations are taking advantage of technologies such as Natural Language Processing (NLP), Large Language Models (LLMs), and more to create AI-driven products, services, and apps.

Amongst those that are blazing new trails in the AI space are two Australian start-ups: Pending AI, which is helping scientists and researchers in the pharmaceutical space improve early research & development stages, and Eclipse AI, a company that unifies and analyses omnichannel voice-of-customer data to give customers actionable intelligence to drive retention.

What they have in common is their choice to use MongoDB Atlas. This multi-cloud, developer data platform unifies operational, analytical, and generative AI data services to streamline building AI-enriched applications.

Here is how we are helping these two Australian start-ups create the next generation of AI products faster, with less complexity, and without breaking the bank.

Pending AI improves pharmaceutical R&D by leveraging next-generation technologies

Pending AI has developed a suite of artificial intelligence and quantum mechanics-based capabilities to solve critical problem statements within the earliest stages of pharmaceutical research and development.

The Pending AI platform is capable of dramatically improving the efficiency and effectiveness of the compound discovery pipeline, meaning stakeholders can obtain better, commercially viable scaffolds for further clinical development in a fraction of the time and cost.

Building its two artificial intelligence-based capabilities - Generative Molecule Designer and Retrosynthesis Engine - was a mammoth task.

The known number of pharmacologically relevant molecules in chemical space is exceptionally large, and there are over 50 million known chemical reactions and billions of molecular building blocks - expert scientists have to undergo cost- and time-inefficient trial-and-error processes to design desired molecules and identify optimal synthesis routes to them.

Pending AI needed a database that could handle a very large number of records, and be highly performant at that scale, as required by the vastness of chemical space.

A few databases were considered by Pending AI, but MongoDB kept standing out as a battle-tested, reliable, and easy-to-implement solution, enabling Pending AI’s team to build a highly performant deployment on MongoDB Atlas.

“As a startup, getting started with the community edition of MongoDB and being able to run a reliable cluster at scale was a huge benefit. Now that we’re starting to leverage the AWS infrastructure in our platform, MongoDB Atlas provides us with a fully managed solution at a low cost, and with a Private Endpoint between our AWS deployment and MongoDB cluster, we have kept latency to a minimum, and our data secure,” said Dr. David Almeida Cardoso, Vice President, Business Development at Pending AI.

Pending AI’s Generative Molecule Designer has been built as a machine learning model on MongoDB Atlas, trained to understand the language of pharmaceutical structures, which allows for automated production of novel compound scaffolds that can be focused and tailored to outputs of biological and/or structural studies.

The Retrosynthesis Engine is also built using a set of machine learning models and MongoDB Atlas, trained to understand chemical reactions, which allows for the prediction of multiple, valid synthetic routes within a matter of minutes.

“We’re also excited to explore the new Atlas Search index feature in MongoDB 7.0. We hope this will allow us to integrate some of the search functionality, which is currently complex to manage and maintain, directly into MongoDB, rather than relying on a separately maintained Elasticsearch cluster,” added Cardoso.

Being part of the MongoDB AI Innovator program also allowed Pending AI to explore leveraging cloud infrastructure to scale its platform and test newer versions of MongoDB quickly and easily.

Eclipse AI turns customer interaction insights into revenue

Eclipse AI is a SaaS platform that turns siloed customer interactions from different sources - these can be customer calls, emails, surveys, reviews, support tickets, and more - into insights that drive retention and revenue.

It was created to address the frustration of customer experience (CX) teams around the number of hours and man-weeks of effort needed to consolidate and analyse customer feedback data from different channels. Eclipse AI took on the challenge of solving this issue and worked hard to find a way to offer customers faster and more efficient ways to turn customer feedback into actionable insights.

The first problem was consolidating the voice-of-customer data which was so fragmented; the second was analysing that data and turning it into specific improvement actions to improve the customer experience and prevent customer churn.

Because MongoDB Atlas is a flexible document database that also can store and index vector embeddings for unstructured data, it was a perfect fit for Eclipse AI and enabled its small dev team to focus on building the product very efficiently and quickly, without being burdened with managing infrastructure.

MongoDB Atlas also comes with key features such as MongoDB Atlas Device SDKs (formerly Realm) and MongoDB Atlas Search that were instrumental in bringing Eclipse AI’s platform to life.

"For us, MongoDB is more than just a database, it is data-as-a-service. This is thanks to tools like Realm and Atlas Search that are seamlessly built into the platform. With minimum effort, we were able to add a relevance-based full-text search on top of our data. Without MongoDB Atlas we would not have been able to iterate quickly and ship new features fast,” commented Saad Irfani, co-founder of Eclipse AI.

“Best of all, horizontal scaling is a breeze with single-click sharding that doesn't require setting up config servers or routers, reducing costs along the way. The unified monitoring and performance advisor recommendations are just the cherry on top.”

G2 rated Eclipse AI as the #1 proactive customer retention platform globally for SMEs, a recognition that wouldn’t have been possible without the use of MongoDB Atlas.

Exploring your AI potential with MongoDB

MongoDB Atlas is built for AI. Why? Because MongoDB specialises in helping companies and their developer teams manage richly structured data that doesn't neatly fit into the rigid rows and columns of traditional relational databases, and turn that into meaningful and actionable insights that help operationalise AI.

More recently, we have added Vector Search - enabling developers to build intelligent applications powered by semantic search and generative AI over any type of data - and enhanced AWS CodeWhisperer coding assistant to our list of tools companies can use to further their AI exploration.

These are just a handful of examples of what is possible in the realm of AI today. Many of our customers around the world, from start-ups to large enterprises like banks and telcos are investing in MongoDB Atlas and capabilities such as Atlas Search, Vector Search, and more to create what the future of AI and generative AI will look like in the next decade.