Elenjical develops A.I. powered fintech apps

South African financial IT consultancy Elenjical has developed three machine learning applications that use artificial intelligence to marshal large and diverse amounts of stored information from multiple sources as well as generating proprietary code from natural language inputs to interact with complex systems and data sources

“Our goal is to reshape the traditional way our clients interact with data,” says Bereket Demeke, ES’s Executive. “In the complex landscape of financial markets our new apps are not just tools - they are methods enabling clients who work in fintech sector to engage with their data effortlessly,” he explains.

 

Three pillars of innovation

Elenjical’s applications are designed to provide a cohesive, unified method for sourcing and synthesising information across financial companies’ complex channels. They promise substantial time savings by cutting the hours spent on repetitive tasks, increasing automation, and moving businesses towards greater operational efficiency and smarter resource management.

In particular, Elenjical’s Information Retrieval App transforms access to internal knowledge bases, including SharePoint and Confluence libraries. Operating with a conversational AI interface, it lets company employees work with information faster. The app also reads and extracts insights from various document formats such as PDFs, PowerPoints, and Word documents, giving fast access to the data teams need.

“Unlike generic AI models, such as Chat GPT, our app understands domain specific information such as financial markets and capital markets technologies. That’s making it a must-have tool for financial professionals,” says Siju Mammen, technology lead at the Elenjical.

Natural Language to Proprietary Code App targets the generation of proprietary code from natural language. The first use case of this application was tested for generation of the Murex MSL code. It gives developers a real head start in coding for specialised financial applications. This marks the first version of the app, currently requiring a developer to operationalise the code. In upcoming editions, Elenjical aims to evolve it into an agent model, enabling it to independently deploy, run, and test the code.

Natural Language to SQL App transforms natural language queries into SQL valid for a given database schema. It’s designed to handle structured data queries in complex financial databases. Where the Information Retrieval App deals with unstructured data like meeting notes or PDF documents, this application focuses on structured data already stored in a system, letting more people query it directly without writing SQL themselves.

A vision for the future

The company is testing and improving these applications internally, and has started an AI consulting practice to bring these services to market. The strategy pairs technological innovation with sector-specific expertise, aimed at building AI capability the financial sector can use.

“We are merging our deep understanding of financial markets with AI to create better-performing, niche services. Our aim is to be at the forefront of AI integration in the financial sector, offering something truly unique”, says ES’s founder and CEO, Tinu Elenjical.