Vipul H. Harihar

When Vipul Harihar, MS 2023, was hired by GenTrust, a wealth management firm with offices in New York, Miami and Puerto Rico, the expectations were straightforward: clean up code, support internal systems and help modernize a traditional trade operation.

But when company leadership asked if he could do something with AI, he took it as a serious engineering challenge. Four months later he had designed and built an AI-powered proprietary operating system that integrates with internal and third-party software, and it is now the core of the firm's trading technology platform.

The platform, launched in July 2025, uses the same kind of language model behind tools like ChatGPT, adapted into a secure system built for financial operations. Many AI tools are unusable in wealth management given their tendency to hallucinate and the risk that user data could be shared or used to train models. Harihar built a custom system that turns thousands of internal documents, workflows and compliance rules into information the model can draw on, without sharing any data.

He also reduced hallucinations by limiting what the model is asked to do. The platform operates within tight boundaries and, unlike most language models, asks clarifying questions when it is unsure.

Perhaps most remarkable: Harihar built the entire system himself. Front end, back end, mobile integration, dashboards, data pipelines and the product's visual design. The total development budget was fifty dollars a month, covering access to the language model API.

“I didn't come to DSI with all the answers. But I left with the ability to build something from start to finish. Columbia teaches you how to operate without a fixed blueprint.”