Supernova Technology Innovation & Technology Culture

How do you use AI in your day-to-day work, and what influence does it have on your work?

I use various AI-powered tools in my daily work for different tasks. For example, I use the Intelligent Recap feature within Microsoft Teams to automatically generate meeting summaries or action items. My teammates and I use a specialized tool to draft and refine product requirement documents, also known as release notes. I also use the tool to create a repeatable process for summarizing feedback collected via various methods, such as email and Jira tickets, and extract common themes or conflicting information more efficiently. I’m also actively exploring additional use cases of AI in preparing product training videos based on published product requirement documents and product marketing brochures based on request-for-proposal documents. 

How does your team ensure AI is being leveraged responsibly?

We’re often trying to feed proprietary, private or sensitive data into an AI engine or tool in exchange for insight. There are always concerns around data security, privacy and access. At Supernova, we’ve taken the position of utilizing AI in a highly controlled environment by developing specialized tools using self-hosted and self-trained models. In the case where a third-party AI tool is needed, our information security team performs extensive due diligence before a tool can be whitelisted for employee usage. Data content has to be desensitized and cleaned before getting fed into any AI tool.

How has AI helped your team enhance customer research?

Supernova recently hosted a virtual user group conference, during which we invited actual users to share candid feedback about existing functions and about our upcoming product roadmap. Using AI, we were able to integrate meeting summaries with enterprise client profiles as well as integrate participant bios with a few prompts. The insights derived from this exercise actually revealed a misconception in our original user personas and introduced a brand new use case for which we have to create a more tailored marketing message.

What project are you most excited to work on in 2025, and what is particularly compelling about this work for you?

I’m most excited to work on integrating AI into our team’s day-to-day workflows. There’s plenty of opportunities available for us to hand off some of the menial and repetitive stuff that we do to AI. One such example is doing a first glance at code reviews to point out best practices or potential bugs that a human might miss. It would be great to essentially have an extra pair of eyes doing a sanity check on everything we’re doing.

What does the roadmap for this project look like? Who will you collaborate with, and what challenges do you anticipate having to overcome?

We’ll be starting small with only a single code repository and will hopefully expand our implementation to all the code merged into our main repos. Working with each development team is going to be critical to discovering the areas where AI falls slightly short or understanding how prompt engineering will come into play in order to hit the areas it misses on a first pass. Of course, when considering AI and proprietary code, privacy is always a concern. At Supernova, we’ve built out our own private, on-premises graphics processing unit compute cluster to host large language models locally. We’ll be making use of it for privacy-sensitive AI requests.

What in your past projects, education or work history best prepares you to tackle this project? What do you hope to learn from this work to apply in the future?

I’ve been heavily involved in developing our AI product, Prism. I believe my experience in this area has made me highly familiar with the shortcomings and advantages of AI and where it can be used. We’ll be using this project as a benchmark for future meshing of our day-to-day workflows with AI.

How does innovation show up in your company culture?

At Supernova, innovation shows up in how intentionally we apply AI to real-world problems. We’re constantly exploring how advances in large language models and intelligent automation can simplify complex workflows for financial institutions.

There’s a strong culture of ownership, and engineers are encouraged to experiment, test new approaches, and challenge assumptions. But innovation here isn’t about using AI for the sake of it. It’s about building technology that meaningfully improves clarity, efficiency and reliability for the people who rely on it every day.

What’s one recent innovation that improved user or employee experience?

One recent innovation was enhancing how we use LLMs to interpret and structure complex financial documents. By refining how our AI reasons through unstructured information, we significantly improved the consistency and accuracy of structured outputs. For users, that means less manual review and faster turnaround times. For our internal teams, it streamlined development and reduced time spent troubleshooting edge cases. It’s been a strong example of how thoughtful AI integration can elevate both product quality and employee experience.

How do you balance experimentation with stability?

In AI, innovation moves fast, while reliability is critical in financial services. We balance the two by building modular systems and rigorously evaluating new approaches before they reach production. 

We encourage experimentation, but it’s grounded in measurable outcomes and controlled rollouts. That allows us to evolve our technology while maintaining the trust and stability our clients expect. For us, “building better tech for people” means delivering AI that’s not only advanced, but dependable.