GridSentry

Overview page; includes basic metrics and any alerts that need to be attended to
Pole example page; shares info on assessments, schedule, and sensor readings
Agent Activity page; users can monitor each agent and their workflow

Inspiration

As a team, we were inspired by our team members' experience developing AI models used for predictions.

What it does

We install our model and software on company poles that track weather, vibrations, and tilt relative to gravity. Using scheduled maintenance and visits, the poles are photographed and uploaded to the online portal. The data is gathered and sent to our app, where an admin can view and approve any reports to be sent to maintenance. The AI model can make their own alerts, ranked by priority to be attended to.

How we built it

The original build was completed using HIVE, Omega Creative Media's proprietary AGS development software; updates and changes were made using Codex, Claude Code, as well as various frontend and backend skills developed by the team members.

Challenges we ran into

One of the biggest challenges we faced was taking our idea and applying it to a business model for a startup. The pricing, expenses, and structure of our business were difficult to pinpoint, but we were able to create a startup with a supported path to market.

Accomplishments that we're proud of

We are proud of both the front end and back end of our website. We are thrilled with the outcome and full-bodied nature of the project.

What we learned

A lot of the learning opportunities came from our brainstorming early in the hackathon. We realized that companies, including those sponsoring this event, can be lacking in the agentic AI operations division, and we want to help push them forward.

What's next for GridSentry

We hope to either become a publicly available SAAS or a privately purchased software. Our main goal is to branch out to clients in the United States to boost their productivity and efficiency in their maintenance using agentic operations.