AnnouncementIntroducing MongoDB 8.0, the fastest MongoDB ever! Read more >>

Ceto AI Leverages MongoDB to Drive AI Insights for Preventative Maintenance in Maritime Industry

an illustration of a man with a tablet working at the harbor.

INDUSTRY

Maritime (Transportation – Logistics)

PRODUCTS

MongoDB Atlas
Atlas Vector Search

USE CASE

Gen AI

CUSTOMER SINCE

2023
Ceto AI is a maritime technology company that uses AI to provide predictive analytics to the maritime insurance sector. The company is using MongoDB Atlas and MongoDB Atlas Vector Search to integrate AI with real-time data collected from thousands of sensors across its customers’ fleets. This allows Ceto to predict and preempt potential failures, streamline operations, and manage risks proactively.
Tony Hildrew, Founder & CEO, and Ben Harrison, CTO, explain how they use Atlas Vector Search and AI insights at Ceto. This transcript has been edited for clarity.
INTRODUCTION

Ceto is a maritime-first technology company. We capture and analyze high-frequency data to prevent machinery breakdowns and deliver connected insurance products to ship owners.

Working with MongoDB has allowed us to deploy models very quickly without having to worry too much about their structure, about the scale, and about the data volume involved.

These ships do not stop—365 days a year, 24 hours a day, seven days a week—they move 90% of global trade. Everything that we rely on in our daily lives has some connection to the maritime industry.

THE CHALLENGE
AI is critical to everything that we're doing on the data side of things. There are far too many data points for us to really understand and far too many patterns hidden deeply—layers within the data sets—for a human brain to get their head around. So, we're using machine learning models and AI models to detect these patterns and spot trends, similarities, and anomalies before we typically could.
THE SOLUTION

Vector Search is becoming more and more important in our decision support system. When our platform detects a potential anomaly, we have an understanding awaiting as to what the root cause of that problem could be. We are taking reams of data sets and what we're calling “points of interest” within the data that we're labeling and starting to build context around.

We're growing quickly. We don't really know where we're going to be six months, 12 months, 18 months from now. So we needed a non-relational database that can scale that we don't have to be worrying too much about schemas for, that we can plug new data into very quickly and start generating products from. So, from a starting point, MongoDB is perfect in that regard.

What will your story be?

MongoDB will help you find the best solution.