Our mission is to accelerate the next generation of supply chain with specialised data extraction. Our product connects to any email inbox or unstructured data source and automatically extracts data from emails & attachments in real-time - outputting a clean, structured feed via API.
We enable teams to shift towards high-value tasks and organisations to build for the future.
In the last year, we've processed over 15 million emails from some of the largest global shipping companies - both public and private. Example clients include dry bulk shipping companies, tanker owners, bulk shipbrokers and freight forwarders. In 2018, we've experienced huge growth both in logos & MoM % revenue - 2019 we're set to more than triple this.
We are one of the few London-based startups backed by Y Combinator. In 2017 we closed a 2.5 million USD seed round - from Cherubic, AME Cloud and Founders Fund.
Our product is split in two parts. The first part is our website where the Frontend is built in React using the latest ECMAscript release. The backend of the website is written in the Node.js framework Loopback. It is used as a REST API with strong ACL for the website, but at the same time used for a public customer API. Our main database is postgres, but for caching we use Redis. Everything is hosted on AWS.The second part is the data processing and machine learning part. This is mainly written in Python and mainly run via Docker on AWS. We import and process various data sets, like live satellite tracking data from ships. For our main machine learning pipeline we use Kinesis with Lambda functions and the Serverless framework. We use CircleCI with Nightwatch for E2E testing.