Harbor

Harbor is a new, AI-enabled system of record for clinical trial data that replaces legacy electronic data capture (EDC) systems. Today, medical device and pharma companies spend months setting up custom EDCs that research sites then spend hours per subject per day entering data into. With Harbor, the EDC is spun up simply by reading your clinical trial protocol and research sites upload raw source documents into the platform, skipping the tedious and error-prone data entry process altogether. EDCs haven’t fundamentally changed since the 1990s. They are passive, regulatory compliant data bins that cause massive trial delays, coordinator burnout, and weeks of back-and-forth to resolve data errors. Because of this, data management currently consumes ~30% of total clinical trial budgets. With LLM and document extraction capabilities finally reaching the accuracy, reliability, and traceability required in high-risk domains, Harbor is redefining the way data is collected and monitored in clinical trials, all while remaining fully GCP- and 21 CFR Part 11 compliant. After months of building our initial product, our platform is now live with its first few clinical studies. For our largest customer and their 1600 subject randomized trial, we were able to use our internal tools to get their study database configured in just one week, which was ten times faster than legacy EDC vendors quoted. We built Harbor because we lived through this problem. Albert spent four years in clinical trials and regulatory strategy for a medical device startup, spending weeks at clinical sites watching coordinators battle legacy software firsthand. Nate brings the technical firepower, having built scalable software at Google and Ramp and as employee #1 at a previous YC startup.