Feasibility questionnaires ask sites to predict their own enrolment, and the answers are optimistic. A ranking built on what sites have actually done is a better starting point for the people who choose.
AI site selection for clinical trials ranks candidate sites and investigators on evidence: their history in comparable registered trials, your own enrolment and data-quality records from past studies, competing trials recruiting the same population nearby, and whether the protocol’s procedures fit what the site can do. Each ranking shows its reasons, and your feasibility and clinical operations team makes the selection.
The same machinery helps after selection. Pre-screening support at a site matches the protocol’s criteria against records the site already holds, inside the site’s own systems, and suggests candidates for the investigator to review. It never decides eligibility.
We back-test the ranking on your completed studies: given only what was known at selection, would it have ranked the sites that actually enrolled above the ones that did not? That comparison, on your data, is the evidence for using it, and it tells you which inputs carry weight in your therapeutic areas. Where pre-screening touches patient data, it runs on the site’s infrastructure under GDPR Article 9 and the controller’s lawful basis, with every suggestion logged for review.
It combines public registry history, a sponsor’s or CRO’s own site performance data and population and competition signals into a ranked list with reasons. The value is replacing self-reported feasibility estimates with what sites have actually delivered. The feasibility team still chooses, because local knowledge, contracts and ethics timelines rarely appear in data.
It can help sites find more of the eligible patients they already see, by matching protocol criteria to records held at the site and suggesting candidates for the investigator. It does not recruit patients or decide eligibility. How much it helps depends on how much of the criteria are recorded in structured data, which we check on a sample first.
At minimum the protocol and access to public registries. The ranking gets much better with your CTMS history for sites you have used: enrolment, screen failures, start-up times and data quality. Patient-level data is only needed for site pre-screening, and then it stays inside the site’s own systems.
What we built, what stage it is at, and a link to the live thing wherever there is one.
yourOS is an operating system with an AI at its heart. You talk to it like a person, out loud or typed. It makes your calls, plans your days and works on your projects with a crew of agents, on your own private server. Our own product, built from the first commit; the waitlist is open.
Website, backend and app assets for Sonora, a free AI sound-therapy app on iOS and Android published by Cognitive AI.
Brand, website, prototype, apps on five platforms, the AI backend and the algorithm-intelligence pipeline for Podswap, a social growth engine that runs without a human in the loop.
In closed beta: Roxy, a private AI assistant with permanent memory running on infrastructure the user owns. Brand, site, product, backend and conversational design.
Live at coherence.com: brand identity generated with AI agents we directed, the motion system and website for the group behind Sonora, AboutAI, WakeUp and MudShadows. Agent work remains in build.
Live at domainbooth.com for DomainBooth, a premium domain brokerage: a new animated mark, every page redesigned and rebuilt with designed mobile layouts, and a custom CMS for its sales record, featured names, press and enquiries.
Start by back-testing a ranking on two of your completed studies.
30-minute technical call · no deck