AI in admissions, built our way, answers applicants and students from the policies you publish and keeps their paperwork moving. It does not score, rank or reject anyone: under the EU AI Act, admission decisions are a high-risk use, and they stay with your admissions team.
All Education & EdTech →
An admissions or student-services inbox is mostly the same questions at volume: entry requirements, deadlines, which documents are missing, how fees and deposits work, what a CAS or visa letter needs, when accommodation opens, how to change module. The answers are in the prospectus, the handbook and the student record. The queue exists because the questions arrive at night, in many languages and in peaks around results and enrolment.
A student support chatbot that answers from those documents, with a link to the page it quoted, clears that load. One that improvises is worse than none, because an applicant who acts on a wrong deadline has a grievance. So it answers from policy or says it cannot, and hands over.
web, email or chat
welfare, hardship, appeal
record in the SIS or CRM
from published policy, cited
written back to the record
decisions and concerns
Some institutions use AI to help process applications, and the practice is contested. In the EU, AI that decides access or admission to education is a high-risk system under Annex III of the AI Act, with obligations on risk management, human oversight and documentation. We do not build systems that score or rank applicants. We build the administrative layer around the decision, which the admissions team makes.
Policies differ by institution and are changing. What is widely understood is that AI-writing detectors produce false positives, which makes them a poor basis for a decision about an applicant. Our admissions assistant does not run AI detection on applications. If an institution wants a policy on AI use in statements, that belongs in its published guidance and with its staff.
It should recognise them and step aside. Any message touching mental health, safety, harassment, hardship or disability support is routed to student services straight away, with the conversation attached and the relevant contact details shown to the student. The assistant does not counsel, and it does not try to resolve those conversations itself.
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 with one programme's admissions questions and the policy pages that answer them.
30-minute technical call · no deck