Funders ask for FAIR data and a data management plan. Researchers have files on drives and little time to describe them. The gap between the two is mostly metadata, and metadata is something a model can draft.
AI-assisted research data management reads datasets, code and the papers they support, drafts the descriptive metadata a repository needs, and keeps the data management plan in step with what the project actually produced. A data steward or the researcher approves each record before it is published. The aim is datasets that are findable, accessible, interoperable and reusable to the FAIR principles, without the description work falling entirely on the researcher.
We build on the repository you already run, such as Dataverse, DSpace, InvenioRDM or Zenodo, and on your CRIS, rather than adding another research data management system. Persistent identifiers come from your existing DataCite or equivalent arrangement.
dataset, code, publication
formats, variables, contents
your schema and vocabularies
edit and approve
repository and CRIS updated
held for access decision
It is the set of systems an institution uses to plan, store, describe, preserve and share research data: data management plan tools, active storage, repositories and the CRIS that links data to projects and outputs. AI adds a layer on top that drafts descriptions, checks plans against reality and flags sensitive data, so the existing systems hold better records.
FAIR depends mostly on rich, accurate metadata: what the data is, how it was made, what the variables mean and how it can be reused. That is the part researchers skip under time pressure. A model can draft it from the files and the paper, mapped to your schema, and a steward can approve it in minutes instead of writing it from scratch.
It can be, if the models run on institutional or EU sovereign infrastructure, processing has a lawful basis with Article 89 safeguards, and access is controlled. We design for that and flag personal data before anything is shared. The legal assessment, and any ethics committee requirements, remain your institution’s.
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 a sample of deposits your stewards found hardest to describe.
30-minute technical call · no deck