A good proposal is the researcher’s idea, argued well, inside a funder’s rules. The idea cannot be generated. The arguing can be drafted from what the researcher has already written, and the rules can be checked.
All Universities & Research Institutes →
AI tools for research grant writing, built for an institution, draft proposal sections from the researcher’s own papers, prior proposals and notes, structured to the funder’s template, and check the result against the call’s rules: page limits, mandatory sections, eligibility, budget categories and evaluation criteria. The researcher writes the idea and owns every word submitted; the research office gets consistent compliance checks across every application.
This matters because funder policies are converging on the same point: applicants are responsible for their proposals, must not breach confidentiality, and in some cases must disclose AI use. A system that drafts from the applicant’s own work, logs how AI was used and runs on institutional infrastructure fits that much better than a public chat tool.
rules, criteria, limits
aims, idea, notes
papers, prior proposals, CV
section by section
limits, sections, criteria
before the researcher submits
Generally yes, within the funder’s rules, and those rules vary. Most hold the applicant fully responsible for content and originality, prohibit sharing confidential material with third-party tools, and some require disclosure of AI use or limit applications substantially generated by AI. Check the current policy for each call; we build systems that keep drafts grounded in your own work and log AI use.
For an individual, a general model can help with structure and clarity. For an institution, the better question is which system can draft from your researchers’ own outputs, apply each funder’s rules and keep unpublished ideas on your infrastructure. That combination is rarely available off the shelf, which is why we build it around your research office.
No. Funders judge the idea, the team and the plan, and those come from researchers. AI takes over assembly: restating track records, fitting text to templates and limits, keeping institutional sections consistent and catching non-compliance. That frees time for the part reviewers actually score.
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 call your research office supports every year.
30-minute technical call · no deck