The programme has not changed since the last bid. The questions, the word limits and the outcome framework have. Most grant writing time goes on reshaping the same evidence, and that is the part a model does well.
All Nonprofits & Charities →
AI for grant applications means a drafting system that answers each funder’s questions from your organisation’s own material, past applications, evaluations, budgets and outcome data, and shows where every sentence came from. The grants lead still decides what to claim and submits the bid.
That framing matters because the failure mode of a general chat tool in charity grant writing is fluent invention: a plausible outcome figure, a partnership that was only discussed, a beneficiary number from the wrong year. Funders check, and an application that overclaims damages a relationship that took years to build. So the system is built to retrieve before it writes, and to leave a visible gap when the evidence is not there rather than filling it.
questions, limits, criteria
past bids · evaluations · budgets
to the word limit, with citations
figures against budget and accounts
and submits on the portal
flagged, never filled in
Usually, with care, and the funder’s own rules decide. Some funders now publish guidance on AI use in applications, ranging from disclosure to restrictions, so check each one before drafting. Across all of them the expectation is the same: the organisation stands behind every claim. A system that drafts from your own evidence, cites it, and leaves a named person to edit and submit fits that expectation far better than pasting questions into a chat window.
Your previous applications (successful and not), end-of-grant reports, evaluations, the current budget and accounts, and whatever outcome data you collect. Rejected bids are useful too, because the feedback shows what funders found weak. Most of the setup work is gathering and tidying that library, and it is worth doing regardless of AI.
It can read funder guidance you collect, or listings from a directory you already subscribe to, and score them against your programmes and eligibility so the team reads the promising ones first. It does not replace a subscription to a funding database, and the decision to apply stays with the team, because fit includes relationships and timing the documents do not show.
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.
Bring one upcoming application and the documents behind it. We will show what a cited first draft looks like.
30-minute technical call · no deck