§ Volume I · Thesis

Grants as files, read by agents.

an essay · 2026


I.Where grants live today

Trapped in web forms that AI cannot reach.

A typical grant platform is a web application. The proposal lives in a database row; the sections render as textareas; the history is whatever the platform chose to record. The user's tools — their editor, their agent, their version control — watch from outside the glass.

That was fine when the main thing you did with a draft was edit it yourself. It is no longer fine. The best drafting partners in the world now live one cd away, and they do their best work on a directory of files, not a 6,000-token prompt.

2023 was the year of the chatbot. 2024, RAG and finetuning. 2025, MCP and tool use. 2026 will be the year of the computer environment and filesystem.

— Alex Albert, Anthropic

The rest of this essay is the reasoning behind GrantKit: what changes if a proposal is a set of files; why the filesystem is a better substrate than a web UI for this kind of writing; and what the cloud is still good for when files win.


II.Three reasons

Why files beat a web form.

i. Context

The agent reads everything, not a snippet.

A web form hands the model the single section you are editing. A filesystem hands it the budget, last year's proposal, the solicitation PDF, the reviewer's letter, and every response you have drafted — and lets the model decide what to pull in. That difference is the difference between a copyeditor who skimmed the abstract and one who read the whole file.

ii. Provenance

Every edit is a reviewable diff.

Git is a log. A web "undo" is a guess. When your broader impacts section drifts across three weeks of revisions, you want to see the line where the outreach plan moved from "publications" to "six summer REU slots," who made the change, and when. That is what git log gives you. That is not what a revision history sidebar gives you.

iii. Portability

The model is yours to choose.

Today, Claude. Tomorrow, a local model running on your laptop. Next quarter, a model that does not exist yet. A grant stored as plain markdown is not an AI lock-in bet. It is writing, held in the same medium as writing has been held for forty years, and it will outlive every AI vendor in the category.


III.What the cloud is for

Files for writing, cloud for sharing.

"Everything in files" sounds austere. It is not. A grant in flight is rarely a solo document. Advisors read drafts, collaborators write sections, program officers want a shareable link. None of this is served well by passing a zipfile over email.

So GrantKit treats the cloud the way you treat GitHub: the files are the source of truth on your machine; the cloud is the canonical place where teammates see them, where a program officer clicks a link, where permissions live. A push reconciles. A pull reconciles back. The same mental model you already have for code.

The risk with any such system is silent data loss: you push a stale version and overwrite a teammate's work without knowing. We built conflict detection into the sync from day one. Every push checks whether the cloud has moved since you last pulled; if it has, the push stops and prints a plan. You choose what to do. Nothing is overwritten without your say-so.


IV.The writing loop

Pull. Edit with your agent. Push.

The loop is the point. A grant is a long document written in small motions: tighten the abstract by forty words, add a concrete metric to broader impacts, reconcile the budget with the narrative, check the citations. Each motion benefits from an agent that has the whole corpus at its disposal. Each motion wants a diff, not a Save button.

When the loop is fast, a proposal stops being a dread-object you open twice a week and becomes something you edit the way you edit code — incrementally, with confidence, with history. Deadlines become less frightening because the last seventy-two hours are no longer where the work compresses.


Write the next grant the way you write code.

pip install grantkit