From funder fit to final report: a blueprint for Grant Writing

You write grants for several nonprofits at once, and every one of them is on a deadline somebody else set. One client needs a letter of inquiry by Friday. Another needs a full proposal with a need statement, a logic model and a budget narrative that explains every line. Your funder research lives in a spreadsheet. Your best paragraphs live in old proposals you search by memory. The method lives in your head.

This page is a blueprint for a Flow Playbook that carries that method. It is not built. AI Consulting is a Playbook that exists today, and its launch story is the walkthrough for every step below. This blueprint is yours to take. Build it from your own method, put your name on it, and launch it as your Playbook. If you do, I would like to hear about it.

The opportunity

The money is there and it is still growing. Americans gave $617.2 billion to nonprofits in 2025, up 5.7 percent, and foundations gave $117.15 billion of it. In the 2026 State of Grantseeking survey, 93.5 percent of organisations applied to private foundations, and the median largest award was $90,000. More than half said one or two people secured that award. One of those people is often you.

AI is already in the work. Instrumentl found drafting proposals is the most common use of AI among grant professionals, at 46 percent. Of those using it, 71 percent said they could write and submit a proposal in under a week. Across the sector, 92 percent of nonprofits now use AI in some form. Yet only 7 percent report a major improvement to their mission, and 81 percent use it ad hoc without writing down what works. The tool is in. The method is not written down.

The rules are moving under everyone. The 2024 revision of the Uniform Guidance raised the de minimis indirect rate from 10 to 15 percent for awards issued on or after October 1, 2024. On August 7, 2025, Executive Order 14332 put every new federal funding notice under senior appointee review and told agencies to write them in plain language. Meanwhile 84 percent of nonprofits with government funding expect cuts, which sends more of them to the same foundations. The Bureau of Labor Statistics expects about 10,000 openings for fundraisers a year, so your method will keep being taught to someone new. And the custom GPT some grant writers loaded with their boilerplate and past proposals retires on December 11, 2026. A Playbook is plain files in your own GitHub. Nobody can retire it.

The signals

Each figure measures something narrower than it sounds. Surveys count who answered. Vendor research counts a vendor’s view. A market estimate is a model. Read them as a direction, not a forecast.

What your Playbook holds

The figure at the top of this page is the folder as it could sit on GitHub. Six Markdown files. Here is what each one does.

The README is the front page. It says who the Playbook is for, what a reader will have at the end, and the order to read the documents in. A stepped figure shows a funder prospect becoming a submitted proposal. An isometric figure maps the path.

Funder Fit Method is where every engagement starts. How you find funders and what goes into the funder research register. Funder, program, deadline, what they gave last year, who the program officer is, and when you last checked. A Register Skill draws it. A Scorecard turns your fit questions into a score a client can see. A Go or no-go form records the decision and the reason.

Proposal Template by Section is the backbone. Need statement, goals and objectives, logic model, methods, evaluation plan, budget narrative and sustainability plan, in the order a reviewer reads them. A Workflow Path draws the proposal from the funder’s notice on the left to the submitted file on the right. The logic model is a Diagram, so inputs, activities, outputs and outcomes sit in boxes a client can follow. A table holds the question each section must answer.

Boilerplate Library Standard is how the client’s standard paragraphs are kept honest. Mission, history, each program, the numbers served, the board, the audited financials. Every paragraph lists its sources. A claim nobody has confirmed is marked to check, and Flow counts the marks until you answer them. A Change Summary shows a client what changed in their boilerplate and when.

Reporting Calendar and Post-Award Report is what a client forgets until a funder writes. A timeline chart shows every report due to every funder. A submission checklist is an Approval Card, so the executive director signs before anything goes out and the record stays with the proposal. A report intake form collects the outcomes and spending a post-award report needs.

Worked Example is a funder register, one full proposal and one post-award report for a made-up client, filled in end to end. A reader learns more from one finished proposal than from ten rules.

What Flow does for this work

Chat answers from the folder. The README carries the questions a reader might ask. What goes in a budget narrative. When is the next report due. An empty Chat offers them as buttons, and every answer links to the document it came from.

A Register Skill draws the funder research register. You describe how you track prospects in the Fit Method, and the Skill draws the register from that text. It uses only what the text says and names what is missing. It waits in Review Changes until you keep it.

A Form records the go or no-go. The Fit Method ends with a Decide form. The client picks a funder from the register, chooses go or no-go, and writes the reason. Flow records the option and the reason, so it is still there when the funder comes round again.

A Job keeps the funder’s rules current. Bring a funder’s guidelines page in with New from Web Page and choose Follow the source. Each Jobs run reads the page again and brings changes in where you have not edited. The watch says what it found.

The import checklist settles a client’s old files. A client’s last funded proposal comes in from Word, their budget from Excel with its tables kept, and their 990 from PDF. Each gets a short checklist in Sources, and Walk Through with Chat takes the open items one at a time.

Sources and Change Summary travel with the proposal. A finished proposal shows what it was made from, and marks a source that changed since. After the yearly boilerplate refresh, the Change Summary on each proposal says which paragraph moved.

A door for your own agents. With Flow Pro, Settings opens a door for the Claude Code or Codex you run in Terminal, as Read or Read and propose. Your agent can read the Playbook’s reading order and propose a draft post-award report. It arrives in Review Changes under the agent’s name.

How you build it in Flow

The AI Consulting story walks every one of these steps on a real screen. Follow it with your own material.

1. Add an empty folder and choose it. Chat answers from the folder before any document exists. The walkthrough shows it at an empty folder, and Chat already in it.
2. Ask Chat for the README. Describe who the Playbook is for and what you want a reader to have at the end. Chat writes it in your voice and marks every claim it cannot stand behind. See a front page, in the author’s voice.
3. Bring in what you already have. The funder spreadsheet, a funded proposal with the client’s name changed, the funder guidelines page you cite most. New from Web Page turns a page or a shared AI chat into a document with its links kept. See an old AI chat became a reference.
4. Let Ideas pick a Skill. Press Suggest on your Fit Method document. Ideas reads the sections and names a Skill for each, a Register for the funder list, a Workflow Path for the proposal. A figure or a form waits in Review Changes until you keep it.

5. Ask Chat for the next document with your own pages as sources. The Proposal Template can be written from your Fit Method and the funded proposal you brought in. Repeat until the path is done. See the next document, from his own pages.
6. Review every change. When you merge two sections of the template or rename the register, every page that pointed at it follows. See Review changed the plan, and the source followed.

Apply it to a client job

A Playbook is for using, not only reading. Say a small reading program signs you to win its first foundation grant. Open the Playbook, start a folder for the client, and drop in their last proposal, their budget and their 990. Ask Chat to score the funders on their list against the Fit Method, then draft the need statement from the Proposal Template and the client’s boilerplate. Chat marks every number it cannot stand behind, and you confirm each one from the 990. A Skill draws the logic model from the methods section. The executive director ticks the submission checklist and signs. When the award letter comes, the report dates go into the Reporting Calendar.

When the funder asks a question you did not expect, the answer goes into the Boilerplate Standard, and the lesson goes back into the Fit Method. A new associate can read the Fit Method and the Template on their first day and take a client from prospect to submission the way you would.

Riverbend Reading Room / README.mdHarbor Trust proposal / Need statement.mdHarbor Trust proposal / Logic model.mdFunder Research Register.mdHarbor Trust proposal / Submission checklist.mdProposal Template by Section.md Imported · 3 to check2 claims to check1 change to reviewKeptSigned off6 files sent

Riverbend Reading Room

Riverbend Reading Room / README

Proposed

Folder

Imported · 3 to check

Riverbend Reading Room

Harbor Trust proposal / Need statement

Proposed

Callout

2 claims to check

Riverbend Reading Room

Harbor Trust proposal / Logic model

Proposed

Diagram · Flowchart

1 change to review

Riverbend Reading Room

Funder Research Register

Proposed

Register

Kept

Riverbend Reading Room

Harbor Trust proposal / Submission checklist

Proposed

Approval Card · Sign off

Sign off

Signed off

Riverbend Reading Room

Proposal Template by Section

Publish · GitHub Repository

github.com/…/grant-method

README.mdFunder Fit Method.mdProposal Template by Section.mdBoilerplate Library Standard.md

Publish to GitHubCancel

6 files sent

01Start the client folder02Draft the need statement03Draw the logic model04Check fit and keep05Director signs off06Publish the update

Publish it, and keep it current

When the folder is ready, choose Publish and then GitHub Repository. Flow sends the files and nothing else. A reader brings the Playbook in with File, then New from GitHub, and the folder’s address. Check the repository’s visibility first. Your method can be public while every client’s proposals, budgets and 990s stay in their own folder on your Mac.

When a rule changes and you publish again, every reader’s copy shows the update as a change they review. They keep their own edits. Nothing is replaced behind their back.

The same source can also become a GitHub Pages site, a PDF, an EPUB, or Word and Excel files for a client’s team. Chat on the Playbook, and the figures a reader steps through, stay in Flow.

What it costs

Bringing any Playbook into Flow is free on Base. Writing with Chat, and Chat on a Playbook, need Flow Pro at $10 a month. Publishing to GitHub needs the Publish add-on too, another $10 a month. There is no fee per Playbook, so publish one or twenty for the same price. Any AI you connect follows the terms of that service. Publishing does not bring clients on its own. It gives the clients you earn a living copy of your method.

Start here

Read the walkthrough once, end to end. Then add an empty folder in Flow, name it, and tell Chat in three sentences how you take a client from funder research to a submitted proposal. The README it writes is the first document of your Playbook. If you want to talk it through first, the Playbooks page has one email address and four questions.