A close your clients can read: a blueprint for Accounting Advisory

You close the books for dozens of businesses and then answer the questions that come after. Why did cash drop when profit rose. What does the new deduction mean for us. Can we treat this as a repair. The close is a method you repeat every month. The explanation is a craft you have practiced for years. Both live in your head, in a checklist someone started in 2019, and in a folder of past emails you search when a client asks the same thing again.

This page is a blueprint for a Flow Playbook that carries that method and that craft. 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 know-how, put your name on it, and launch it as your Playbook. If you do, I would like to hear about it.

The opportunity

The accounting market is large and slow. US accounting services bring in about $158 billion a year and grew under 2 percent in 2026. Inside that slow market, one part is moving fast. Client advisory services grew 17 percent at the median practice in 2023, and the practices surveyed by CPA.com and the AICPA expected to double that revenue over three years. The growth is in explaining and advising, not in the close itself.

AI arrived in firms faster than almost anywhere else. Thomson Reuters found firm-level use of generative AI among tax firms went from 8 percent in 2024 to 34 percent in 2026. Wolters Kluwer’s 2025 survey found the share of firms using AI jumped from 9 to 41 percent in one year. Karbon’s 2027 report puts firms using at least one AI tool at 86.7 percent. The tools are in. What most firms do not have is a written way of using them that a new hire or a client can read.

The people to do the work are getting scarcer. Accounting degrees fell 6.6 percent in a year, and new CPA exam candidates fell by a third, from 42,626 to 28,082. The Bureau of Labor Statistics still expects 1.6 million accountants and auditors to be needed in 2035, with about 115,000 openings a year. The 2026 filing season was the first to carry the 2025 tax law, with a new form and about 164 million returns to explain to the people who filed them. And the custom GPT some advisors used to package their know-how 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 close becoming a note. An isometric figure maps the path.

Monthly Close Method is the backbone. The steps of your close, who owns each, and the checks that must pass before the books are called done. The checklist is an Approval Card, so the record of who closed what stays with the month.

Close Explanation Guide is the craft. How you turn a finished close into a note a business owner reads in five minutes. What goes first, what to leave out, how to say that cash fell while profit rose without a lecture. A template holds the shape. A stepped figure shows how the note is built from the numbers.

Research Note Standard is how a tax or accounting question becomes an answer a client can rely on. How the note is written, what it cites, how it is dated, and which questions go to a specialist instead. Every claim links to its source. What you have not confirmed is marked, and Flow counts the marks until you answer them. A form lets a client ask a question in the shape you need.

Issues and Decisions Register keeps the open questions per client, who owns each, and when it was last checked. A Register Skill draws it. It is the end of searching old emails.

Worked Example is a close note and a research note for a made-up client, filled in end to end, with the choices explained. A reader learns more from one finished note than from ten rules.

What Flow does for this work

Chat answers from your Standard and your Register. With the Playbook chosen, Chat searches your documents before it replies and links each fact to its file. Ask How do we treat a repair? and the answer comes from the Research Note Standard, with the section named. A new hire gets the same answer you would give. When your documents are silent, Chat says so.

The close checklist is signed in the document. The Monthly Close Method ends in an Approval Card. Eleven checks, each with its owner. The person who closes ticks them, types their name and presses Sign off. Flow writes one signed record beside the month, and History lists it. Change the checklist later and the card asks for a new signature. The old record stays.

A Job keeps a cited IRS page current. Bring the page in with New from Web Page and choose Follow the source. Each Jobs run reads it again and brings changes in where you have not edited. On a quiet week the Job skips without calling a model. A Sources block on every research note marks a source that changed since the note was written.

Field-Notes Diagram draws the month’s numbers to size. Select the paragraph that explains why cash fell while profit rose, and run the Skill. It draws the four numbers as bars, each to its size and printed beside it, with the one the paragraph stresses in colour. A business owner reads it in ten seconds. It waits in Review Changes until you keep it.

A Form takes a client’s question in your shape. The Research Note Standard ends in a Form. What they want to know, what it is for, when they need it, and a checklist of what to attach. Its button is Submit, so the request is recorded beside the document with their name and the day. Nothing arrives in an email thread you have to search later.

A Register that draws itself. The Issues and Decisions Register is drawn by the Register Skill from the open questions in the text. Each row has an owner, a status and when it was last checked. Chat adds a row when a question comes in and updates it when you answer. It is the end of searching old emails.

Your agents can draft the note. With Flow Pro, Settings ▸ General ▸ Your agents opens the folder to the Claude Code or Codex you run in Terminal. It can read the Guide and the month’s tables and propose the close note. The proposal lands in Review Changes under its name. You decide what the client reads.

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 close checklist from 2019, a past client note with the names changed, the IRS 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 Method document. Ideas reads the sections and names a Skill for each, a Workflow Path for the close, a Register for the open questions. 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 Explanation Guide can be written from your Method and your past notes. Repeat until the path is done. See the next document, from his own pages.
6. Review every change. When you merge two checks or rename a document, 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. After a close, open the Playbook, start a folder for the client and drop the month’s statements in as tables. Ask Chat to draft the close note from the Guide, and to mark every line it is unsure about. The Method’s checklist tells you what to confirm before the note goes out. When a client asks a question you had to research, the answer goes in the Register, and the lesson goes back into the Standard. Next month starts from what you learned.

A new hire can read the Method and the Guide on their first day and close their first month the way you would. That is the staffing problem answered one person at a time.

March Statements.mdMarch Close.mdMarch Close Note.mdMarch Close Note.mdResearch Note.mdIssues and Decisions Register.md Imported · 2 to check11 checks open2 claims to check1 change to review1 claim to check1 change to review

Juniper Bakery

March Statements

Proposed

Table

Imported · 2 to check

Juniper Bakery

March Close

Proposed

Approval Card · Sign off

Sign off

11 checks open

Juniper Bakery

March Close Note

Proposed

Chart · Waterfall

2 claims to check

Juniper Bakery

March Close Note

Proposed

Field-Notes Diagram

1 change to review

Juniper Bakery

Research Note

Proposed

Sources

1 claim to check

Juniper Bakery

Issues and Decisions Register

Proposed

Register

1 change to review

01Start the month02Run the close checklist03Explain the close04Draw the numbers05Answer the question06Log it in the Register

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 statements 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 describe your close to Chat in three sentences. 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.