The board pack that remembers your judgment: a blueprint for Finance Advisory

You are the finance person for companies too small to have one full time. You close the month, build the pack, and sit with the board to say what the numbers mean. The cadence never changes. The judgment is what they pay for, and today it lives in your head, in a spreadsheet only you understand, and in whatever last quarter’s deck happened to say.

This page is a blueprint for a Flow Playbook that carries that judgment. 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

Finance teams have adopted AI, and then stalled. Gartner found that 59 percent of finance functions used AI in 2025, almost unchanged from 58 percent in 2024 after a jump from 37 percent the year before. At large companies the picture is further along. Deloitte’s CFO Signals found 93 percent of CFOs say their business uses AI, and 44 percent use it for planning and budgets. In FP&A teams, the people who build the packs, only 23 percent use AI at least monthly, while 40 percent are still testing it.

The reason for the stall is trust. A 2026 survey of 270 CFOs by Datarails found finance teams spend 26 percent of their week checking or correcting AI output, and only 5 percent would trust AI to produce a board-ready report without a person reviewing it. The draft is fast. Knowing whether it is right is not. A method that carries your rules, your thresholds and your review is the thing missing from the AI tools these teams already pay for.

The demand for people like you is rising while the supply of finance talent falls. CFOs expect to grow headcount by only 2 percent in 2026, down from 6 percent, while three in four raise their technology budgets. Accounting degrees fell 6.6 percent in a year. One marketplace for part-time executives reported demand for fractional roles up 149 percent year over year, with finance the most wanted role. And the custom GPT some advisors used to package their method 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. One marketplace’s numbers are one marketplace. 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 your month from close to board. An isometric figure maps the path.

Monthly Reporting Method is the heart of it. The steps from a closed ledger to a board pack, who does each one, and what must be true before the pack goes out. The sign-off is an Approval Card, so the record of who approved what stays with the month.

Judgment Rules is what clients pay for. How you read gross margin, cash and runway. The thresholds you act on, and what you do when one is crossed. Where each rule came from, with a link. The rules you are still testing are marked, and Flow counts the marks until you settle them.

Scenario Model Template builds low, base and high cases from ranges the reader states, and says which decision the model is there to inform. A Scenario Model Skill draws it. Charts draw themselves from the rows.

Board Pack Template is the pages, their order, and the one paragraph at the front that says what happened and what you recommend. A stepped figure shows a reader how the paragraph is built from the numbers.

Worked Example is one pack for a made-up company, filled in end to end, with the judgment calls explained. A reader learns more from one finished pack than from ten rules.

What Flow does for this work

Chat answers from your Judgment Rules. With the Playbook chosen, Chat searches your documents before it replies and links each fact to its file. Ask When do I flag runway? and the answer is your threshold, from your rule, with the file named. A client who brings the Playbook in gets the same answer from the same rule. When your rules are silent, Chat says so.

A Job keeps the pack’s tables current. A Job can keep a table or a chart current instead of a section. Point the cash table at the month’s export and each run asks only for its rows, leaving the header and the chart’s type as you wrote them. On a month when the source has not changed, the Job skips without calling a model and says No change in its sources.

Scenario Model draws the cases from your ranges. Select the section that states the hiring plan and its ranges, and run the Scenario Model Skill. It draws low, base and high cases and names the choice the model is there to inform. It uses only the numbers in the text and refuses to guess the rest. The result waits in Review Changes.

A Chart draws the cash bridge. A waterfall from last month’s cash to this month’s, drawn from the table’s rows, sits in the pack as a chart block. Put it beside the front paragraph in a Hero and the two stay side by side on every screen, in a Chat reply and on a published page.

The board signs the pack inside the document. The Monthly Reporting Method ends in an Approval Card. Tick what was delivered, type a name, press Sign off. Flow writes one signed record beside the document, and History lists it. Edit the pack after the signature and the card asks for a new one. The old record stays.

A rate page or a filing calendar follows its source. Bring in the page you check every month 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. Your Judgment Rules cite the current figure, not the one from the quarter you wrote them.

Your agents can prepare the first draft. With Flow Pro, Settings ▸ General ▸ Your agents opens the folder to the Claude Code or Codex you run in Terminal. It can read the Method’s reading order and the Rules, then propose the month’s front paragraph. The proposal lands in Review Changes under its name. You decide what the board 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. A past board pack with the company’s numbers changed, the article where you first read a rule you still use, a shared AI chat where you once worked out a threshold. New from Web Page turns a page or a 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 month, a Scenario Model for the cases. 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 Judgment Rules can be written from your Method and your past packs. Repeat until the path is done. See the next document, from his own pages.
6. Review every change. When you drop a page from the pack or rename a rule, every document 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. On close day, open the Playbook, start a folder for the client and drop the month’s numbers in as a table. Ask Chat to draft the board pack from the Template, applying the Judgment Rules, and to mark every line where a rule fired or where it was unsure. The Method’s sign-off tells you what to confirm before the pack goes out. When a board member asks a question you had not planned for, write the answer back into the Rules. The next month starts from what you learned.

The Judgment Rules also answer the trust problem. When a client asks what the AI did and what you checked, the rules are written down, dated and the same for every client.

March Trial Balance.mdMarch Board Pack.mdMarch Board Pack.mdMarch Board Pack.mdMarch Board Pack.mdJudgment Rules.md Imported · 2 to check1 claim to check1 change to review1 change to reviewSigned off2 documents changed

Pelican Tools

March Trial Balance

Proposed

Table

Imported · 2 to check

Pelican Tools

March Board Pack

Proposed

Callout

1 claim to check

Pelican Tools

March Board Pack

Proposed

Scenario Model

1 change to review

Pelican Tools

March Board Pack

Proposed

Chart · Waterfall

1 change to review

Pelican Tools

March Board Pack

Proposed

Approval Card · Sign off

Sign off

Signed off

Pelican Tools

Judgment Rules

Proposed

Change Summary

2 documents changed

01Start the month02Read the numbers03Run the cases04Draw the bridge05Sign the pack06Write the lesson back

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 numbers stay in their own folder on your Mac.

When you change a threshold and 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, or Word, Excel and PowerPoint files for the board. 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 month 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.