|
TUE · OCT 6 · EDITION |
Build a client advisory agenda from a period-end export
Most advisory meeting prep is the same work every period - pull the financials, find the variances, decide what to raise. This workflow hands the pattern-spotting and first-draft talking points to an AI assistant, then puts the accountant back in charge for the figure check, the client context, and the follow-up items no export can surface. It is built for accountants who are already doing this work manually and want to cut the drafting time without cutting the review step.
BUILD WITH AI
How to use an AI assistant to prep client advisory meetings faster
This workflow turns a client's period-end financial export into a structured advisory agenda draft in under 30 minutes. The assistant handles the pattern-spotting and drafting; you handle the judgment and the number check.
1 |
Export the client's current-period P&L and balance sheet as a CSV or copy the table directly from your accounting system - no PDF, no reformatting yet. |
2 |
Open a second tab with the prior-period equivalent so you have both periods ready to paste side by side. |
3 |
Paste both tables into your AI assistant with a clear label: 'Current period:' above one block and 'Prior period:' above the other. |
4 |
Send this prompt exactly, filling in the bracketed fields: 'You are helping an accountant prepare for a client advisory meeting. The client is a [industry type] business. |
5 |
Review the assistant's variance list against both source tables - confirm each figure and direction is accurate before reading any further output. |
6 |
Use the draft talking points as a starting structure; edit for client context, add any open items from your notes, and remove anything the assistant flagged that you already know has an explanation. |
7 |
Add a short 'items to follow up' section manually based on your own knowledge of the client's situation - this is the part the assistant cannot supply. |
8 |
Save the finished document as the pre-meeting agenda and share it internally or use it as your own reference notes. |
WORKED EXAMPLE
In practice
A bookkeeping client in professional services has just closed the month. The accountant has exported the current-month P&L and the prior-month P&L as two separate copied tables, ready to paste.
What came back. The assistant returned a ranked variance list with five items, flagged subcontractor costs as up more than 15 percent, and produced four talking points including one about gross margin compression. One talking point cited a specific payroll figure that was actually the total compensation line, not payroll alone - the label in the source data was ambiguous and the assistant picked the wrong interpretation.
How it was checked. The accountant traced each figure in the talking points back to the corresponding row in the exported tables and corrected the payroll reference before the meeting.
A constructed example. The prompt is usable as written; the figures show the shape of a result, not a measured one.
WHEN TO USE IT
| WHEN NOT TO
|
SPONSORED
GO DEEPER
Go deeper
Next issue: more of the tools and shifts reshaping how accounting gets done.
Forward this to the partner still doing it the old way.
An original workflow written for practitioners. Replicate it in a sandbox first; nothing here replaces your review.
How accountants are using AI, automation and smarter workflows to close faster, audit cleaner, and free up time for real work.
Accounting Stack · Audit Friendly Data · Accounting & Finance Jobs
Audit Friendly · modernaccounting.ai