AR Follow-Up Drafts for Microsoft Excel · Finance
Overdue-invoice reminders from your Excel aging table, weekly
Every Monday it reads your AR aging table on OneDrive or SharePoint and drafts reminders with exact amounts, sent only after you approve the batch.
Can't be bought yet: waiting for Microsoft Excel approval. It opens for purchase on its own once approved.
- Runs on a schedule
- 3 AI steps
- A person approves before it acts
- About 20 min to set up
Sound familiar?
The job, before and after this agent.
What it feels like today
- “Our AR aging lives in Excel and chasing it is always next week's job.”
- “Writing each reminder with the right amounts and tone takes far too long.”
- “We need a record of who we reminded, and when.”
What you get with the agent
- Past-due totals per customer from the table's exact amounts, added up in code, never by the AI
- Disputed, payment-plan, do-not-contact and no-email customers skipped
- Friendly, firm or final tone by age, with fees or holds only if your policy states them
- One batch approval, then a final amount check before each email is sent to your AR inbox's replies
- Every sent reminder logged as a row in a second Excel table, plus a summary for your AR owner
Before
You filter the aging workbook, write reminders one at a time and keep a separate note of who you chased.
After
Monday's drafts are waiting with correct amounts and tone. You approve the batch and the reminder log fills itself in.
How it works
The whole workflow, step by step.
Every Monday the agent reads the AR aging table in your Excel workbook on OneDrive or SharePoint (up to 150 customer rows). For each customer, AI copies the past-due amounts exactly (the total is then added up in code, never by the AI), skips anyone not overdue, disputed, on a payment plan, marked do-not-contact or without an email, picks a friendly, firm or final tone by age and drafts the reminder with your payment instructions. The whole batch waits in Reviews; once approved, each email gets a final amount check, is sent with replies to your AR inbox and is logged as a row in a second Excel table, and your AR owner gets a summary. It needs the aging as an Excel table and doesn't mark the aging rows themselves.
- TriggerMondays at 8:00
- App callRead your AR aging table
- LogicEach customer
- AI stepDraft the reminder (or skip)
- LogicCheck the math
- Human approvalApprove this week's batch
- Approved:Each approved reminder
- LogicEach approved reminder
- AI stepFinal check on the wording
- LogicCheck before sending
- LogicSend it?
- Passes:Email the reminder
- Held:Held
- OutputEmail the reminder
- App callLog it in the reminders table
- OutputHeld
- LogicCount what happened
- AI stepPrepare the amount sent
- LogicCheck the math
- OutputEmail the summary to your AR owner
This is the workflow that opens in your workspace when you set the agent up. Every step can be edited.
- Step 1Mondays at 8:00Runs every Monday morning, after you've refreshed the AR aging table in the workbook. Set your time zone on the trigger.
- Step 2Read your AR aging tableReads the AR aging table in your Excel workbook (OneDrive or SharePoint): one row per customer with the overdue buckets.
- Step 3Each customerRepeats the draft step for every customer row in the aging table (up to 150 per run).
- Step 4Draft the reminder (or skip)AI copies the overdue amounts from the row, skips customers who shouldn't get a reminder, picks friendly, firm or final by age, and drafts the email with the exact amounts.
- Step 5Check the mathAdds up each customer's past-due buckets in code — not by AI — writes the correct past-due total into the draft and the email, and flags any total the AI got wrong for your AR owner.
- Step 6Approve this week's batchAll of this week's drafts wait in Reviews together. Your AR owner edits any email, sets send to false on any that shouldn't go out, and approves the batch; nothing is sent before that.
- Step 7Each approved reminderRepeats the wording check, the code checks, the send and the log for every draft in the approved batch.
- Step 8Final check on the wordingAI makes a last pass on each approved email for amounts that don't match the aging row (typos made while editing) and mentions of AI only — greetings, payment instructions and your policy's own wording are fine. It must quote the exact sentence it objects to.
- Step 9Check before sendingIn code: drafted to send (not skipped), still marked to send after review, a recipient, a past-due total, and a subject and body with no placeholders left — plus the wording check's verdict. Anything that fails is held, with the reason.
- Step 10Send it?Drafts that pass every check are emailed and logged; the rest are held and listed in the summary with the reason.
- Step 11Email the reminderSends the approved reminder to the customer from your workspace's sender, with replies going to your AR inbox.
- Step 12Log it in the reminders tableAdds a row to your reminders log table: date, customer, tier, amount, recipient and “Sent”.
- Step 13HeldSkipped, set to not send by your AR owner, or stopped by a check; the reason is in the run history and the summary.
- Step 14Count what happenedIn code, not AI: sorts every approved draft by what really happened — sent (email went out), skipped, held (with the reason) or failed.
- Step 15Prepare the amount sentAI only copies each sent reminder's past-due total from the code-counted results, so the amount sent can be added up in code; it never sorts or counts the reminders.
- Step 16Check the mathAdds up the past-due totals of the reminders that were sent in code — not by AI — and writes that amount into the summary.
- Step 17Email the summary to your AR ownerSends the run summary (sent, held, skipped, failed — counted in code — and the amount sent, added up in code) to the person who owns collections.
Example run
What goes in, and what comes out.
Example with fictional data
Comes in
Aging table row for a fictional customer, Northgate Supply: $3,400 in 91+, notes empty.
The agent produces
Past due $3,400. Final-tier draft with your payment instructions, in the weekly batch. Once approved and sent, a row is added to the reminders table with date, tier, amount and recipient.
What you need
Everything it takes to run it.
About 20 minutes from purchase to live. A checklist above the canvas takes you through each step.
Plan
Included in Enterprise; on other paid plans it's $99 once. Agents run live on paid plans, from Basic ($39/mo).
Your AI key
Connect any of 14 AI providers on your own key. Your provider bills usage directly, at cost; we add no markup.
Apps
- Microsoft ExcelAwaiting approval
Checklist
- A paid plan (agents run live on paid plans).
- An AI provider key (Settings → AI Providers).
- Microsoft Excel, connected in Settings → Integrations. Microsoft Excel is waiting for Microsoft's approval, so this agent switches on once it's live.
- The AR aging as an Excel table (Insert → Table) with an email per customer, and a second table for the log.
Setup, about 20 minutes
- Connect your AI provider. The AI steps run on your own key (OpenAI, Anthropic, Google and more). Add one in Settings → AI Providers.
- Connect Microsoft Excel. Connect the Microsoft 365 account that can open your AR workbook (Settings → Integrations → Microsoft Excel).
- Paste your collection policy. Open “Draft the reminder (or skip)” and replace the placeholder with your tiers, payment instructions, late-fee policy and sign-off.
- Pick your aging table. Open “Read your AR aging table” and pick the account, drive, workbook and table (one row per customer, with an Email column).
- Pick your reminders log table. Open “Log it in the reminders table” and pick the account, drive, workbook and the log table (Date, Customer, Tier, Amount, Sent to, Status).
- Add your AR inbox and AR owner. Open “Email the reminder” and enter the Reply-to address, then “Email the summary to your AR owner” and enter who gets the summary.
- Test it with Dry Run. Press Dry Run: the agent runs on sample data with no messages sent and nothing written to your apps.
- Switch the trigger on. Open the trigger, set your time zone and switch the schedule on. It runs every Monday at 8:00 — refresh the aging table before then.
Is it a fit?
Who it's for, and what it won't do.
Built for
- Finance teams working in Microsoft 365 and Excel
- Bookkeepers who keep client aging in OneDrive or SharePoint
- B2B firms collecting on net terms
What it doesn't do
- It never emails a customer before you approve the batch.
- It needs the aging as an Excel table, not loose cells.
- It doesn't mark rows “reminded” in the aging table (Excel's update needs a cell address); it adds a row to your log table instead.
- It doesn't re-check payments live in your accounting system: refresh the table before each run.
- It never invents amounts, invoice numbers, fees or consequences; it reads up to 150 customer rows per run.
We list the limits up front so you can decide before you buy.
Price
$99 one-time
Per workspace. It never renews.
- Included at no extra cost on Enterprise.
- Buying and running it live need a paid plan, from Basic ($39/mo).
- Dry Run costs nothing: simulated AI and app calls, nothing sent.
- AI usage is billed by your own provider, at cost. No AI credits to buy from us.
One-time agent purchases aren't covered by the 30-day money-back guarantee. Refund policy
FAQ
Questions about AR Follow-Up Drafts for Microsoft Excel.
Which apps does it need?
Microsoft Excel. A Google Sheets version, AR Follow-Up Drafts, is also in the marketplace. The agent's page shows whether each app is ready to connect.
Could it email the wrong amount?
It never emails before you approve the batch, never invents amounts or fees, and checks each approved email against its row before sending. Refresh the table before each run, since it doesn't re-check payments live.
What does my workbook need?
The aging set up as an Excel table (Insert → Table) with an email per customer, plus a second table for the log. Setup takes about 20 minutes; it reads up to 150 customers per run.
Is it worth the price?
It's a one-time purchase that never renews, and it turns weekly collections writing into a review. Live runs need a paid plan and your own AI key; Dry Run is free.
What should the workbook look like?
An Excel table (Insert → Table) with one row per customer: Customer, Email, Current, 1-30, 31-60, 61-90, 91+ and Total columns, plus Notes for disputes or payment plans. A second table logs the reminders sent, with six columns: Date, Customer, Tier, Amount, Sent to, Status.
Why a second table instead of marking the row?
Excel's update action needs an exact cell address, which moves when the aging export is refreshed, so each sent reminder is added as a row to a log table instead.
Is anything sent without approval?
No. Every week's drafts wait in Reviews; nothing is emailed until you approve the batch, and you can hold any single reminder by setting send to false.
Can the AI get the totals wrong?
Not in what your customers see: the AI only copies the bucket amounts from the row, and each past-due total is added up in code and written into the email and the log. If the AI's sum was off, the review shows what was corrected (e.g. “past-due total 1830.00 → 1730.00”).
Is this a subscription?
No. AR Follow-Up Drafts for Microsoft Excel is a one-time purchase of $99 per workspace and never renews. The Enterprise plan includes it at no extra cost. Running it live needs a paid plan (from Basic ($39/mo)), and your AI provider bills you directly for usage.
Can I test it before it touches real data?
Yes. Once it's set up in your workspace, Dry Run plays every step on sample data with simulated AI and app calls: nothing is sent and nothing in your apps changes. Switch the trigger on only when you're happy.
AR Follow-Up Drafts for Microsoft Excel is almost ready.
Can't be bought yet: waiting for Microsoft Excel approval. It opens for purchase on its own once approved. Create a free account now and you'll find it on your Agents page.