by Audra Carpenter

Draft late invoice reminder emails every Monday for your approval

Have Claude Cowork set up a Monday-night agent that drafts late-invoice reminder emails for you to review and send, as the author describes.

What the agent did

Source-reported example · as described by Michel Abood (San Diego), works in a wine-import business (per his own reply on the post); the posts do not name the company; Rundown profile 'michel' links to linkedin.com/in/michelabood; company size not stated

The author, Michel Abood, who works in wine import in San Diego, posted on The Rundown's Workflow Hub that his industry has tight margins and a rudimentary back end, so sending late-invoice reminders was repetitive manual labor.

He says he had Claude Cowork walk him through creating an agent that logs in every Monday night, checks the company's late accounts receivable, and compares the customer names against a Google Sheet list he created.

It uses an email template he provided, adds the contact name from the Sheet, and includes each late invoice's identifying number, amount and due date. The agent puts the emails in his Drafts folder and emails him a report showing which customers were included, how much each one owes, and the totals.

He reviews the drafts, confirms they look good, and sends them himself. His LinkedIn post of 2026-10-12 describes the same workflow (Gmail drafts, final say his).

Both posts attach a screenshot of a report email to himself, dated 10/11/2026 and labeled a test run: subject "TEST Invoice reminders 10/11/2026: 7 draft(s) ready", the line "TEST RUN. Drafts were created for review; the weekly schedule is not affected.", and "7 draft(s) ready in Gmail Drafts," followed by a past-due amount the author blacked out.

Neither post quotes a prompt or shows an example of the customer reminder drafts.

He says this "has saved me about an hour every Monday night of tedious, repetitive manual labor" (his own estimate). His LinkedIn post describes "a task that takes me the better part of an hour every week: chasing late invoices."

The report-email screenshot attached to both posts is a test run dated 10/11/2026 that says "7 draft(s) ready in Gmail Drafts"; the 7 drafts are from that test run, not a typical weekly count.

Limitations

Short posts with no prompt and no example of the customer reminder emails, and no measured before-and-after. The time saved is the author's own estimate.

Both posts attach a screenshot of a test-run report email dated 10/11/2026 ("7 draft(s) ready"; a past-due amount is blacked out); it is labeled a test run and says the weekly schedule is not affected, so 7 is not a reported typical weekly volume.

The posts do not name the receivables system or say how the agent logs in, how long the weekly job has run, or whether the reminders got invoices paid.

He says he reviews and sends every reminder himself; he also says everything he builds has "a human in the loop until I am 100% sure there won't be some embarrassing or problematic error" (his reply on the post).

The Rundown post's text says the emails go to a Drafts folder and does not name the email service; the attached screenshot and his LinkedIn post say Gmail. The posts do not name his company. The model is not stated.

Try it in your business

What you'll need

Claude Cowork; access to your list of overdue invoices (the post does not say how); a Google Sheet of customer names and contact names; your own reminder email template; access to your mailbox so drafts can be saved; your own review before anything is sent.

The agent reads the company's late-receivables list, a Google Sheet and an email template and leaves drafts in the author's mailbox, so it works across several of his tools. The post does not say how those connections are made. The label is our reading, not something the author states.

Starting prompt

The author didn't publish their prompt (read both posts, the author's reply and the attached screenshot; the steps are listed but no prompt is quoted), so this is our adaptation.

How ours differs from the original setup: Same execution agent (Claude Cowork). The author published no prompt, so this is our starting prompt built from his step list.

It asks for the report in the conversation instead of the email the author's agent sends him, adds a list of overdue customers missing from the Sheet and unreadable items, and says to change nothing in the invoice system. The system, sheet and template are blanks for you to fill in.

Our suggested starting prompt — not the author's original · untested
Every Monday evening, open [my receivables or invoice system] and list invoices that are past due. Match each customer against my Google Sheet [name] (customer name, contact name). For each match, draft a late-invoice reminder from my template [paste template], using the contact name and each overdue invoice's number, amount and due date. Save the drafts in my Drafts folder. Do not send any email. Then give me a short report: customers included, amount owed per customer and the total, plus any overdue customer who is not in my Sheet and anything you could not read. Do not change or mark anything in the invoice system; I review and send the drafts myself.

Replace the [bracketed] parts with your own files and tools.

Get examples like this every Tuesday and Friday

Practical ways to put AI agents to work in your business. We check the original sources, explain the setup and point out the limits. Free.

Unsubscribe any time. Privacy policy

Report a correction

Related use cases

Categorize bank transactions, number vouchers, match payments to invoices and draft year-end accounts

Have Claude Cowork do the bookkeeping from a bank statement and spreadsheet, match payments to invoices and draft year-end accounts, as the author describes in a LinkedIn post that he says Claude wrote.

Claude Cowork · Finance and bookkeeping · Prompts and files · Source: Andrew Blumson, founder of Adevious, a UK AI training and software business (per adevious.co.uk); the business whose bookkeeping the post describes is not named · October 24, 2026

Screen potential clients against your ideal-client criteria and log the scores in a spreadsheet

Have Claude Cowork screen potential clients against your ideal-client criteria and log each score with a link to its proof in a spreadsheet, the agent the author describes.

Claude Cowork · Sales · Prompts and files · Source: Soon Lai (@soonlaii), fractional CTO and founder of Troolla Tech, which sells AI and fractional-CTO services to founders (per his X bio and troolla.com) · November 13, 2026

Stage bookkeeping entries from receipts and bank rows for owner approval

Have Claude Code or Codex work through a bookkeeping backlog: read receipts and invoices, propose accounts and VAT, match bank rows, and stage draft entries that wait for your approval before anything is posted.

Claude Code and Codex · Finance and bookkeeping · Connected apps · Source: Philip Eriksson, co-founder of Igdrasil (Swedish bookkeeping platform), writing about his own companies · September 27, 2026