Skip to content
English
  • There are no suggestions because the search field is empty.

Recipe: Who owes us money, and who pays late?

Use Agentic AI Insights to review accounts receivable by age and payment behavior per customer

Published: 2 November 2026

Audience

  • Finance Team

Objective

This article explains how to review your accounts receivable with Claude or ChatGPT. You see what is outstanding by age, and which customers are a real collection risk and which are just slow.

Prerequisites

The MCP connector is active on your organization. 
        An Admin has enabled the MCP connector for your organization.

Your AI assistant is connected.
        Your AI assistant (Claude or ChatGPT) should be connected to PSOhub.
        See How to Connect Claude to PSOhub or How to Connect ChatGPT to PSOhub.

Steps

  1. Copy the prompt exactly as written:
  2.    Who owes us money, and who pays late? 
       Count only invoices that were sent, and list drafts separately. Show what is outstanding now by days past the due date: not due yet, 1 to 30, 31 to 60, 61 to 90, over 90. Then the ten largest overdue invoices. Keep credit notes separate so they do not flatter the total.

       Over the last [12] months: the average days to pay per customer, worst first, and our days sales outstanding. Split customers into a real collection risk and slow but reliable, and give different advice for each.

       Show this as a dashboard: a header with the scope and date, a one-line verdict with three to five key figures, the findings ranked worst first with the reason and the amount, a table with the rest, what this answer could not see, and three actions with an owner. Use a single HTML page if you can show one, otherwise the same blocks as formatted text. Link every project, customer, person and invoice to PSOhub.

     

  3. Optional: change [12] to any number of months.
  4. Paste the prompt into Claude or ChatGPT and send it.

Result

You get a dashboard with your outstanding invoices by age, the ten largest overdue invoices and each customer's payment behavior over the year. It gives separate advice for real collection risks and for slow but reliable payers.

💡 Tip: Ask a follow-up question, for example:

  • Draft a reminder for the top three.
  • Do the late payers also have thin margins?
  • Which of them still have work running with us?

Related Articles