Hire an AI overdue invoice reminder writer

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A warm reminder that makes paying easy
• A range the customer can realistically pay and proposed terms
• A firm follow-up that states the consequence and keeps the door open

How it does the job well

• Check the current policy and the customer's order or account facts before replying.
• Answer the actual question in the first two lines, then explain.
• Match the customer's tone. Acknowledge the problem once, without grovelling.
• Hand refunds outside policy, legal threats and safety issues to a person.

Mistakes it avoids

• Promising refunds, dates or fixes the policy does not allow.
• Copy-paste replies that ignore what the customer said.
• Closing a ticket without a clear next step.

What a good result looks like

An example, not your task: An invoice is 30 days late and the customer has gone quiet.

• Step 1: warm reminder. A subject line and a letter that assumes good faith, shows how to pay and gives a reason to pay now.
• Step 2: what they can pay. The customer's situation, a realistic range and date, and proposed terms such as a plan or part payment.
• Step 3: firm follow-up. A letter with the facts, the terms, the plain consequence and an open door.
• Hand-back summary. Each step's file, any step not run and why, and every MISSING line in one list.

How the work is checked

• Each step passed its own checks, or the run stopped at the step that failed and says why.
• The steps ran in order, and each one used the result of the one before.
• Nothing was invented to fill a gap. Every gap is a MISSING: line.
• Nothing was sent, published or paid for without a clear yes.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

A second opinion

Before it hands back, your AI reviews the draft the way Robert Collier and John Maynard Keynes would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Write the warm reminder. Writes a warm reminder that assumes good faith, makes paying easy and gives a reason to pay now.
• Send and wait. A pause. Send the reminder yourself. Wait the days you set before going on.
• Find what they can pay. Works out the range the customer can realistically pay and proposes terms they can meet, following Keynes.
• Send and wait again. A pause. Send the proposed terms yourself. Wait the days you set.
• Write the firm follow-up. Writes a firm follow-up that states the consequence, restates the terms and leaves the door open.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id get-a-late-invoice-paid-and-keep-the-customer only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/get-a-late-invoice-paid-and-keep-the-customer/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• The invoice facts: amount, date, what it was for, any part paid
• Your history with the customer and what they have said about the delay
• What you know of their situation and means
• Your own limits: how long you can wait, what discount or plan you would accept

Helpful context (optional)

• The customer's payment history
• Their recent orders, which show whether they still value you
• Your cash position, so the limits are real

Tools and access

• Any good chat AI: Every step is a plan or a piece of writing.
• Your invoicing tool: Shows what is paid and lets you add a payment link to each letter.
• Any good chat AI: Writing a short letter is a task any strong chat AI does well with this skill.
• Your invoicing tool: It holds the real amount, date and pay link, so the letter matches your record.
• A spreadsheet: Hold the parts, ranges and schedule so numbers add up.
• Any good chat AI: Structuring the case and writing the reason is text work.

Functions and deliverables

• Overdue invoice reminder writer: Draft a polite overdue reminder and review ways to pay. Prepare a firmer note with only the next steps you have approved.
  • A warm reminder that makes paying easy
  • A range the customer can realistically pay and proposed terms
  • A firm follow-up that states the consequence and keeps the door open
• Payment reminder letter writer: Share the invoice and customer history. Get a clear, polite payment reminder and a firmer follow-up draft.
  • A short reminder letter or email with a subject line
  • A follow-up for if they do not reply
  • A note on the tone chosen and why
• Deal payment checker: Share the amount asked for and what you know about their finances. Get a payment range, a fixed proposal and what could change it.
  • The ask split into parts with ranges
  • A payment range for them, with assumptions
  • A verdict and a fixed sum or terms
  • What would change the number
• UK late payment reminder writer: Give it a UK business invoice amount and date. Get the script’s interest result, due-date basis and reminder drafts, with scope limits flagged.
  • Interest and fixed fee worked out
  • A dated calculation
  • A sequence of reminder emails
  • Notes on what the law does and does not cover
  Source: Pro Skill Packs.
• Brand profile builder: Share your website. Get a reusable profile covering your products, customers, voice and approved claims, with sources.
  • A folder of eight plain files, from a start file for your AI to a claims list and a change log
  • A tag on every fact, and every claim marked approved, pending or banned
  • A two-sentence diagnosis of your biggest gap, and a list of what's missing and who can answer it
  • A short slice for your next step, if you name one
• Robert Collier: Draft letters or emails using Robert Collier’s recorded approach. Start with the reader’s needs, show proof and make the next step clear.
  • Your problem worked on the way Robert Collier would: their questions, their method, their push-back
  • The answer or the work, in Robert Collier's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• John Maynard Keynes: Examine demand and uncertain plans through John Maynard Keynes’s recorded ideas. Follow spending across the system and ask who bears the cost of waiting.
  • Your problem worked on the way John Maynard Keynes would: their questions, their method, their push-back
  • The answer or the work, in John Maynard Keynes's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• An invoice is 30 days late and the customer has gone quiet.
• A good customer has hit a rough patch and you want to be paid without losing them.
• Your reminders either sound like threats or like apologies.

Limits to check before starting

• The invoice is in dispute, or the customer says the work was wrong: use the Dispute demand letter draft writer workflow.
• You have not billed the customer yet: send the invoice first, with a plain note of the due date.
• You want to sue or hand the debt to a collector: talk to a lawyer or a debt collection service.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the handoff pack. It's a zip with HANDOFF.md plus one skill file for each step.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Tell it your limits first: the last date you can wait and the plan or part payment you would accept. The proposed terms never go past them.
• Paste the invoice facts and your history with the customer. It writes the warm reminder.
• Send it. If nothing arrives in the agreed days, paste what you know of their means.
• Send the proposed terms. If still nothing, send the firm follow-up.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/get-a-late-invoice-paid-and-keep-the-customer for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.