Accounts Receivable Risk Analyzer Prompt

A simple prompt that scores client payment risk using everyday data, flags early warning signs, and gives clear follow‑ups by risk tier.

Workflow Stage:
Media Type & Category:
Save Prompt
Prompt Saved

Prompt overview

  • Builds a multi‑factor scoring model from simple inputs most teams already track.

  • Classifies clients into Low/Medium/High/Critical risk with concrete criteria and playbooks.

  • Sets monitoring cadences, early warning signals, and relationship‑safe collection tactics.

Quick Specs

Variables to fill

  • Business type/industry: {industry}

  • Standard payment terms (e.g., Net 30): {terms}

  • Client base characteristics (SMB/enterprise, domestic/international, seasonality): {clients}

  • Current payment tracking (invoicing tool, spreadsheets, AR aging): {tracking}

  • Biggest collections challenges (short text): {challenges}

Example variables block (copy and edit)

  • {industry}: B2B SaaS

  • {terms}: Net 30 with 5‑day grace

  • {clients}: SMBs in US/EU, usage‑based billing, quarterly seasonality

  • {tracking}: Stripe + AR aging report; notes in CRM

  • {challenges}: invoice disputes surface after due date; approval bottlenecks

Prompt template


Act as an expert financial risk analyst and collections specialist with 15 years of Fortune 500 experience in AR analytics. Build a practical, multi‑factor model to predict late payments using data most businesses already collect. Provide clear risk tiers, early warning indicators, and tailored playbooks that protect relationships while improving cash flow.

Inputs

– Business type/industry: [industry]
– Standard payment terms: [terms]
– Client base characteristics: [clients]
– Current payment tracking methods: [tracking]
– Biggest payment challenges: [challenges]
Output format (return this only)

A) Heading: Data You Already Have (Use These Fields)

– Invoice data: invoice date, due date, amount, itemized lines, currency.
– Payment history: days sales outstanding (DSO), average days past due (DPD), % invoices paid late, largest historical delay, write‑offs.
– Behavior signals: time to first reply, reschedule frequency, dispute frequency, approvals chain length, bounced emails, meeting no‑shows.
– Contract terms: prepayment %, discounts, credit limits, auto‑pay on/off.
– Operational signals: product usage drop, unresolved support tickets, project milestone slippage.
– External but free signals: website outages, leadership changes on LinkedIn, public funding/layoff news.
B) Heading: Multi‑Factor Risk Score (0–100)
Assign points per indicator; higher = riskier. Default weights (adjust per [industry]):

– Historical payment behavior (max 30)

Average DPD last 6 invoices: 0 pts (≤0), 10 (1–7), 20 (8–15), 30 (≥16).

Invoice concentration (max 10)

– Any invoice > 20% of monthly revenue: +10.

Disputes and credits (max 10)

– ≥2 disputes last quarter or credits > 2% revenue: +10.

Communication lag (max 10)

– No reply within 5 business days to invoice/reminder: +10.

Usage/engagement decline (max 10)

– 30‑day usage down ≥25%: +10.

Approvals/PO risk (max 10)

– Multi‑step approvals or missing PO: +10.

Term risk (max 10)

– Terms > Net [terms] baseline by +15 days or no auto‑pay: +10.

External strain (max 10)

– Public layoffs/negative news in 60 days: +10.

Score = sum of points (0–100).

C) Heading: Risk Categories and Criteria

– Low (0–19): on‑time or ≤3 days late; stable usage; quick comms.
– Medium (20–39): occasional 4–10 day delays; minor disputes; slower comms.
– High (40–69): frequent 10–20 day delays; approvals/PO issues; usage trending down.
– Critical (70–100): >20 day delays or invoices > 30 days past due; disputes unresolved; negative external signals.
D) Heading: Early Warning Indicators (Monitor Weekly)

– Average DPD rising 3 weeks in a row.
– First‑response time slips beyond 3 business days.
– Usage or purchase volume down > 20% month‑over‑month.
– Repeated “awaiting approval” status beyond 10 days.
– Contacts changing roles or leaving company.
– New dispute within 7 days of invoice.
E) Heading: Playbooks by Risk Category
Use bullets in this pattern: Action — Goal — When — Owner — Script/Notes.

Low risk

– Auto‑pay enrollment — keep DPD ≤ 0 — onboarding — AR — “We can set auto‑pay; cancel anytime.”
– Early pay incentive 1% 10 Net 30 — speed cash — renewal — Sales/AR — cap discount to margin.
Medium risk

– Pre‑due reminder cadence (7/3/1 days) — prevent slips — every invoice — AR — short, friendly messages.
– Approval map capture — remove bottlenecks — first delay — CSM — “Who approves POs and payments?”
– Small credit limit — cap exposure — at contract — Finance — limit growth until on‑time streak.
High risk

– Split invoices/milestones — reduce friction — before project start — Sales/PM — 40/40/20 terms.
– Payment plan with written schedule — collect gradually — when >15 DPD — AR — e‑sign agreement.
– Escalation to senior sponsor — unblock approval — at >10 DPD — Exec — keep relationship tone.
Critical risk

– Stop‑work/hold shipment clause — protect cash — at >30 DPD — Ops — send formal notice.
– COD/prepayment for new orders — prevent exposure — immediately — Sales — allow reversion after 3 on‑time payments.
– Collections partner last resort — recover — at >60 DPD — Finance — provide documentation pack.
F) Heading: Monitoring Protocols and Cadence

– Weekly: risk score refresh; top 10 risers review; new disputes scan.
– Biweekly: call‑down on High/Critical accounts; confirm approval chain and payment date.
– Monthly: AR aging reconciliation; root‑cause analysis for top 5 delays; update weights if false positives.
– Quarterly: evaluate terms (Net 30 vs. Net 45) and auto‑pay penetration; set targets.
G) Heading: Dashboard and Thresholds
Provide a small table: Metric | Target | Trigger

– % invoices on auto‑pay | ≥ 60% | < 50% triggers outreach campaign
– Weighted Average DPD | ≤ 5 days | ≥ 8 days triggers Level‑2 playbook
– AR > 30 days past due | ≤ 8% of AR | ≥ 12% triggers exec review
– Dispute rate | ≤ 1% | ≥ 2% triggers invoice QA audit
H) Heading: Documentation Checklists

– Keep for each client: signed MSA/SOW, PO/approval trail, invoice copies, reminder history, call notes, payment promises, dispute evidence, usage reports.
– Standardize note fields: promised date, reason for delay, next action, owner.
I) Heading: Implementation in 30 Days

– Week 1: backfill DPD and disputes; set baseline scores; pick top 10 high‑risk.
– Week 2: implement reminder cadence and approval maps; launch auto‑pay push.
– Week 3: negotiate payment plans; introduce milestone billing on new work.
– Week 4: review metrics; adjust weights; document SOPs.
Rules

– Keep language simple; use USD where dollar figures are referenced.
– If inputs are missing, proceed with the default weights above and label assumptions.
– This is educational guidance, not legal advice; confirm contract remedies locally.

Sample Output:

 

 

How to use

  • Fill in variables for industry, terms, client profile, and tracking tools.

  • Paste recent AR aging and note any disputes; run the prompt to score accounts.

  • Work the playbooks by tier, starting with Critical and High, and track results weekly.

FAQ

  • Do I need paid credit checks?
    No. The model relies on behavior and internal data; add credit checks only for large exposures.

  • How do I avoid damaging relationships?
    Use friendly scripts, clear promises, and milestone billing; reserve stop‑work for repeated breaches.

  • Can weights change?
    Yes. Tune weights quarterly based on which factors best predicted lateness in your data.

Compliance and notes

  • Educational template only; not legal advice. Review contract terms before pausing work or shipments.

  • Do not share confidential client details in public tools.

Revision history

  • v1.1 – Added scoring weights, dashboard thresholds, and 30‑day rollout – 2025‑10‑13

LEAVE A REPLY

Please enter your comment!
Please enter your name here

Most Used Prompts

Related articles

Alarm application with C Windows Forms code and image

Learn how to build a user-friendly alarm app with clear notifications.

AIVA Project Development Plan for AI Vision Agent on Ethereum Blockchain

Learn how to structure and execute a multi-phase AI vision project effectively.

Smooth Vertical Aim Adjustment Script for Precise Headshots in Game

Enhance gameplay by improving shooting accuracy with precise vertical adjustments.

Aim Assist Feature Definition Types Ethics and Implementation Guide

Explore practical strategies for designing and implementing ethical aim assist systems.