Purpose
Jobin (AR manager) at Acme Corporation uses AI signals to prioritize outreach without reading months of email history. Signals flag worsening payment behavior early and attach Conversation Summary and AI recommended strategy so Jobin (AR manager) knows exactly what to write in the next follow-up.Acme Corporation — priority risky accounts
These five customers appear throughout the docs as Jobin (AR manager)‘s typical Monday triage list:| Customer | Signal | What it means |
|---|---|---|
| Apex Solutions | Credit risk | Liquidity crisis on the customer side — Jobin (AR manager) escalates to Maria (VP Finance) before aggressive dunning. |
| Mesa Valley Construction | Promise to pay active | Broken payment promise — Jobin (AR manager) sends a firm follow-up via Next Step. |
| Redwood Chemical Supply | Promise to pay active | Broken payment promise — Jobin (AR manager) may Rewrite the draft or Save draft until after a call. |
| Orion Electric Supply | Disputed pricing | Active dispute driving short payments — Jobin (AR manager) pauses program touchpoints and applies the Disputed label. |
| Sterling Logistics | Contract dispute | Adversarial tone, legal involved — Jobin (AR manager) routes internally to Maria (VP Finance); no automated outreach. |
What AI signals are
An AI signal is a pattern detected on a customer account that warrants attention. Signals are generated by analyzing a combination of payment behavior data and communication history. Common signal types include:- Payment behavior worsening — The customer is paying materially slower than their own historical baseline.
- Severe or chronic late pattern — The customer has a persistent history of paying late.
- Accelerating deterioration — Lateness has worsened month over month.
- Balance growing — Open balance is increasing while payment velocity is flat or declining.
- Ghosting — The customer is unresponsive to outreach despite having an overdue balance.
- Churn risk — Open balance has dropped sharply, the customer has gone quiet, and remaining balance is deeply aged.
- Frequent short payer — The customer routinely pays less than the invoiced amount.
Signal severity levels
Every signal is assigned a severity to help your team prioritize:| Severity | Meaning |
|---|---|
| Risky | Immediate attention required. The AI has detected a significant risk pattern. |
| Watch | Action recommended soon. The pattern is concerning but not yet critical. |
| Healthy | No collection action needed. The account is in good standing. |
Conversation summary
The AI reads every email and logged communication in a customer’s thread and generates a concise summary of where things stand. The summary answers:- What is the current status of the collection conversation?
- Who needs to take the next action?
- Is there a commitment date or a predicted payment date in the conversation?
Collection strategy plan
For each customer, the AI generates a recommended next step — either send an email, make a call, or escalate internally. The strategy plan includes:- Recommended action — The specific action type (email, call, or internal follow-up).
- Reasoning — A brief explanation of why this action is recommended.
- Urgency — A score and bucket (Critical, Today, This Week, Upcoming) indicating how time-sensitive the action is.
- Email draft or call script — A pre-written draft with the appropriate tone and template.