Collections Prioritization & Dunning
Score overdue accounts and propose outreach to compress DSO.
A predictive model scores each overdue account by risk and recoverability, rules assign the outreach strategy for each segment, and a language model drafts the message for each situation. Collectors stop working a flat aging list and start with the accounts that move DSO most.
LLM workflow (rung 4 of 6). A coded control path: chain, router, parallel fan-out, evaluator-optimizer.
Not an agent: the sequence of steps is fixed in advance, so the whole path can be tested end to end.
A language model handles step 3. Rules: steps 2, 4 and 5 · Predictive ML: step 1.
- Autonomy: T2 · Act on exception
- Acts unattended on the confident majority; routes the rest to a human. Human role: reviews only the routed cases.
- How it is governed
- The path is testable end to end. Each step is independently evaluable.
- Anthropic (Claude Certified Architect – Foundations (CCAR-F))Workflow: models and tools on predefined code paths (chaining, routing, parallelization, evaluator-optimizer). source
- OpenAI (OpenAI agent guidance (Agents SDK, Codex, OpenAI Academy))Orchestrating via code, which the Agents SDK calls more deterministic and predictable. source
- Google Cloud (Generative AI Leader)Workflow agents (sequential, parallel, loop) that run steps in a fixed order. source
- Microsoft (AI-901 (Azure AI Fundamentals) and AB-100 (Agentic AI Business Solutions Architect))Sequential and concurrent orchestration patterns, with steps in a set order. source
How Koko classifies AI · the full ladder is taught in AI & Agentic Delivery Foundations.
Synthetic KokoAI figures — a demo fixture, not audited or a guarantee
DSO 70→58 on the $980M AR book frees ≈$164M of cash one time (12 days × ≈$13.7M/day). Recurring ≈$21M/yr = ≈$8M yield on the freed cash + ≈$13M less write-off as the 90+ bucket ($30M) is worked down.
Opens your own Claude with the prompt and KokoAI's overdue accounts receivable pre-loaded as text — no upload, no setup. Tailor it live to your own numbers.
Try it
Illustrative demoKokoAI's $980M AR book, DSO 70. The workflow ranks overdue accounts, drafts dunning, and holds disputes — targeting DSO 58. Edit the inputs to tailor the output — it's baked synthetic data, so nothing leaves your browser until you run it live.
How many highest-impact overdue accounts to work first.
Overdue Accounts Receivable (synthetic sample) — grab the one-pager PDF (the ROI, the data, and the prompt on one sheet) to share or keep, or the raw CSV / Markdown to drag into Claude or Microsoft Copilot. The prompt hand-off above already includes the same data as text.
Synthetic KokoAI demo data — not audited
Drop a PDF, Excel, Word, CSV, or text file (e.g. a 10-Q, an AR aging, an invoice register) and we'll run this use case on it. Your file is read in your browser and never uploaded — only the extracted text goes into your own Claude or Copilot.
Read in-browser · not uploaded · 10-Q/10-K trimmed to financials + MD&A
Workflow
- 1.Predictive MLScore open receivables by overdue risk, balance and customer history.
- 2.RulesAssign each account an outreach strategy by segment (gentle reminder → escalation).
- 3.Generative AIDraft tailored dunning communications per segment.
- 4.RulesSequence and schedule outreach; track promises-to-pay.
- 5.RulesFlag disputes and route them to the dispute workflow.
Prompt recipe
Given the attached AR aging and customer payment history, rank overdue accounts by expected recovery impact. For the top [N], propose an outreach action and draft the message in the right tone for the relationship and overdue stage. Flag any account with an open dispute for separate handling.
- Customer-facing messages reviewed before send (or capped to low-risk tiers)
- Credit policy and tone guardrails enforced
- Dispute accounts excluded from automated dunning
- PII handling and communication audit trail