Skip to content
shimli
Sign upBook a demo
Collections

Automated collections with AI agents: from cold receivables to confirmed payment.

Autonomous collections is a process where an AI agent reaches the debtor, negotiates within the institution's policy and records the payment commitment without human intervention. Here it runs across the whole portfolio in parallel, reaching out at the optimal moment.

Consumer banking and lenders · Central America

A collections manager on a phone call by the window of a bright office
The starting point

The team ran the numbers before calling us. It was never a question of effort: it was arithmetic.

420accounts assigned to each officer
6 minper full action: dial, wait, explain, record
42 hto work through the list a single time
40 hin an entire working week

And that list was early arrears only. Whatever went uncontacted in the first days moved to late-stage arrears, where recovery costs several times more.

How it runs

From portfolio upload to the validated payment.

  1. 01Portfolio intake

    Daily API load: days late, amount and balance.

  2. 02Per-customer analysis

    History, effective channel and response hour.

  3. 03Outreach and negotiation

    WhatsApp or call at the optimal moment.

  4. 04Promise recording

    Amount, date and reason to the CRM, with a reminder.

  5. 05Validation and closing

    OCR validates payment. Off-policy cases escalate.

What it uses from Shimli

The pieces behind automated collections.

AI agents

They negotiate within authorized extensions and escalate anything outside policy.

  • How it was used here
  • The extension table the committee approves was loaded: up to two payments, no principal forgiveness.
  • The agent only offers a plan if balance and days past due fall inside that table.
  • Outside it, it doesn’t negotiate: it hands the case to an officer with the full conversation.
Agents/Credit · ApplicationsActive

Tools5

  • buscarClienteDatabaseLooks up the customer by IDin use
  • leerDocumentoReadExtracts the data and checks validityin use
  • validarRequisitosLogicChecks against the product requirementsin use
  • calcularCuotaComputeComputes the instalment from amount and termin use
  • armarExpedienteActionHands the complete file to the analystin use

Limits

CanRequest and validate documentsPrepare the fileCannotApprove the loanHands to a personIf a document does not match

Flow Builder

The whole journey: trigger by days past due, branches by balance and action by channel.

  • How it was used here
  • The trigger is day 3 past due, not month-end.
  • Branches by balance: low amounts go to WhatsApp, high amounts to a call.
  • With no reply in 48 hours, the flow retries through the other channel.
Nodes73Messaging14AI agents9Logic12Integrations21
Portfolio loaded420 accounts Days past due1–30 · 31–90 · +91 Collections agentnegotiates within policy Promise recordedwrites to the core
Collections agentCan doOffer up to 6 daysSend payment linkCannotWaive principalEscalates to a humanIf the balance is disputed

AI voice

A natural-voice call when the amount or the profile calls for it.

  • How it was used here
  • It only kicks in on high balances and customers who never read the WhatsApp.
  • It uses the same script and the same extensions as the text agent.
  • It’s recorded and transcribed inside the same CRM case.
Calls/Marco RíosLive01:24
  • 00:04AgentGood afternoon, am I speaking with Marco Ríos? I'm calling about the instalment due on the 28th.
  • 00:15CustomerYes. I don't get paid until the 15th, I can't cover it all now.
  • 00:27AgentI can register a commitment for the 15th. Does that date work?
  • 00:36CustomerWhat if I pay half today?

Live summary

Reason
Instalment 6 days overdue
Proposal
Half today, balance on the 15th
Next
Send payment link on WhatsApp
Hand to a person

Mass campaigns

Reminders by arrears bracket, with delivery and reads measured in real time.

  • How it was used here
  • One send per bracket: 1 to 15 days, 16 to 30, 31 to 60.
  • Approved utility template, at each bracket’s peak read time.
  • Whoever doesn’t read it enters the one-to-one outreach flow.
PAYMENT REMINDER · JULYCompletedWHATSAPP API1,082 contacts · TEXT
Sent
948
100% of total
Delivered
904
95% of sent
Read
643
71% of delivered
Rejected
134
14% bounce
REJECTION REASONS134 total
Message undeliverable103  77%
Number in Meta A/B test21  16%
Throttled for low engagement9  7%
Other (rate limit)1  1%
DELIVERY FUNNEL
Sent948 · 100%
Delivered904 · 95%
Read643 · 59%
Rejected · out of funnel134 · 14%

Measured in production · 2025

$2.5M+recovered in overdue receivableswith AI agents · 2025
7×proven returnrecovered per dollar invested
$31M+in payment promisesrecorded and validated · 2025
80%of queries resolvedwithout human intervention
The outcome

What changes in collections operations.

Portfolio coverage

The whole portfolio managed in parallel, not just the fraction the team could reach before cases went cold.

Cost per action

Volume grew without adding headcount: cost stopped rising with every new customer.

Traceability

Every agent decision is audited: what it analyzed, what it decided, under which policy and when.

The institution's name is withheld under a confidentiality agreement. We can share a direct reference during the commercial process.

The other three processes

The agent runs the same way on every one of them.

CreditFrom the incomplete file to a decision with everything in view.See the case SupportFrom the message queue to the reply that resolves.See the case OperationsFrom the WhatsApp order to the invoice issued.See the case

What people ask before getting started.

Straight answers on what Shimli is, what it costs, what it integrates with and who is behind it.

Shimli is a platform to build and run AI agents inside a company's operation. An AI agent is a program that understands the context of a conversation, queries the institution’s systems, decides within the policies defined for it and carries the task through to the end. It is built by Sheilim LLC, headquartered in Miami.
A chatbot replies from a script: it recognizes an intent and returns text written in advance. An AI agent understands context, analyzes information, executes tasks in the institution’s systems and escalates to a person when needed. A chatbot replies; an agent resolves.
One plan at $139 a month with every feature on the platform: there are no editions or tiers. It includes 3 human seats and 1 admin, 1 Flow Builder, WhatsApp, Facebook, Instagram and web connection, and unlimited WhatsApp templates. Added separately: an extra instance at $59 a month, an extra Flow Builder at $19, an extra human seat at $9, and AI usage at $49 per 2,450 queries. You can create the account and get into the platform yourself.

Let's build this same case
on your operation.

We review your collections process, identify where the agent fits and define with you the indicators we're going to move. No commitment, nothing to install.

Design my collections case