Collections

From cold receivablesto confirmed payment.

Agents that reach out at the optimal moment, negotiate within policy and record every promise, across the whole portfolio in parallel.

Consumer banking and lenders · Central America

A collections officer on a phone call from the office

The starting point

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

0accounts assigned to each officer

0 minper full action: dial, wait, explain, record

0 hto work through the list a single time

0 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.

01Portfolio intake
Daily API load: days late, amount and balance.
02Per-customer analysis
History, effective channel and response hour.
03Outreach and negotiation
WhatsApp or call at the optimal moment.
04Promise recording
Amount, date and reason to the CRM, with a reminder.
05Validation and closing
OCR validates payment. Off-policy cases escalate.

What it uses from Shimli

The pieces that make this case work.

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.

CrediAmigoAgent · actionslive

buscarUsuarioDatabaseLook up the customer by ID

clasificarUsuarioLogicClassify the credit level

requisitosDataValidate approval requirements

aprobacionLogicConditions to approve credit

cuotaMensualComputeCompute the monthly payment

Code InterpreterWeb Search

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.

Flow canvas

Start

BranchContact · 5068…Contact · 5066…Else

AI AgentCrediAmigoDigital assistant · live

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.

AI call · in progress01:24

Customer · Collections+504 ···· Voice

AgentA reminder of your $1,250 payment. Want to defer it?

CustomerYes, in two installments please.

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.

2,608Enviados

2,506Entregados

1,782Leídos

395Rechazados

Sent100%

Delivered96%

Read71%

Measured in production · 2025

$0.0M+recovered in overdue receivableswith AI agents · 2025

0×proven returnrecovered per dollar invested

$0M+in payment promisesrecorded and validated · 2025

0%of queries resolvedwithout human intervention

The outcome

What changes in the operation.

01Portfolio coverage

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

02Cost per action

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

03Traceability

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

Common objections

What teams usually ask before getting started.

Straight answers to the most common questions from credit, collections and technology teams.

Shimli isn't a chatbot. It's a platform to build AI agents that understand context, analyze information, execute tasks in your systems and escalate to a human when needed. A chatbot replies; an agent resolves.

The agent never decides out of bounds. It operates under policies, rules and guardrails defined by your institution, and the final decision can still be human. You define what it can and cannot do.

No. You can start with a controlled pilot and connect progressively via APIs. Shimli doesn't require replacing your current systems, it integrates on top of what you already have.

The next step

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

From $139 a month, with a 14-day trial and self-serve setup. See pricing