How Banco Mercantil runs its consumer litigation end to end with Enter

+12 p.p

win rate on cases managed by Enter

-25%

in average payout per lawsuit

+12 p.p

win rate on cases managed by Enter

-25%

in average payout per lawsuit

+12 p.p

win rate on cases managed by Enter

“Our legal department is increasingly an area that contributes directly to the business, working as a real reducer of demands and expenses.
‍
Enter has enabled us to better categorize our lawsuits and pinpoint their root causes with greater precision, which lets us manage the budget more accurately and put the right preventive measures in place.”

Carolina Marinho do Vale Duarte

Executive Director

SUMMARY

12 pp increase in win rate on lawsuits managed by Enter

25% reduction in average damages paid per lawsuit

+40 dismissals for abusive litigation, 2 sanctions for bad faith litigation and a referral for criminal investigation — in the case of an abusive litigant with many lawsuits, as mapped by Enter's AI agents

Industry

Financial services

Location

Latin America

Learn more

With 80 years of history and 10 million customers, Banco Mercantil is a benchmark in payroll-deductible credit and social security benefit payments for the 50+ public.

The bank operates with over 3,000 employees across in-person and digital channels, including its own app and WhatsApp, with a focus on payroll loan since 2009.

Atua com mais de 3 mil colaboradores em canais presenciais e digitais — app próprio e WhatsApp — com foco no consignado desde 2009.

Challenge

Scale without visibility

Payroll loan is one of the top three most litigated issues in banking lawsuits in Brazil¹. In 2023, the sector saw 585,000 lawsuits on the topic — a 143% growth in three years². By 2024, that volume exceeded 1,700 new lawsuits per day³.

Mercantil handles a high volume of lawsuits every year. With the rise of the bank fraud industry and the growing number of abusive litigants, the bank needed to sharpen its work on prevention, early fraud and scam detection and timely identification of abusive litigants. Specifically, the bank needed solutions to address:

Granular lawsuit classification and root-cause identification of losses — knowing not just that fraud occurred, but also what specific type of scheme was involved and how to improve preventive measures to protect customers.
Access to an intelligence network capable of identifying abusive litigants with a track record in the system.

The core question was:

How do you understand what's inside your lawsuit — and use that insight to make decisions that improve the bank's operations beyond the legal team?

Solution

Enter was hired to operate and improve Mercantil's consumer litigation end to end. The premise is simple: any legal argument is only as strong as the evidence behind it.

Enter was built to deliver accuracy in identifying legal inputs and a top-tier, strategic lawsuit answer in consumer litigation.

01 Categorization of every lawsuit

Mercantil's volume puts manual review out of reach. Enter connects via API to the Brazilian National Justice Council (CNJ) and Mercantil's legal ERP, reading each lawsuit in detail — identifying the product involved, the allegation and the amount in dispute.

A sample analysis showed that 65% of fraud cases concentrate in three types.

That data fed two paths. On the legal side, Mercantil began refining its responses to lawsuits by applying the most relevant legal inputs for each fraud type.

On the product side, the legal team fed the antifraud team with data that drove more investment in preventive measures, attacking the root cause and giving customers more security.

O dado alimentou dois caminhos: no jurídico, a IA da Enter passou a refinar as teses utilizando os subsídios disponíveis de forma mais estratégica para cada tipo de golpe.

No produto, o jurídico alimentou o time antifraude com dados que induziram o investimento em mais medidas preventivas, atuando diretamente na causa raiz do problema e trazendo cada vez mais segurança para seus clientes.

02 Exhaustive review of lawsuit files and legal inputs

Enter's AI agent understands Mercantil's reality and knows which documents are required for each lawsuit type. It reads full lawsuit files, flags any gaps to the partner law firm before the lawsuit answer is drafted and verifies, for example:

Whether the correct contract is attached
Whether the biometric signature matches the identity document
Whether supporting documents are valid and current
Whether the dossier, even if it spans hundreds of pages, demonstrates that the funds were subsequently utilized

03 Fraud and violations detection

Enter's AI agent runs more than 30 violation checks and builds an attorney dossier, consolidating the history of lawsuits against the bank, behavioral patterns and connections to other litigants.

In one case, a single litigant filed hundreds of lawsuits against Mercantil in less than 10 months. Enter's AI agents mapped the full set and identified the pattern:

97% of lawsuits with identical hearing waiver requests
99% had fee waiver requests with no justification
Standardized claim value of US$2,000
13% of the entire litigated base concentrated in 39 CPFs (Brazilian individual taxpayer ID numbers) with four or more claims on the same contracts
Identification of the referral firm linked to the litigant — located through document analysis, including powers of attorney from the digital signature provider

With the dossier in hand, Mercantil began challenging lawsuits using a targeted legal strategy. Together, we secured more than 40 dismissals for abusive litigation from 16 different judges, along with 2 sanctions for bad faith litigation and referrals to NUMOPEDE, a Brazilian judicial agency overseeing legal misconduct.

In the quarter after Enter mapped the pattern, new filings from that abusive litigant dropped by 98% — an estimated US$3.3M in claim value that did not enter the pipeline in that single quarter.

The impact is not limited to the bank. When the structured dossier reaches a judge — with documented patterns, connections between litigants and evidence of coordinated conduct — the judiciary gains information it would otherwise never receive.

Detection at scale does not just protect the bank. It feeds the legal system with organized evidence that allows judges to act beyond the scope of individual lawsuits.

Com o dossiê estruturado, o Mercantil passou a contestar com uma tese específica para aquele perfil. Juntos, chegamos amais de 40 sentenças de extinção por litigância abusiva, de 16 juízes diferentes, e 2 com multa por má-fé e ofício ao NUMOPEDE.

No trimestre seguinte ao mapeamento, os processos provenientes da litigância abusiva detectada caíram 98%— uma estimativa de R$16,6MM em valor de causa que deixou de entrar em um único trimestre.

O efeito não fica restrito ao banco. Quando o dossiê estruturado é apresentado ao juiz —com padrões documentados, conexões entre litigantes e evidências de atuação coordenada — o judiciário passa a ter informação que, de outra forma, não chegaria organizada até ele.

A detecção em escala, portanto, não só protege o banco. Ela alimenta o sistema com evidências que, organizadas, permitem ao judiciário ir além da sentença individual.

“With Enter, we've been able to optimize the use of legal inputs with a strategic approach to consumer litigation, correlating the legal theory, the inputs and the specific type of fraud scheme or allegation. It lets our team operate strategically, increasing wins and reducing costs.”

Luiz Bolognani

Manager of Civil Litigation and Judicial Collections

04 AI-customized lawsuit answers for each lawsuit type

With patterns mapped, Enter develops specific legal theses for each lawsuit type, which are reviewed and audited by partner law firms before filing. These include abusive litigation, abusive claim splitting and challenges to allegations of unauthorized loans.

For that last one, the agent reads the legal inputs in full, helps identify patterns in how funds were used in cases of unrecognized contracts or fraud, identifies the contracting month and tracks what happened to the money. In one case, the lawsuit was filed 20 months after signing, and bank statements showed the funds had been transferred to accounts directly linked to the account holder, month by month from the start.

05 Product improvement driven by AI analysis of court rulings

Enter ran a study of court rulings to map the main grounds for Mercantil's losses. The main arguments used can be reversed with legal inputs like biometrics, geolocation, profile monitoring and device IP address — all of which can be better deployed through technology.

Mercantil moved fast with the diagnosis: it addressed the top win-rate detractor with better use of the dossier the bank already had but was not exploiting in full.

“One of the studies Enter produced for Mercantil delivered a stratified view of a sample of our lawsuits with fraud or scam allegations, which let the bank put more accurate preventive measures in place to improve customer experience and security.”

Carolina Marinho do Vale Duarte

Executive Director

RESULTS

In less than twelve months of working with Enter, Mercantil measured initial results that show:

12 pp higher win rate on lawsuits managed by Enter versus the average win rate on lawsuits handled outside the platform, in the same period and across the same subjects
25% reduction in average damages paid per lawsuit
For the abusive litigant case: 40+ dismissals without merit, 2 sanctions for bad faith, and a 98% drop in new filings from that litigant in the following quarter

‍

“12 pp more wins and a 25% reduction in average damages paid per lawsuit are results that meaningfully impact both the legal department's and the bank's bottom line.”

Rafael Perri

Manager of Legal Controllership and Intelligence