.avif)
How Banco Mercantil runs its litigation with the support of Enter’s AI
+12 p.p
-25%
+12 p.p
-25%
+12 p.p
“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.”
12 p.p. increase in performance with Enter's technology
25% reduction in operating costs per lawsuit
+40 dismissals for abusive litigation, 2 malicious prosecution fines and a referral for criminal investigation — in the case of one plaintiff concentrating a large number of lawsuits, mapped by Enter’s AI agents
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.
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:
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's AI was built to deliver accuracy in identifying legal inputs, equipping attorneys with the data foundation they need to build a strategic answer in consumer litigation.
In managing volume litigation, as Mercantil does, classifying the lawsuits creates an operational complexity that escapes manual review. Enter’s AI connects via API to the CNJ (the National Council of Justice’s case database) and to Mercantil’s legal ERP and reads each lawsuit with granularity — identifying the product involved, the claim, and the amount in dispute.
This registry made it possible to study patterns at scale. Analyzing a sample of the bank’s lawsuits, we found that 65% of the fraud concentrates in three main types.
The data fed two paths: in legal, Enter's AI helped the bank match the right legal inputs to each type of scam.
In product, the legal team at Mercantil fed the anti-fraud team with data that drove investment in more preventive measures, acting directly on the root cause of the problem and bringing customers more security.
Enter’s AI agent understands Mercantil’s reality and knows which documents each type of case needs. It reads the case files in full, flags any gaps to the licensed attorney before the lawsuit answer is drafted— checking, 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
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
Armed with the data-backed dossier, Mercantil's legal department started filing a lawsuit answer built around that exact profile. The bank reached more than 40 dismissals for abusive litigation, from 16 different judges, and 2 with a malicious prosecution fine and a referral to the Demand Profile Monitoring Unit (NUMOPEDE).
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.
“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.”
With the patterns mapped and validated by Mercantil's legal team, Enter delivers structured text suggestions that Mercantil's licensed attorneys review, audit, and formalize before filing — covering malicious prosecution, abusive claim splitting, and unrecognized loan disputes.
In that last one, the agent reads the legal inputs in full, helps identify patterns in fund usage in cases of unrecognized contracting or fraud, identifies the month of the contract, and traces what happened to the money.
In one case, for example, the lawsuit was filed 20 months after the contract — and the statement showed the funds had moved to accounts directly tied to the holder, month by month from the beginning.
Enter ran a study of court rulings to map Mercantil's main grounds for adverse outcomes. The analysis showed that the main arguments used can be reversed with legal inputs such as biometrics, geolocation, profile monitoring and device IP address — all of which Enter's technology can put to better use.
With the diagnosis in hand, Mercantil moved fast: the bank attacked the #1 detractor of performance — improving how it used the dossier the bank already had but was not fully exploiting.
“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.”
RESULTS
In less than twelve months of working with Enter, Mercantil measured initial results that show:
- 12 p.p. increase in performance across lawsuits that use Enter’s technology versus the average win rate on lawsuits off the platform, over the same period and on the same subjects
- 25% reduction in operating costs 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 performance 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.”
