How Enter helped Nubank bring operational efficiency to consumer litigation

For each case, Enter activates over 30 integrations via APIs provided by Nubank to gather all relevant case information at scale. Our AI agents thoroughly review the data to verify the consistency of the claimant's narrative and distill scattered facts into a single, clear, actionable document for the legal team.

Key data collected includes:

• Call recordings and service logs, comparing what the customer claims in the complaint with what they actually reported to Nubank
• Customer communication history, including calls, chat and email
• Customer profile analysis, to verify whether transactions fall within the customer's usage patterns
• Information on the device used in the transaction
• Authentication records (passwords, biometrics, facial recognition)
• Credit and collections data (credit bureaus, debt history, payment records)

‍

In this next step, Enter’s AI agents run more than 30 wrongdoing detection per lawsuit, covering expired documents, tampered proof-of-address records, bar registration status, and other recurring illegal patterns.

Roughly 20% of the lawsuits Nubank receives are tied to abusive litigation patterns. A diagnosis Enter ran uncovered patterns of concentration and coordinated action, shown in the distribution below.

Within this group, just 10 plaintiffs account for more than 38% of the abusive litigation, acting in a coordinated way. The average number of lawsuits per attorney in this group is nearly 50, against 1.5 for a regular plaintiff.

The two worst offenders requested a fee waiver in 100% of their lawsuits and a hearing waiver in more than 97%.

The analysis also uncovered the recurring use of expired documents, shown below, more than 12 years past their expiration date, and proof-of-residence records belonging to third parties, alongside identical initial filings repeated across lawsuits spread over more than 21 states.

Enter’s AI agent maps these patterns in minutes. Running the same analysis by hand would take Nubank’s internal team months.

With the evidence assembled, Nubank's legal team defines the response criteria for each type of lawsuit. Based on those criteria, Enter's AI agents structure parameterized documents that bring together the most relevant facts and evidence — extending what the team can review and act on at scale.

The approach varies by lawsuit. In scam-related claims, for example, the AI identified:

• The device from which the transactions originated
• The existence of biometric authentication by the account holder
• Customer statements in service interactions - audio or text - that confirm the transactions were approved
• The customer's habitual transaction profile and any alerts Nubank issued during the transaction
• Recovery attempts made by Nubank

For lawsuits tied to abusive litigation patterns, legal inputs were structured around three signals: claim recurrence, standardized filings, and the concentration of amounts over time.

In total, more than 400 AI models, with 97% accuracy, support the generation of drafts and parameterized documents that enable Nubank to handle a share of its monthly lawsuits with heavy use of evidence and far less manual effort.