---
title: "Nubank cuts AI agent rollout time to 4.4 days using simulated customers"
slug: "nubank-cuts-ai-agent-rollout-time-to-4-4-days-using-simulated-customer"
date: "2026-11-18"
category: "FinTech"
author: "Tariq Al-Mansoor"
correspondent: "Tariq Al-Mansoor"
correspondentRole: "Gulf & Capital Correspondent"
readingTimeMinutes: 1
tags: ["Fintech","News"]
originalSourceUrl: "https://linas.substack.com/p/nubank-ai-agents-simulated-customers"
canonicalUrl: "https://aurav.ae/nubank-cuts-ai-agent-rollout-time-to-4-4-days-using-simulated-customer"
publisher: "Aura-V Intelligence (aurav.ae)"
---

# Nubank cuts AI agent rollout time to 4.4 days using simulated customers

> Nubank’s AI team reduced the release cycle for its support agents from 21.2 days to 4.4 days by testing new versions with thousands of simulated customer conversations.

## Key Takeaways (TL;DR)

- Nubank uses a simulator to vet AI agents before live deployment, shrinking rollout from 21.2 to 4.4 days.
- Live A/B tests show the new agent improves self-service rates by 4.9 points and transactional NPS by 36.7 points.
- An open-weight Qwen model replaced GPT-5.2, raising self-service by 8.8 points and cutting p95 latency by 25%.

Nubank announced that its AI team now validates each new support-agent version against thousands of simulated customers before any live rollout, cutting the average release time to 4.4 days from the previous 21.2 days [Source](https://linas.substack.com/p/nubank-ai-agents-simulated-customers). The approach, described in the “Screen Before You Serve” paper, lets an LLM judge score multi-turn dialogues and only promotes agents that meet a pre-set pass criterion to live A/B testing.

In the live test of Brazil’s highest-volume support agent, the new version scored 4.9 points higher on self-service rate and 36.7 points higher on transactional NPS than its predecessor. An open-weight Qwen model later replaced GPT-5.2 after screening across 29 configurations and 16,000 simulated conversations, delivering an additional 8.8-point lift in self-service, stable satisfaction, and a 25% reduction in p95 latency.

Our read: The bottleneck for AI-driven support now lies in rapid, reliable testing rather than model capability; Nubank’s simulator demonstrates a scalable method to accelerate iteration while maintaining performance safeguards.

---

*Original Think-Tank Source: [How Nubank Ships AI Agents in Days, Not Weeks 🤖](https://linas.substack.com/p/nubank-ai-agents-simulated-customers)*
