---
title: "Building AI agents for 127 million customers"
url: https://daily.dev/posts/building-ai-agents-for-127-million-customers-yk2dcgusz
source_url: https://building.nubank.com/building-ai-agents-for-127-million-customers/
type: article
source: "Nubank"
published: 2026-03-23T16:44:32.916Z
updated: 2026-03-23T16:45:05.141Z
tags: ["llm", "fintech", "ai-agents", "rag"]
reading_time: 1
upvotes: 1
comments: 0
language: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Building AI agents for 127 million customers

**[Nubank](https://daily.dev/sources/nubank)** · 1 min read · 1 upvotes · 0 comments

## Summary

Nubank's engineering team shares five hard-won lessons from building production AI agents for 127 million customers. Key insights include: adopting an evals-first approach using TNPS and LLM-as-a-judge instead of traditional NPS; defining agents through the ReAct paradigm with distinct prompt, tool, and data layers; using automated prompt optimization (DSPy, Japa) instead of hand-written prompts; avoiding fine-tuning until frontier model capabilities are exhausted; and moving deterministic business logic into composite tools rather than relying on LLM reasoning. The post also covers automated simulation and red-teaming for pre-production validation.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://building.nubank.com/building-ai-agents-for-127-million-customers/>

---

Tags: [#llm](https://daily.dev/tags/llm), [#fintech](https://daily.dev/tags/fintech), [#ai-agents](https://daily.dev/tags/ai-agents), [#rag](https://daily.dev/tags/rag)

[View this post on daily.dev](https://daily.dev/posts/building-ai-agents-for-127-million-customers-yk2dcgusz)