# How NG.CASH uses Decagon

**35 additional agents**: “Avoided the need to hire over 35 additional agents while managing growing inquiry volumes”

As published on [decagon.ai](https://decagon.ai/case-studies/ng-cash), July 2026. Captured by usedby on 2026-10-07.

- Company: [NG.CASH](https://www.usedby.ai/companies/ng-cash.md)
- Tool: [Decagon](https://www.usedby.ai/tools/decagon.md)
- Teams: Customer Support

## What the story says

NG.CASH, a Brazilian digital bank for Gen Z, uses Decagon AI agents on chat and email to handle customer support inquiries, replacing a decision-tree support platform. The agents let it absorb growth in inquiry volume without expanding the support team.

Summary written by usedby from the source page, in English. The figures are those of Decagon and NG.CASH, not ours.

> Optimized staffing – Avoided the need to hire over 35 additional agents while managing growing inquiry volumes, leading to substantial cost savings.

- **70%**: “Improved deflection rate - Increased to 70% with Decagon’s AI Agents, significantly reducing manual escalations.”
- **six million**: “Following NG.CASH’s acquisition of Z1’s customer base, the company reached six million accounts, without increasing its customer support team or requiring excessive preparation time.”
- **13%**: “Low Resolution Rate: Only 13% of inquiries were autonomously resolved, leading to friction in customer interactions, high operational costs, and elevated account closures.”

> Decagon has been incredibly impactful for us. Through our recent acquisition, we scaled our customer base dramatically without having to add to our support team or waste time on complex preparation. Their AI agents have made our transition seamless and efficient while increasing customer satisfaction.
>
> Petrus Ballhausen Arruda, Co-Founder & COO

## What usedby checked

We compared the story with its live page on 2026-10-07.

- Checked: the figure 35 additional agents is printed word for word on the page, near the name of NG.CASH.
- Checked: the passage quoted above is copied word for word from the page, near the name of NG.CASH.
- Checked: the publication date is read from the page’s own metadata, never guessed.
- Checked: NG.CASH uses Decagon. Confirmed line. Latest check across sources: 2026-10-07.
- Not checked: the result itself. We quote it; we did not measure it.

---
Source: https://www.usedby.ai/case-studies/ng-cash-decagon · How we check: https://www.usedby.ai/methodology