> For the complete documentation index, see [llms.txt](https://docs.raiaai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.raiaai.com/use-cases/case-study-kublau.md).

# Case Study: Kublau

**Kublau scales credit-card loyalty operations across Latin America with an Agentic Workforce built on raia**

***

**Snapshot**

| **Metric**                          | **Before raia**        | **After raia (AI Agents)**                           |
| ----------------------------------- | ---------------------- | ---------------------------------------------------- |
| Languages served after hours        | Portuguese only        | **4 languages** (PT-BR, ES, EN, FR) — 24 / 7         |
| Daily card-holder inquiries handled | ≈ 1 800, manual triage | **≈ 4 000**, with **62 %** resolved end-to-end by AI |
| Promotion-eligibility lookup time   | 8 min avg.             | **< 45 s** via chat, email, SMS, or voice            |
| Staffing required to keep pace      | +10 FTEs forecast      | No extra hiring — AI capacity ≈ **8 FTEs**           |
| Time-to-market for a new promo      | 4–6 weeks              | **< 1 week** — upload T\&Cs, clone agent             |

> “raia lets us drop a trained, multilingual agent into any new programme—sometimes overnight. It’s the difference between saying *yes* to a regional launch and turning it down.”\
> — **Senior Product Manager, Kublau Loyalty Platform**

***

#### 1 | Company & Challenge

São Paulo–based **Kublau** delivers card-tracking and CRM platforms for issuers across Latin America. Expanding into promotions & loyalty orchestration revealed three hurdles:

1. **Incentive complexity** — unique tiers, caps, and country-specific rules for each card.
2. **Multilingual support** — card-holders ask in Portuguese, Spanish, English, and French.
3. **Launch velocity** — marketing wanted new promos live in days, but support scripts lagged by weeks.

***

#### 2 | Why Kublau chose raia

* **Language agility** — a single agent answers seamlessly in four languages.
* **Massive document ingestion** — 15 000+ pages of T\&Cs and tickets vectorised in hours.
* **Omnichannel skills** — chat widget, email, SMS, and IVR out of the box; one unified timeline.
* **CoPilot HITL** — 45-day shadow phase let ops staff refine responses to 95 % accuracy.

***

#### 3 | Solution Design

| **AI Agent**             | **Primary Role**                                               | **Key Integrations**             |
| ------------------------ | -------------------------------------------------------------- | -------------------------------- |
| Promo-Concierge Agent    | Explains rules, checks eligibility, pushes tailored offers.    | Vector store, core-banking API   |
| Reward-Tracker Agent     | Shows real-time points / cash-back balance and milestone ETAs. | Rewards ledger API, WhatsApp/SMS |
| Partner-Onboarding Agent | Guides merchants through promo setup, validates SKU feeds.     | Salesforce, DocuSign webhooks    |

Deployment: **6 weeks** from data load to first production chat.

***

#### 4 | Results (first 90 days)

* **≈ 120 000 conversations** handled; 62 % fully resolved by AI.
* Remaining 38 % arrive pre-diagnosed, cutting human handle-time **44 %**.
* **< 60 s** first-response in any of four languages.
* **No new hires** despite 3× promo-launch volume — ≈ US $550 k annual labour saved.
* Card activation rate +9 pp for issuers using Promo-Concierge.

***

#### 5 | Key Takeaways

1. Train on real tickets to capture authentic customer language.
2. Clone agents per country, overlaying only local regs.
3. Give marketing self-serve Packs — new promos go live in under a week.

***

#### 6 | What’s Next

* Voicebot IVR to deflect call-centre load.
* Proactive spend-stimulus nudges when users near reward thresholds.
* Cross-border compliance bot for evolving FX and disclosure rules.

***

**Bottom line:** Kublau’s raia-powered Agentic Workforce delivers a multilingual, always-on concierge that slashes support costs and accelerates loyalty-promo launches across Latin America.

{% embed url="<https://youtu.be/ZFtkC0uIQ2M>" %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.raiaai.com/use-cases/case-study-kublau.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.